PATIENT -CENTERED SYSTEM AND METHODS FOR TOTAL ORTHODONTIC CARE MANAGEMENT
According to one or more embodiments, a computer implemented system for providing an orthodontic care management solution and a method for providing an orthodontic care management solution may be provided. The method may include receiving user data, such as by a user interface associated with an orthodontic care management platform. The method may further include obtaining authorization related information associated with the orthodontic care management solution. Additionally, the method may include determining a treatment plan for the user based on the user data and the authorization-related information. Also, the method may include determining a sequencing plan associated with the treatment plan based on an arrangement of one or more stages of operations associated with the treatment plan. The method may further include displaying the sequencing plan to the user. Further, the method may include receiving feedback data associated with the treatment plan. Additionally, the method may include updating the one or more databases with the feedback data. Further, the method may include performing an artificial intelligence enabled operation for providing the orthodontic care management solution.
This application is a non-provisional application corresponding to the provisional application No. 62/722,319, filed Aug. 24, 2018 pending. This application is also related to applications titled “Modular Aligner Devices and Methods for Othrodontic Treatment” filed on Aug. 23, 2019 and “Modular Orthodontic Devices and Methods Of Treatment”, filed Aug. 23, 2019 the entire contents of which are incorporated by reference herein.
FIELD OF THE INVENTIONThe present invention generally relates to computerized orthodontic care management systems. More particularly, the invention is directed towards enabling an ecosystem for total orthodontic care management using computerized techniques with human interaction input when desired.
BACKGROUND ARTOrthodontics is a branch of dentistry that deals with managing of irregularities related to alignment of teeth, malocclusions, smile correction and other structural and aesthetic deformities related to teeth and smile of a patient. Currently orthodontic care is managed by a professional care provider which is reactive and craft based. This process adds substantially to the cost of care and leads to poor care outcomes. Provision of quality orthodontic care involves focus on certain key dimensions, such as patient centeredness, access to care, efficient therapeutics, patient safety, and clinical effectiveness. Reactive orthodontic care is fraught with errors during all stages of treatment from communication, diagnosis, planning, monitoring and therapeutics. These may be a result of lack of knowledge, cognitive biases, mistakes, slips and lapses, disregard of rules and are driven by practices of omission or commission. Improper design and use of orthodontic appliances further compounds the errors. Improper scheduling of patients and lack of a systematic approach in monitoring adds to the vicious cycle of poor care. These factors singularly or in combination negatively impact the overall treatment quality which includes patient satisfaction, and result in increasing the duration of care, cost of care and also lead to irreversible biological damage to the teeth and its structures. Since the orthodontic care systems available in the art are mostly of reactive type and not process sensitive, it becomes difficult to extract leanings from the patient records and history and use them to provide better care solutions. Currently, orthodontic treatment processes lack application of strategic approaches for optimizing the delivery of highly reliable care within a system that is self-learning, resilient, and anti-fragile. Additionally, in the current systems there is no provision to incentivize superior care providers and/or patients. Also, the orthodontic care systems available in the art provide for limited or zero error management, which requires careful and precise identification of causes and sources of orthodontic errors and then finding ways to prevent and intercept them on a continual basis. Also, currently care practices are limited in creating a generative environment where continuous learning feedback loops are provided to enhance operator and patient skills. Furthermore system wide inefficiencies exist that prevent the optimal and strategic sequencing of operations. Collaborations to provide patient care in a cost effective and efficient way are limited. These limitations add significantly to the delivery, result in providing poor patient care and yet add to escalating costs significantly.
Some of the causes for occurrence of diagnostic and therapeutic errors in clinical practice of orthodontics include the 7 M's: Miscommunication, Misdiagnosis, Misplanning, Misprognostics, Misprescription, Mismanagement, Misadministration, and Misaction. The root cause of these is grounded in design of the system deficits of operator and patient knowledge, inadequate doctor skills, and the violation of rules.
Another cause of poor care is related to the lack of universal measures for reporting poor care practices and outcomes. Additionally corrective mechanisms to ameliorate the deficiencies are limited than outcomes. These factors lead to prevalence of unregulated practices by doctors and unrealistic demands for care by patients In the absence of requisite reporting mechanisms to measure and report patient care outcome and experiences, coupled with the lack of appropriate skill enhancement for doctors and patients, the delivery of optimal care for the patient suffers.
Currently orthodontic treatment practices remain reactive by nature. This model of care increases the care cycle, cost and pain to the patient. The extended care cycle may present safety issues to the patient in terms of increasing the possibilities of damage to the teeth such as root desorption, decalcification and increase the likelihood of tooth cavities. Furthermore, since documentation of patient care is limited, meaningful information regarding patient response to treatment is lost resulting in a lack of learning and memory in the system. These further perpetuate a craft driven reactive approach to care rather than knowledge based proactive generative approach to care. Other deficiencies in the care system that impacts the patient includes the lack of orthodontic fee transparency, the patient ignorance in terms of evidence based treatment practices and an understanding of quality measures for treatment outcome. Furthermore, the patient has minimal involvement in defining, directing and managing their personal orthodontic care. For instance designing the smile they desire to have or the appliance of their choice to meet their individual aesthetic needs or managing their self-care.
In consideration of the deficiencies discussed earlier, there is a need to empower the patient to manage their personal care when appropriate, facilitate doctors to practice cost effective care that is safety driven and error-free and evidence based.
In light of the discussion above, there is a need to overcome the current deficiencies in orthodontic care delivery at every level of the care system for all the stakeholders in order to achieve high reliability, high performance orthodontic care in a science based, learning driven orthodontic care system that is transparent and authentic. This mandates the design and implementation of applicable tools and technology within the framework of a total orthodontic care management ecosystem.
Any discussion of the background art throughout the specification should in no way be considered as an admission that such background art is prior art nor that such background art is widely known or forms part of the common general knowledge in the field.
SUMMARY OF THE INVENTIONThe present invention aims to provide highly reliable and cost effective orthodontic care for a patient with minimal utilization of resources. The present invention discloses a total orthodontic care ecosystem that may provide complete diagnosis, designing, planning, and implementing of patient care, configuring and/or manufacturing therapeutic strategies and manufacturing personalized appliances and evaluating care milestones and outcomes within the framework of a self-learning, smart, and generative orthodontic care management system through the entire life cycle of patient care. Furthermore, the methods and systems disclosed herein are designed to maximize the patients' self-management of their entire care under appropriate conditions.
The total orthodontic care management ecosystem disclosed herein can empower the appropriate patient to self-manage lifelong care and provides error-free and reliable and high-performance evidence based care, transparent and secure ecosystem for orthodontic care management, using computerized care management practices at every level with human input when desired. Such levels may include: appropriateness of care provider, self-care management diagnostics, prognostics based decision making, debasing, continuous evaluation and monitoring of pre-mortem and post mortem analysis, preplanning an evaluation checklist, risk management, risk analysis, care milestones planning, patient motivation and engagement and marketing practices, evidence precision and targeted therapy that mostly deliver determinate, controlled, reliable and predictable force systems with the use of customized, fixed, removable and/or both orthodontic appliances in combination with conventional appliances, and optimizing the sequencing and staging of the therapeutics and devices driven by discrete milestones, condition and response based scheduling, customized manufacturing of appliances, root cause analysis in a double loop learning system complimented with cross channel communication and shared repositories of information and knowledge that facilitate continuous learning for all stakeholders—patient, doctor, device manufacturers, research teams, academia and other third party service providers and provide evidence and performance reports to all stake holders such as but not limited to care outcomes, patient experiences, device capabilities and the like. Furthermore the system is designed to incentivize all stakeholders
In one or more embodiments, a computer-implemented system for orthodontic care management may be provided for managing the entire orthodontic care workflow, from planning till post-active treatment management which includes a unified, bundled, cost effective combinatorial approach to care delivery with optimization parameters considering but not limited to a patients' budget, the maximum aesthetic value, the length of care of each therapeutic strategy and its sequencing and staging. The computer-implemented system may be used to provide an orthodontic care management solution. The system may comprise one or more databases configured to store data of one or more users. The system may further comprise a server including computer code for providing the orthodontic care management solution, wherein the server comprises: at least one memory configured to store the computer code, the computer code further comprising computer executable instructions for performing at least one of one or more functions comprising: receiving user data; obtaining authorization data associated with the orthodontic care management solution; determining a treatment plan based on the user data and the authorization data, wherein the treatment plan comprises one or more stages of operations; determining a sequencing plan associated with the treatment plan, based on an arrangement of the one or more stages of operations associated with the treatment plan; displaying the sequencing plan to the user; receiving feedback data associated with the treatment plan; updating the one or more databases with the feedback data; and at least one processor configured to execute the computer code to provide the orthodontic care management solution.
In one or more embodiments, the computer-implemented system for orthodontic care management may be provided for managing the entire orthodontic care workflow and associated human activities, from planning till post active treatment management.
In one or more embodiments, the computer-implemented system may be fully automated and equipped with the capabilities of interactive human use to design a targeted visual care plan based upon consideration of patient needs and wants, aesthetics, function stability and biological and physical boundaries of the craniofacial complex.
In one or more embodiments, the automated computer-implemented system may be provided with the capabilities of interactive human use to design a targeted plan based upon consideration of nature of tooth movement, minimizing displacement and collision of dental skeletal and facial structures, maximizing planned displacements while minimizing and controlling unwanted displacements to achieve the targeted outcome and using minimal number of therapeutic strategies, modalities and appliances that generate the optimal biological force systems to achieve superior patient care.
In one or more embodiments, the automated computer-implemented system may be provided with the capabilities of interactive human use to design a targeted plan with personalized appliance selection and design based upon consideration of patient needs, patient tolerance, nature of malocclusion, costs, aesthetics and the like.
In one or more embodiments, the automated computer-implemented system may be equipped with the capabilities of interactive human use to alter and update a targeted plan in response to changing patient conditions and update personalized appliance selection, design and subsequent care management and workflow may be provided.
In one or more embodiments, the automated computer-implemented system with the capabilities of interactive human use to design a targeted plan and appliance design, displayed in 2d or 3d modes in AR or VR environments or holographic using text, voice, haptic input or mouse based input and the like may be provided.
In one or more embodiments, the automated computer-implemented system may be equipped with the capabilities of interactive human use to display a targeted plan and appliance design on a user avatar may be provided. The user avatar may include a 2d or 3d model, in an AR or a VR environment, or holographic or using text and voice. In one or more embodiments, the computer-implemented system for an orthodontic care management ecosystem that guides the patient in terms of whether they have suitable characteristics such as but not limited to nature of malocclusion, self-motivation, needs and ability to manage their entire care process or specific phases of treatment on their own but not limited to only post orthodontic care retention management may be provided.
In one or more embodiments, the computer-implemented system may provide for an orthodontic care management ecosystem that guides the patient in terms of establishing an optimized hybrid model that provides optimal access points for professional services in concert with the patient managing their own care may be provided.
In one or more embodiments, the computer-implemented system may provide the orthodontic care management ecosystem that guides the patient in terms of having access to professional care services on an as-needed basis for instance but not limited to when patients self-management of care is not tracking may be provided.
In one or more embodiments, a method for providing an orthodontic care management solution is provided. The method may include: receiving user data; obtaining authorization data associated with the orthodontic care management solution; determining a treatment plan based on the user data and the authorization data, wherein the treatment plan comprises one or more stages of operations; determining a sequencing plan associated with the treatment plan, based on an arrangement of the one or more stages of operations associated with the treatment plan; displaying the sequencing plan to a user on a user device; receiving feedback data associated with the treatment plan; and updating one or more databases with the feedback data.
In one or more embodiments, another method for providing an orthodontic care management solution is provided. The method may include: receiving user data; obtaining authorization data associated with the orthodontic care management solution; determining a treatment plan based on the user data and the authorization data, wherein the treatment plan comprises one or more stages of operations; determining a sequencing plan associated with the treatment plan, based on an arrangement of the one or more stages of operations associated with the treatment plan; displaying the sequencing plan to a user on a user device; receiving feedback data associated with the treatment plan; updating one or more databases with the feedback data; and performing an artificial intelligence enabled operation for providing the orthodontic care management solution.
In one or more embodiments, another method and a computer-implemented system for patient smile correction may be provided, wherein the smile correction is based upon a list of predetermined parameters, including, but not limited to patient wants, patient needs, patient facial anatomy, patient smile anatomy, patient age characteristics, patient psychosocial profile, patient medical and dental conditions and dental characteristics such as tooth shape, size, color, gum tissue level and form, bone characteristics, lip morphology, patient growth pattern functional capacity cost. Further, the method and the computer based system for patient smile correction may either be configured to operate automatically, based on the analysis of patient's facial characteristics, or may be driven but not limited to feedback from a community and patient care outcome and experience relational data bases with evidence driven research.
In one or more embodiments, the method and the system for patient smile management may also be configured to provide automatic feedback to a patient or doctor whether a diagnosis or treatment plan matches standards of orthodontic care or feedback from the professional's community.
In one or more embodiments, the method and the system for patient smile management may include features pertinent to designing of a smile and malocclusion correction, sequencing and staging treatment, appliances selection, monitoring care, evaluating care milestones, checklists and ordering device for manufacturing and tracking.
In one or more embodiments, a method and computer implemented system to automatically or through human interaction approve for the planned care based upon conditional standards can be provided by an authorizing agency. These may include but not limited to government, insurance, or other professional agencies.
In one or more embodiments, a method and computer-implemented system for provision of bids for managing treatment costs based on expected cost of treatment may be provided. The treatment costs may be managed from various financial service providers, such as banks, insurance companies, government agencies, doctors, product manufacturers and the like. In one or more embodiments, the provision of financial services may be done in terms of crypto-currency.
In one or more embodiments, real-time treatment tracking for sharing treatment related data on community platforms may be provided.
In one or more embodiments, a method and computer implemented system to allow for competitive bidding and aggregate demand to provide the best pricing for the patient is implemented. Access to the competitive bidding may be provided but not limited to the financial sector, insurance, care providers, managed care services organizations, and product manufacturers.
In one or more embodiments, a method and a computer-implemented system for an orthodontic care management platform may be provided. The orthodontic care management platform may be configured to provide context and temporal dependency that may include voice-based, image-based, or text-based checklists for the patient or doctor in order to evaluate care progress.
In one or more embodiments, a method and a computer-implemented system for an orthodontic care management and display platform may be provided that allows the care provider or patient to evaluate and monitor care with the display being projected on smart glasses or AR, VR or holographic environment and the display is context-dependent and directs the viewer in a guided context-driven mode to minimize change or attention blindness. Furthermore, the data may be presented in text or speech or video format.
In one or more embodiments, a method and a computer-implemented system for an orthodontic care management and display platform may be provided where the targeted plan can be designed through speech, gesture or haptic interface or text is used to create a target setup or design appliances or manage the patient record. The method and computer-implemented system may include artificial intelligence capabilities for providing an action-to-voice mapping of user commands. The method and computer-implemented system may also include artificial intelligence capabilities for providing a voice-to-action mapping.
In one or more embodiments, a method and a computer-implemented system for an orthodontic care management system is provided, where the display automatically demonstrates the pretreatment malocclusion, the target plan and appliance design, and the current condition of the patient under care and temporally defined future state and automatically registers the various operator defined states by best fit to assess care progress in terms of measured displacement changes and also provide response statistics and analytics against a comparative relational database from historical records of similarly treated patients.
In one or more embodiments, a method and a computer-implemented system for an orthodontic care management where the patient progress is tracked and all stake holders are automatically informed of the progress both visually text or voice may be provided.
In one or more embodiments, a method and a computer-implemented system for an orthodontic care management may be provided where the patient progress is tracked and based upon care progress, the monitoring schedule and patient visits and care related activities are automatically reconfigured based upon assessment of current situation and predicted future states derived from the tracking of history of the patient and universal relational data base of historical records of similarly treated patient.
In one or more embodiments, a method and a computer-implemented system for an orthodontic care management ecosystem may be provided where the patient target plan and appliance design is derived from a relational database, historical records of similarly treated patients.
In one or more embodiments, a method and a computer-implemented system for associating a blockchain enabled database with the orthodontic care management platform may be provided. The blockchain enabled, encrypted and secured and tamper-proof database has security, hierarchical levels of access to various agents, time stamped data records, such as patient dental medical records which may be speech, text, image, video, for providing one or more but not limited to care outcomes, product performance, doctor performance, patient adherence, learning, performance analytics and training recommendations. In one or more embodiments, the blockchain enabled database may be configured for incentivizing patients for use of patient database or any agent contributing to the enrichment of the database.
In one or more embodiments, an interactive user interface for accessing the orthodontic care management platform may be provided. The interactive user interface may be configured to provide a context-based virtual avatar for accessing one or more concierge services which include but not limited to personal coaching and motivation for the patient or doctor, reminder and scheduling services, personal patient care manager and advocate.
In one or more embodiments, the orthodontic care management platform may be configured to provide a rating and feedback management system for evaluating patient experiences of orthodontic care.
In one or more embodiments, the orthodontic care management platform may be configured to provide deep machine learning capabilities for providing a self-generative learning system for orthodontic care management, using data derived from local relational historical databases of patient records, provider records, research centers, manufacturer databases, insurance databases and the like. The learning data derived from such databases may include but not limited to best practices, optimal scheduling, product efficiencies, doctor performance, cost effectiveness errors, poor outcomes records and the like. In some example embodiments, this data may be used to build an artificial intelligence model using the learning data as input and providing auto-recommendations as output.
In one or more embodiments, the orthodontic care management platform may be configured to automatically or interactively design orthodontic treatment planning risk analysis, risk management, treatment sequencing, staging, care monitoring, motivation, activity-based tasking, scheduling services and the like. In some embodiments, the automatic orthodontic care may be provided using the artificial intelligence model described earlier.
In one or more embodiments, the orthodontic care management platform maybe configured to design automatically or interactively the optimized appliance configuration but not limited only to customized appliance but inclusive of “off the shelf” products to that generation of reliable forces consistent with the plan stage and sequence of treatment, cost, aesthetics, ease of use, patients tolerance and medical dental history, providers skills, and evidence
In one or more embodiments, the orthodontic care management platform maybe configured to design automatically or interactively customizable or use a thermal ice and or heat packs that may be incorporated within or in conjunction with a customized intraoral appliance configuration or have a standard configuration that may be incorporated in a standard intraoral appliance separately to be used to manage patient discomfort or to accelerate tooth movement through a process of alternating hot and cold cycles. In some example embodiments, cold and hot thermal packs for intraoral use can be designed as well.
In one or more embodiments, the orthodontic care management platform maybe configured to design automatically or interactively to allow the user, that is the patient or the doctor, to design an appliance configuration automatically and interactively to maximize clinical efficiency effectiveness, minimize dependency on patient cooperation maximize aesthetics which may include but is not limited to shape, form artwork motifs, color, fragrance choice of material or device type removable, fixed, labial and or lingual based upon stage sequence or phase of treatment within the bounds of acceptable mechanical, physical, biological, environmental bio-compatibility design considerations for considered in the design of orthodontic therapeutic or devices.
In one or more embodiments, the orthodontic care management platform maybe configured automatically or interactively to enable the selection and use of customized configurations of fixed orthodontic appliances, and or removable appliances in combination with conventional off the shelf orthodontic appliances to achieve the target care plan care.
In one or more embodiments, the orthodontic care management platform maybe configured automatically or interactively to enable the alteration of the care plan, to accommodate but not limited to the cost of care. additional care services for reauthorization of care use based upon unexpected treatment response or change in patient needs or wants.
In one or more embodiments, the orthodontic care management platform maybe configured automatically or interactively enable the redesign and or sequence the use of customized fixed and or removable appliance configurations based upon unexpected treatment response, a change in patient needs, behavior, doctor preferences, and new evidence.
In one or more embodiments, the orthodontic care management platform maybe configured to automatically interact and refresh provider websites or patient blogs or manufacturer websites to provide testimonials or references or authentic patient doctor experiences.
In one or more embodiments, the orthodontic care management platform maybe configured to allow for levels of access and permission for use based upon patient preferences, doctor's preferences and other stakeholders. The overarching permission key driven by the patient or the patient designate
In one or more embodiments, the orthodontic care management platform maybe configured to allow for monetization by any of the stakeholders based upon but not limited using time quality and value of information sought and number of people accessing information.
In one or more embodiments, the orthodontic care management platform maybe configured to allow for managing patient care post orthodontics and automatically or interactively at regular operator defined intervals to evaluate post treatment changes and select and design personalized customizable orthodontic devices to achieve orthodontic corrective therapy or design and select appropriate stabilizing orthodontic retainer appliance order the appliances for manufacture remotely or onsite for fabrication a and define the optimal cycle of use and project and notify the patient as to the next time for self-evaluation and update the patients calendar and personal motivational avatar
In one or more embodiments, the orthodontic care management platform may be configured to provide customized appliance manufacturing services which may be local or at a remote site.
In one or more embodiments, customized appliance manufacture can be accomplished by but not limited to manual fabrication including but not limited to 3D printing and or 3d milling or any computer driven manufacturing technology.
In one or more embodiments, the orthodontic care management platform may be configured to provide combinatorial configurations of customized orthodontic appliances with the use of “off the shelf products” based but not limited to stage and sequence of planned treatment, cost, efficiency ease of use and of installation, maximizing value, time demands, skill of provider availability of customized appliance manufacturing services, past experiences, evidence and guidance from data mining of relational patient histories.
In one or more embodiments, the orthodontic care management platform may be configured to provide a continuous learning system based upon tracking provider performance and enable the care provider for customized user specific tacit and explicit learning experiences at the point of care or user specified location to enhance professional skills, measure the adoption and implementation of the new skills and report these to the appropriate certifying bodies for credentialing
In one or more embodiments, the orthodontic care management platform may be configured to provide a learning system is designed to build context dependent learner specific needs to develop explicit and tacit skills in an AR, VR or holographic environment with speech haptic and gesture capabilities
In one or more embodiments, the orthodontic care management platform allows for telepresence offsite consultations for the doctor or patient or instructor or any stakeholder.
In one or more embodiments, the orthodontic care management platform may be configured to provide a context dependent continuous learning and motivation system based upon tracking patient progress and adherence to care protocol and provide motivation therapy by using voice, image text or avatars to achieve behavioral modification to enhance their motivation and cooperation, and report progress to the guardian care provider, insurance other stakeholders.
In one or more embodiments, a method and computer-implemented system for evaluating the submitted patient records for completeness and providing the user feedback to correct for the deficiencies.
In one or more embodiments, a method and computer-implemented system for evaluating the submitted patient records including voice text and image video records and alerting patient or user of records and reporting on deficiencies.
In one or more embodiments, a method and computer-implemented system for receiving 2D images and or 3D images photographic laser white light, infrared, thermal images X-ray, MRI, PET scan, ultrasound or dynamic video images of the facial dental structures.
In one or more embodiments, a method and computer-implemented system for receiving images and automatically and or human interaction correcting for distortion coloration size and orientation prior to processing for care planning.
In one or more embodiments, a method and computer-implemented system for receiving multiple 2D images and automatically constructing a 3D image from these sets of images may be provided.
In one or more embodiments, a method and computer-implemented system for receiving a single video image and automatically deconstructing it into multiple static images may be provided.
In one or more embodiments, a method and computer-implemented system for receiving and combining images from different sources into a unified image may be provided.
In one or more embodiments, a method and computer-implemented system for manipulating the GUI interface and objects on display through gesture, speech, text, touch screen and mouse.
In context of this specification, the terms “component”, “member”, “element”, and “portion” are considered to be synonymous and denoting parts of an orthodontic appliance that may be constructed as an extension or modification or deformation of another such part or may be joined with the other part through, but not limited to, chemical adhesive bonding, and or mechanical joining but not limited to crimping, soldering, brazing, welding, screw and thread fastening, snap fitting, press-fitting, loop and hook fastening or using shape memory O-rings such as Nickel-Titanium rings or crimable onlay devices or thermal joining techniques. Different terms have been used for different parts only in order to differentiate them from other such parts to enable clarity of discussion. Moreover, each “component”, “member”, “portion” or “element” may be constructed through combining a plurality of segments wherever modularity in design of the orthodontic appliances is required.
In the context of this specification, the term “deformable” is envisaged to include all kinds of non-zero and at least partially reversible deformations such as, but not limited to, elastic or nonlinear recoverable deformations such as super-elasticity or pseudo elasticity behavior.
In the context of this specification, the term “tooth”, such as a first tooth, a second tooth and a third tooth etc. is envisaged to include one or more teeth, depending upon several factors such as, but not limited to, specific applications, applicability of the orthodontic appliance and strength requirements of the attachments.
In the context of this specification, the phrase “attached to a tooth” such as “attached to a first tooth” or “attached to a second tooth” etc. denotes that the attachment may be obtained in a comparatively fixed or lasting manner such as through use of dental bonding agents, tissue impingement, bone anchoring screws and devices and thread fastening, appliance ligation use etc. or the attachment may be obtained in a comparatively removable manner such as through snap fits in undercuts of the tooth/teeth, frictional fits, such as those achieved in removable orthodontic appliances, aligners, lip bumpers in tubes, or through attachment of permutations of male female attachments.
In the context of this specification, a “polymer material” is any naturally occurring or man-made material having long chains of organic molecules (8 or more organic molecules), with physical and chemical properties of such organic molecules giving the material its desired properties.
In the context of this specification, orthodontic appliances can be defined as to have a number of components, passive structural elements that are a part of an assembly used to guide and/or stabilize teeth, and allow for attachment of active elastic deformable objects that generate forces to move teeth. One end of the elastic deformable objects may not always be directly attached to a member of the passive structural element. The active appliances produce tooth moving forces. As a result of recovery from their elastic deformed state to the initial unreformed near zero state. The orthodontic appliances may also include a jig or a positional device that aids in the precise location and fixation of the orthodontic assembly. This may be a part of the entire monolithic configuration or a separate element that carries the orthodontic assembly together the jig, and does not move teeth. The jig may be removed from the mouth after placing the device but may also be configured in a combinatorial design to provide added functionality such as but not limited to stabilization of a passive device and maintained in the mouth for the duration of care.
At least one example of the invention will be described with reference to the accompanying drawings, in which:
It should be noted that the same numeral represents the same or similar elements throughout the drawings.
DETAILED DESCRIPTION OF THE EMBODIMENTSThroughout this specification, unless the context requires otherwise, the words “comprise”, “comprises” and “comprising” will be understood to imply the inclusion of a stated step or element or group of steps or elements but not the exclusion of any other step or element or group of steps or elements.
Any one of the terms: “including” or “which includes” or “that includes” as used herein is also an open term that also means including at least the elements/features that follow the term, but not excluding others.
The present invention discloses an ecosystem for orthodontic care management which may provide optimal care for a patient in an efficient effective manner. This may provide advantage over existing orthodontic care systems in terms of reduced patient costs, improvised care delivery and promotion of practice of evidence based orthodontics rather than a system that is broken, craft based, fragile and not generative. Thus, the methods and systems disclosed herein provide for care being delivered to the right person at the right place at the right time with the right therapy by the right person all the time.
Generally speaking, an orthodontic ecosystem may be divided into three levels:
Micro Level—at the level of patient
Meso Level—at the orthodontist-patient level
Macro Level—at the community level, involving other orthodontists, associated organizations, third party provides such as from financial service industries, patient communities, manufacturers of orthodontic products, academia, research centers, laboratories and the like
Currently, the orthodontic ecosystem is fraught with challenges at all levels.
For example, at micro level, there is information asymmetry, which is biased towards the orthodontist or doctor or manufacturer. Thus, patient has little knowledge, exposure, impact and authority in planning, managing and providing feedback on the care delivery process extended to them. Also, currently the opportunity for the patient to seek input from other communities on the cost, aesthetics and reliability of their treatment process is limited.
Similarly, at the meso level, a doctor or orthodontist has limited opportunities to market, monitor and manage the doctor patient interaction and their own market reputation. This is also due to having no universal accepted standards for measuring personal performance characteristics, a lack of a reporting structure for errors in care, lack of access to patient experience and outcome data, in terms of dental and medical care records, among the communities of doctors and patients. Also, the doctor has limited access to skill level based learning and training resources, access to universal learning resources care guidelines checklists, managing pricing options for patient or is not incentivized to share clinical data.
Further, at the macro level, professional organizations do not have effective mechanisms to suitable rate, monitor and recommend exemplary doctors. Device manufacturers have limited or no access to direct patient requirements and evaluate product performance in the real world setting. Academia and learning institutions have limited or no access to patient records residing organization and insurance industry have no information to incentivize superior performance at practitioner level and recommend guidelines or best practices.
The system 100 illustrates a user 101 in interaction with an orthodontic care management ecosystem 102. The user may be a patient, a doctor, a device manufacturer, a financial service provider, a computing service provider, a government organization, an institutional user and the like, that may be desirous of accessing the orthodontic care management ecosystem 102. The orthodontic care management ecosystem 102 includes an orthodontic care management platform 102a in communication with an orthodontic appliance management system 102b for providing an orthodontic appliance 103. The orthodontic care management ecosystem 102 may also include other components, in communication with the components 102a and 102b, as will be described later in
The one or more services provided by the orthodontic care management platform 102a may include such as orthodontic treatment planning, orthodontic community access, orthodontic appliance designing, orthodontic treatment scheduling and alerts, knowledge sharing, orthodontic treatment monitoring, orthodontic appliance testing, medical recording of patient data, treatment sharing options with third party providers, feedback provisioning, treatment cost management and planning and the like.
In some example embodiments, the orthodontic care management ecosystem may be configured to provide data collection and care planning services. The data collection service may include such as patient data collection. The patient data may include patient's demographic data, patient image captured, by patient doctor or any source also relevant current medical history dental history from electronic patient record retrieved or filled, patient consent data for treatment and the like. In some example embodiments, the patient data may be collected by a user interface mechanism of the orthodontic care management platform 102a, such using a kiosk for information collection in a form, a questionnaire, a self-help portal, a website based patient registration and the like. In some example embodiments, the user interface for patient data collection may also include an option to capture or scan or upload a patient image to identify patient's anatomical features, such as patient's bone face structure, teeth geometry, gums geometry and the like.
In some example embodiments, the user interface for patient data collection may also provide a display of recommended care plan for the patient based on the collected patient data. For example, the user interface may provide recommendation for an orthodontic care plan based on matching of patient' facial features against similar proportioned treated patient. The data for treated patients may be stored in a database associated with the orthodontic care management platform 102a. In some example embodiments, the user interface for patient data collection may also provide options for smile customization for the patient. The smile customization may be performed based on automatic and interactive smile recommendations provided to the patient based on the collected patient data. In some example embodiments, the patient may be able to specify a smile type, such as a smile similar to that of a celebrity, based patient data.
In some example embodiments, the user interface for patient data collection may be an interactive interface, such as a virtual avatar of the patient in one or more of a virtual reality environment, a holographic display, an augmented reality environment and the like. In some example embodiments, the orthodontic care management platform 102a may provide an interactive contextual avatar for data access.
In some example embodiments, the user interface for patient data collection may enable the patient to input one or more queries related to treatment cost, treatment time, and number of visits, doctor reputation and the like. The queries may be input using a bot in one or more examples. The user interface may also enable the patient to select appropriate plan, seek vote from friends and external sources as to what aesthetic look is best for the patient and the like.
In some example embodiments, the orthodontic care management platform 102a may be configured to provide animated images to the patient depicting future state of patient facial change based upon patients' historical images.
In some example embodiments, the orthodontic care management platform 102a may be configured to provide recommendations to the user 101, such as the patient, related to the type of orthodontic appliance 103 best suited for the patient, such as braces, aligners and the like based upon patients preferences and or doctors, as collected in patient data. The patient data may be maintained in a database, such as a secure database. The secure database may include medical records that may be time dated and stamped using secure data technologies, such as block chain, access rights management and the like. The data stored in the secure database may be encrypted and user approved for use by a large community of users, such as patients, doctors, research institutions and the like. In some example embodiments, the secure database may also enable monetization of patient data records, wherein a patient may request for payment per transaction or one-time payment for use of any patient related data by specific organization.
In some example embodiments, the orthodontic care management platform 102a may be configured to provide treatment planning services such as taking approvals for a patient's treatment from an insurance or other third party provider, receiving automatic preauthorization of treatment plan from am authorizing agency, providing competitive bidding for the treatment cost from multiple doctors, integrating with various third party financial service providers to receive financing options for patient treatment based on a patient's savings, income, loan time, credit history and the like.
In some example embodiments, the orthodontic care management platform 102a may also provide payment related services to the user 101. The payment may be in the form of such as crypto-currency in one or more embodiments.
In some example embodiments, the orthodontic care management platform 102a may also provide transaction management related services to the user 101, such as connecting with third party service providers for payment transaction management, clearance, authorization and the like.
In some example embodiments, the orthodontic care management platform 102a may be configured to provide treatment planning services to the user 101, such as a doctor. The treatment planning may include generating target treatment plan, managing staging of treatment, risk planning, diagnostic planning and the like. The orthodontic care management platform 102a may provide a user interface for treatment planning by the doctor to manage various stages of the treatment, such as space closure, intrusion, extrusion, expansion, constriction, alignment detailing, restorative care and its appropriate sequencing. In some example embodiments, the treatment planning may be done automatically or interactively. Further, at each stage, the doctor may be able to identify one or more milestones, progress, processes completed and the like.
In some example embodiments, the orthodontic care management platform 102a may be able to provide checklists to the user 101, such as the doctor to track their progress in delivering the treatment to the patient. The checklist may be displayed to the doctor using any of the display interfaces know in the art, such as display screens, smart goggles, smart watch, tablet display, AR, VR display and the like or using voice output.
In some example embodiments, the orthodontic care management platform 102a may be configured to provide treatment monitoring and testing services to the user 101. For example, the doctor may be able to monitor the patient's progress, perform comparative analysis, monitor appliance performance, generate and receive alerts related to the treatment and the like. On the other hand, the patient may be able to provide feedback on the treatment, the doctor, send reminders and the like using the orthodontic care management platform 102a. In some example embodiments, the avatar based interface of the orthodontic care management platform may be configured for providing scheduling and alerting services. The data related to the treatment monitoring may be automatically updated in a database, such as the secure database discussed earlier.
In some example embodiments, the data about the user 101, such as the patient or the doctor, the treatment, the appliance and the payment transactions, may be stored in the secure database and used for learning purposes. Such as all the data may be added to a learning system locally and externally and using deep learning machine learning techniques, insights may be derived from the data. Such data may include such as data related treatment plans, patient specific information: like age, sex, ethnic background, psychosocial habits, behavior, and the like. Such insights may be used by doctors to do performance measurement based upon target vs. outcome, current standards of care, evidence, doctor skills and the like. Such skill and performance measures may in turn be used to for credentialing doctors on professional websites.
In some example embodiments, the performance data may be used to provide training recommendations to doctors who may include providing training resources, workshops, collaborative learning experiences, certifications and the like to the doctors.
In some example embodiments, the orthodontic care management platform 102a may be configured to provide reputation management services to the user 101. For example, using the learning database, patient treatment data, standard guidelines and doctor data, performance rating of doctor based upon tacit and explicit skills may be computed. In some example embodiments, the performance rating may be posted on social networking platforms for wider user access.
The orthodontic care management platform 102a may be in communication with the orthodontic appliance management system for designing the orthodontic appliance 103. In some example embodiments, the orthodontic appliance management system may be configured to generate a prototype of the orthodontic appliance 103, such as using a 3D printing workflow. In some other embodiments, the orthodontic appliance management system 102b may be configured for directly generating the orthodontic appliance 103, such using in-clinic 3D printers. The orthodontic appliance management system 102b may aid in designing appropriate appliances for each stage and sequence of treatment. In some example embodiments, the orthodontic appliance management system may include software interfaces specifically implemented for designing of the orthodontic appliance 103. The design files associated with the design of the orthodontic appliance 103 may either be stored locally, such as on the orthodontic appliance management system 102b or may be sent to a remote system for manufacturing. The manufacturing of the orthodontic appliance 103 may be done using any of the technologies know in the art, such as through subtractive machining, additive manufacturing, die casting, assembling and the like.
In some example embodiments, the orthodontic appliance 103 may be designed interactively and or for specific stages and can be used in tandem with non-customized devices. Appliance design may include removable, fixed combination, positional devices, both active and passive elements and the like. In some example embodiments, before appliance manufacture, the software interface associated with the orthodontic appliance management system 102b may enable appropriate risk management, wherein risk associated with the use of each appliance type and associated tooth movement or treatment may be automatically generated or simulated by the doctor. The levels of risk for each appliance or sequence may generate and accordingly, the design process may be driven.
In some example embodiments, the appliance 103 may be configured to accelerate tooth movement through thermal cycling. In other embodiments, the appliance 103 may have the ability to fit around any appliance in the mouth. In some example embodiments, the appliance 103 may be equipped with sensors. In some example embodiments, the appliance 103 may be a combination of different types of orthodontic appliances, and fixed and removable orthodontic attachments.
The orthodontic care management ecosystem 102 may also include other components, apart from the orthodontic care management platform 102a and the orthodontic appliance management system, as will be discussed in
Such components may include such as social networking platforms 102c, third party service providers 102d and device manufacturers 102e. The components 102c-102e may be connected to the components 102a-102b over a network 102f, which may be a wired or wireless network. The network 102f may be a Local Area Network (LAN) or a Wide Area Network (WAN). In several embodiments, the network 102f may be Internet. The implementation of the network 102f may be carried out using a number of protocols such as 802.x, Bluetooth, ZigBee, HSDPA, GSM, CDMA and LTE etc.
The orthodontic care management platform 102a may include an imaging unit 102a-1. The imaging unit 102a-1 may be configured to provide an image of the user 101 to the orthodontic care management platform 102a. The image may be provided either by real-time capture of the image or by using a pre-captured image. For real-time capture of the image, the orthodontic care management platform 102a may be equipped with an image sensor, such as a camera, a scanner, an X-ray machine, a CT scan machine and the like. For using a pre-stored image, the imaging unit 102a-1 may be connected to an external source or may use an image uploaded by the user 101 at the orthodontic care management platform 102. The image received by the imaging unit 102a-1 may be provided for further processing to any of the other components of the orthodontic care management 102.
The orthodontic care management platform 102a may include a planning unit 102a-2. The planning unit 102a-2 may be configured to provide treatment planning service using the orthodontic care management platform 102. The treatment planning services may include such as collecting patient data, identifying a smile template for patient smile correction, getting approvals for treatment, sharing treatment related data among a user community and the like. The orthodontic care management platform 102 may be configured to provide a software interface to the user for providing treatment planning services. The user 101, such as a patient, may be provided an input user interface, such as a form, for filling out their details, providing consent about treatment, providing treatment payment related processes and approvals, uploading their images for treatment planning, selecting options for smile type based on the patient data and the like.
Similarly, if the user 101 is a doctor, they may be able to access a software interface for extracting patient data and managing smile correction or malocclusion correction for teeth based on the patient data.
The orthodontic care management platform 102a may include a staging unit 102a-3 which may be configured to provide treatment staging and risk management services.
In some example embodiments, the staging unit 102a-4 may also be configured to provide staging and sequencing services to the doctor. That is to say, the doctor may be able to plan sequence of different stages of treatment using the software based interfaces, such as depicted in
In some example embodiments, the tooth movements may be planned automatically by defining milestones for teeth movements and matching the progress of treatment velocity with desired movements at each stage. This may be depicted using the user interface 500b of
The user interfaces in
The orthodontic care management platform 102a may include a testing unit 102a-4. The testing unit 102a-4 may be configured to provide diagnostic services and monitoring services for monitoring the progress of the orthodontic treatment against a desired outcome.
The orthodontic care management platform 102a may also include a design unit 102a-4. The design unit 102a-4 may be configured to provide services related to design of the orthodontic appliance 103. For example, the design unit 102a-4 may be configured to help a doctor in designing different types of configurations of orthodontic appliances, and attachments couplings mechanisms for the orthodontic appliance 103. For the purpose of designing, the design unit 102a-4 may be configured to operate in collaboration with the orthodontic appliance management system 102b for complete lifecycle, from designing to manufacturing, of the orthodontic appliance 103. The design unit 102a-4 of the orthodontic care management platform 102a may provide user interfaces for designing various types of devices or attachments for the orthodontic appliance 103 based on analysis and outcomes of all other units used in treatment planning, such as the imaging unit 102a-1, the planning unit 102a-2, the staging unit 102a-3, and the testing unit 102a-4.
The orthodontic care management platform 102a may include a feedback unit 102a-6 for gathering and managing feedback related services, such as feedback related to treatment, orthodontic doctor, treatment cost and the like. In some example embodiments, such feedback may be shared over social networking platforms 102c associated with the orthodontic care management platform 102a. Apart from the major design, planning and staging components discussed above, the orthodontic care management platform 102a may also include a UI unit 102a-7 to manage input/output access for the orthodontic care management platform 102a.
In some example embodiments, the UI unit 102a-7 may be configured for providing different interface mechanisms, including but not limited to speech, gesture, text, eye tracking, mouse based input, keystroke detection and the like.
In some example embodiments, the UI unit 102a-7 may be configured to provide access to an authentication interface including but not limited to voice recognition, password based authentication, retinal scan, fingerprint scan, biometric authentication, facial recognition and the like.
In some example embodiments, the UI unit 102a-7 may be configured to provide a context based interactive avatar interface which may take multiple roles based on user context.
In some example embodiments, the avatar may be context based. For example, the avatar may be used to provide follow-up alerts to a patient, such as reminding them to wear their orthodontic appliance, brushing teeth on time, scheduling and alerting about orthodontist's appointments and the like.
At the same time, the avatar may be configured to provide checklists for treatment follow-up to a doctor, sending reminder alerts on the doctor's mobile device updating them about scheduled calendar appointments, treatment monitoring and the like.
In some example embodiments, the avatar may be configured to modify patient behavior. In some embodiments, avatars for doctors and patient may be created to aid in learning.
The data related to treatment schedules, patient information, orthodontist information and the like may be stored in a memory unit 102a-8 of the orthodontic care management platform.
In some example embodiments, the memory unit 102a-8 may be a secure blockchain enabled database for maintaining medical records related to the user 101 accessing the orthodontic care management ecosystem 102.
The orthodontic care management ecosystem 102 also includes the orthodontic appliance management system 102b, which further includes the design unit 102b-1, the 3D printing unit 102b-2, and the manufacturing unit 102b-3 for designing and manufacturing various orthodontic appliances.
In some example embodiments, the orthodontic appliance management system 102b may be configured to perform a 3D printing workflow 300 as illustrated in
The workflow 300 may include gathering patient related data, such as data about patient's dento-facial features, various patient scans, patient demographics, authorizations and the like. In some example embodiments, the data gathering may be performed using the scanning unit 102a-1, the UI unit 102a07 and the memory unit 102a-8 of the orthodontic care management platform 102a. The gathered data may then be used to perform treatment planning, treatment staging and orthodontic appliance designing, such as using the planning unit 102a-2, the staging unit 102a-3, the testing unit 102a-4 and the design unit 102a-5 of the orthodontic care management platform 102a. Further, once the appliance design has been finalized, the appliance may be manufactured using the orthodontic appliance management system 102b for performing orthodontic appliance 3D printing model generation and 3D printing the product. At each stage of the workflow 300, feedback management and social data sharing may also be provided by the orthodontic care management ecosystem 102.
The method 800 may include, at step 801, receiving data related to the user 101. The user 101 may be a patient accessing the orthodontic care management ecosystem 102. In some embodiments, the user 101 may alternately be a doctor accessing the orthodontic care management ecosystem 102. The data related to the user may comprise such as data related to a facial anatomy of the user 101. In some example embodiments, the facial anatomy may comprise smile anatomy of the user 101. The data related to the user 101 may be received such as by scanning the facial anatomy of the user to capture facial features, smile features and the like. In some embodiments, the user 101 may have a preference for a specific type of smile, such as smile of a celebrity, a specific orthodontic treatment to create a specific smile. In such example, the user 101 may provide their data in the form of user preferences entered o a user interface, such as the UI 102a7 of the orthodontic care management platform 102a. In some other example embodiments, the user data may be received by downloading such data from a website. Once, the user data has been received in any such manner, the method 800 may proceed to step 802.
The method 800 may further include, at step 802, obtaining authorization data associated with the orthodontic care management solution. In some example embodiments, this data may be provided by the user, such as approval for a particular type of smile correction, preference to a specific smile and the like. In some other examples, the authorization data may include treatment related approvals, such as obtained from third party providers 102d including banks, insurance companies, government organizations and the like. In some example embodiments, the approvals may also relate to gathering patient consent regarding the treatment cost, orthodontist reputation management and the like. After receiving the desired approvals, the method 800 proceeds to step 803.
The method 800 may further include, at step 803, determining a treatment plan. Treatment plan may be determined such as using the planning unit 102a-2 of the orthodontic care management platform 102a as discussed earlier. The treatment plan may help facilitate a care provider, such as a doctor or a specialist to lay out the entire treatment in terms of different stages, wherein a stage is an operation to be performed during the course of the treatment. For example, one of the stages may be a movement of a tooth in a desired direction. Another stage may be placement of an orthodontic attachment at a desired position in the patient's mouth. In some example embodiments, the treatment plan may be defined by the doctor, based on the smile anatomy of the patient and the patient's desired smile anatomy. In some other example embodiments, the treatment plan may be automatically generated based on patient data, authorization data and some historical data derived from the memory unit 102a-8, wherein the historical data may be related to patient preferences, other patient treatment results, success and failure records of treatment strategies and the like. The treatment plan thus generated may be outlined and/or stored in terms of a plurality of stages. The stages may be defined in a particular order at step 804 of the method 800.
The method 800 may further include, at step 804, determining a sequencing plan. The sequencing plan may be associated with the treatment plan and may include an arrangement of the one or more stages of operations associated with the treatment plan. In some example embodiments, the sequencing plan may be generated to obtain optimization of treatment outcomes, such as using the staging unit 102a-3 of the orthodontic care management platform 102a discussed earlier. For example, the sequencing plan may be configured to automatically or interactively help design a treatment management approach that provides the greatest value choices driven by the patient data, such as most aesthetic smile, least amount of treatment time, fewest visits, the optimized sequencing of treatment when care is offered by between multiple doctors situated remotely and also the reconciliation and optimization of conflicting opinions from various sources by searching of evidence from referencing databases of research material and patient archive records of treatment outcomes. Once the sequencing plan is generated, the method 800 may proceed to step 805.
The method 800 may further include, at step 805, displaying the sequencing plan to the user, such as the doctor or orthodontist performing the treatment. The sequencing plan may be displayed such as on a display interface of the user device used by the doctor.
After display, the method 800 may proceed to step 806, wherein the method 800 may include receiving feedback data associated with the treatment plan. The feedback data may include such as feedback provided by the patient about the various aspects of the treatment, such as execution, cost, success, time taken, comfort level, patient awareness, patient satisfaction and the like. In some embodiments, the feedback may be received at the end of the treatment by the doctor, by providing a feedback form to the patient on a user interface of the user device being used by the doctor and which is connected to the orthodontic care management platform 102a. The feedback data thus received may be used by the feedback unit 102a-6 of the orthodontic care management platform 102a discussed earlier. In some example embodiments this feedback data may be used in reputation management of the doctor providing the treatment. For this, the method 800 may include, at step 807, updating a database, such as a learning data discussed earlier, connected with the orthodontic care management platform 102a. The learning database may also be used to store treatment data, apart from the user data, doctor reputation data, treatment tutorials and the like.
In an example embodiment, a system for performing the method of
In some example embodiments, the operations described in the method 800 above may be further enhanced in capabilities by using AI related techniques, as described in the method 900 disclosed in the
In an example embodiment, a system for performing the method of
In some examples, the method 900 may be further modified as depicted in
In an example embodiment, a system for performing the method of
In some example embodiments, the user may be able to use AI related techniques for performing action to voice and voice to action mapping of user data, as depicted in
In an example embodiment, a system for performing the method of
In some example embodiments, the voice to action an action to voice mappings described in
The method 1400a illustrates the overall patient workflow from the start of treatment to its conclusion. In some example embodiments, the method 1400a may be implemented by a Virtual Care Navigator (VCN), which may be an essential part of this workflow; however the VCN is not explicitly shown in this diagram and will be described separately in greater detail in
The method 1400a illustrates, at step 1401a, capturing patient data, such as by using an input capturing device. The input capturing device may include such as a scanner, an image capturing device like a camera, an input capture mechanism available on a mobile device, and other similar technologies available for capturing multiple 2D images of the user. In an example, the image capturing technology may include capturing patient's facial morphology using computer vision technology, such as using free open source tools for facial recognition and facial orientation detection. In some example embodiments, computer vision may be used in combination with the image capturing technology to ensure that the user takes pictures of the all appropriate orientations (facing front, right-side, left-side) required by a system, such as the orthodontic care management platform 102a. Some open source computer vision technologies, such as OpenCV also include a statistical machine learning library that may be used to learn the user's facial features. Once learned, the system can automatically detect the user the next time around. Thus, the captured user data may also be used as part of a biometric authentication system for access to the patient's dental/medical records, which may be stored in a database. Once patient data is successfully captured, the method 1400 may proceed to, at step 1402, to analyze patient morphology.
Once the patient's details are thus successfully captured and analyzed, the method 1400a may include, at step 1403a, modifying patient data, such as by using patient affect. In some example embodiments, the modification to the patient data may include morphological analysis and 2D-to-3D conversion, such as by building 3D models using image conversion tools known in the art. For example, OpenCV may be used to perform morphological analysis of the patient's face by extracting pertinent features from the 3D model and showing the user how their face is likely to change with the proposed orthodontic treatment. Further, after conversion, the image may be subjected to deep learning using tools known in the art, such as Tensor flow (www.tensorflow.org), to provide the machine learning capabilities required for such analysis and projection. Convolutional neural networks (CNN), well-known to those skilled in the art, are one of the examples of several deep learning algorithms that can be applied to this task. The machine learning techniques such as CNN may include analysis of various factors, such as a patient's view of their own attractiveness, which may be used to determine their attractiveness preference (affective sense) prior to the start of treatment, so that the treatment can be patterned to meet their objectives. In this regard, emotion detection (from the patient's images and models) plays a significant role in determining how happy (or unhappy) a patient is with their looks. Many patients go in for orthodontic treatment because they are not happy with how they look. Their level of dissatisfaction may be more reliably captured by emotion detection tools, rather than their verbal exposition. For example, some common tools known in the art like Emotient (www.emotient.com), Affectiva (www.affectiva.com), and EmoVu (http://emovu.com) may be used for emotion detection.
Once patient's preferences are factored in, the method 1400a may include, at step 1404a, generating personalized care plan and precision therapy for the patient. This may be achieved such as by using built in algorithms, such as within a processing module in the orthodontic care management platform 102a, wherein the built in algorithms may be configured to provide an augmented reality toolkit, a plan generator and other built in functions suitable for orthodontic care processing. The personalized care plan generated in this manner may be presented to the patient, such as using the UI unit 102a-7 of the orthodontic care management platform 102a. The plan and its effectiveness may be monitored, at step 1405a, to provide personalized monitoring to the patient. This may include such as providing a built-in app based monitoring, wherein the app may be used to provide reminders, alerts for medicine intake, due date reminders for patient visit to clinic and the like. Further, the orthodontic care management platform 102a may be configured for performing custom analytics on patient activity, provide doctor-patient based feedback monitoring, providing visualization of current treatment plan and deviation from the current treatment plan (if any) using data visualization tools, design tools and 3D plan generator. The personalized monitoring may enable the patient to be fully aware and in-control of their treatment progress and raise red flags as and when required to get the best possible treatment meted out to them. Thus, the orthodontic care management solution provided to the patient promises to be patient centric, highly advantageous, cost efficient and patient oriented. Further, the patient workflow in method 1400a also includes, at step 1406a, providing 24/7 patient support, from top orthodontists. The patient support may also include activities such as built-in scheduler for notification, app development module for finding nearby top orthodontists, 24/7 on chat support and call facility and the like. The method 1400a may also be configured to, at step 1407a, gather patient feedback for obtaining information about patient's reported experience and outcomes. This may be done using a built-in module for patient/doctor feedback collection and evaluation, such as using the feedback unit 102a-6 of the orthodontic care management platform 102a. The feedback unit 102a-6 may also be configured for doctor-patient feedback collection and visualization and built-in smile feedback support and rating. The feedback data and other patient data gathered in this manner may be subjected to, at step 1408a, further data visualization and monetization and analysis. This may be done using easy-to-understand dashboards (like those generated by tools such PowerBI (https://powerbi.microsoft.com) and Tableau (https://www.tableau.com), well-known to those skilled in the art). The dashboards generated in this way may be configured for leveraging the data analytics and mining created by the user, such as the patient or the doctor using the cloud databases. In some example embodiments, all patient and treatment data may be securely stored on a permissioned blockchain network that is accessible to patients, the doctor, and other entities (pharmacies) who are authorized to see that data. The techniques for the creation of an addition of records to a permissioned blockchain network are well understood by those skilled in the art. The advantages of using a blockchain for patient record storage in this invention are twofold: immutability and transparency. Once stored on the blockchain, patient records cannot be tampered with by anyone (immutability) and the patient has access to it at all times without being at the mercy of the doctor, or having to go through any third-parties to access the data (transparency). Further, since the patient is in control of their data at all times, they can, at their discretion, choose to monetize it by making it available to other doctors and health-related organizations for a fee. Other specific advantages provided by the method 1400a are illustrated by, such as step 1409a, where a learning database is updated by reputation management data and learning data to provide a continuous based AI enabled orthodontic care management solution to the patient. In this age of instantaneous social media reviews, doctors need to be very cognizant of negative reviews by patients adversely affecting their reputation and practice. There is currently no mechanism for patients' reputation to be logged and evaluated, and no way to determine if their negative reviews are justified or written out of sheer malice. By virtue of patient and treatment records being maintained on a blockchain network, the disclosed methods and systems of the invention ensure that there is complete transparency on both sides. Patient reviews are also tracked, so if a patient is in the habit of providing negative reviews as a matter of course for no valid reason, that patient's reputation suffers, and the doctor will be made aware of this when the patient signs up for treatment with the doctor. Further, patients are less likely to claim malpractice or bad treatment since the records are accessible to both patient and the doctor from the start of treatment all the way till the end.
As discussed above, the method 1400a is oriented towards a patient and the services provided to the patient by the orthodontic care management platform 102a of the orthodontic care management ecosystem. Just like that, the method 1400b discussed in the following description is oriented towards a doctor and the services provided to a doctor by the orthodontic care management platform 102a. The
As illustrated in the method 1400b, the steps 1401a, 1402a, 1404a, 1405a, 1406a, 1407a, and 1409a of the patient workflow in the method 1400a are also present in the doctor workflow of method 1400b as the steps 1401b, 1402b, 1403b, 1404b, 1405b, 1406b, and 1408b respectively. However, the focus of the steps will be different in each of the workflows. For example, doctor-specific activities like data mining and data analysis (of patient and treatment data) are part of step 1407b while step 1408a (data monetization and visualization) pertains to patients consuming the output of the analytics done in step 1407b as well as monetizing it by selling their data to doctors and other health organizations that can benefit from it. Similarly, reputation management for doctors in step 1408b (doctors need to be constantly aware of their reputations as it has direct bearing on the viability of their practice) is shown as part of the doctor workflow. These steps are described in greater detail below.
The method 1400b includes, at step 1407b performing data mining and analysis on patient data for use by the doctor during the provision of the orthodontic care management solution. The data analysis may be done using data analysis tools known to those of ordinary skill in the art, such as tolls like matplotlib, info graphics, and Google Analytics to compute data analytics. Further, the data mined in this manner may be used for tracking and visualizing user journey in applications using the custom Google analytics module.
The method 1400b further includes, at step 1408b, updating reputation management data for the doctor and using continuous learning techniques to use this data for further services such as providing an inbuilt system for patient/doctor ranking based on collected feedback using machine learning, providing recommendations about the doctor using big data and machine learning technologies, providing inbuilt voice-to-text action support using ASR (automatic speech recognition) and NLP (natural language processing) techniques, well-known to those skilled in the art.
Throughout the workflows 1400a and 1400b, the virtual care navigator (VCN) plays an important role, as described in the following description in conjunction with
The VCN bot system 1500 illustrated in
In some example embodiments, the haptic feedback may be the preferred output modality as it may be useful to highlight specific teeth positions on the device display. For example, when the doctor moves individual teeth on the screen to various positions during treatment planning, such as using machine learning techniques using Planning Problem and Constraint Logic Programming over Finite Domains (CLP(FD)), haptic feedback can be used to indicate the boundaries or limits of movement, or could also be used to indicate alignment with the surrounding teeth. Such tactile feedback may improve the overall efficiency of the treatment planning process, since the doctor does not have to depend on any displays or speech or text for feedback. Instead, the vibration felt by his finger (haptic feedback) conveys the same information quickly and succinctly. In some example embodiments, this may be implemented using cloud software using well-understood methodologies such as Software-as-a-Service (SaaS). Thus, the haptic input mapping generated this way may be available on multiple channels (including, but not limited to: mobile app, desktop app, website, smart glass app, etc.). In one or more embodiments, the VCN bot 1504 could be implemented using one or more popular cloud platforms, including but not limited to: Microsoft Azure (https://azure.microsoft.com/en-us/), Amazon Web Services (https://aws.amazon.com), and Google Cloud Platform (https://cloud.google.com).
In some example embodiments, the VCN bot 1504 may be configured to use NLP (natural language processing) algorithms to decipher the intent from user input and convert it into database queries to satisfy the user request. The NLP algorithms may use machine learning to train a language model in the domain of patient care (e.g., orthodontics) to ensure that the system can understand user queries within that domain. An example of a widely used cloud-based NLP system is LUIS—Language Understanding Intelligent Service from Microsoft (www.luis.ai). Further, the VCN bot 1504 leverages the dynamic learning (also known as ‘active learning’ by those skilled in the art) capabilities of the NLP system to dynamically update the language models based on user input. This dynamic learning may ensure that the bot adapts itself to user input during use.
In some example embodiments, speech may be used as the input modality. The user's input speech may be first converted into text (using automatic speech recognition) before NLP is applied to the text to extract the user intent. The algorithms used for recognizing large vocabulary continuous speech are well-known to those skilled in the art. Popular cloud-based ASR systems include Microsoft Speech (https://azure.microsoft.com/en-us/services/cognitive-services/speech-to-text/) and Google Speech (https://cloud.google.com/speech-to-text/), which are hereinafter incorporated in their entirety by reference.
In some example embodiments, gestures may be used as the input modality. If gestures are used as the input modality, the gestures may be first converted into text using gesture recognition techniques known in the art, such as those described in https://arxiv.org/ftp/arxiv/papers/1811/1811.11997.pdf), which is incorporated in its entirety herein by reference, before NLP is applied to the text to extract the user intent.
After receiving input in this manner, the VCN system 1500 may be configured to generate a user specific 3D virtual avatar 1503. For example, the user-specific 3D virtual avatar may include a male patient avatar, a female patient avatar or a doctor avatar. The 3D virtual avatar may be automatically generated using 2D images taken by the user (as described in the descriptions for
The operation and access methodologies for the VCN bot 1504 have been described in conjunction with the method flow diagrams illustrated in
At step 1606, the doctor may be asked to specify the preferred mode of interaction. The various modes of interaction may include such as smart glasses, smart glasses, PC, smartphone, tablet, AR headset, and the like. Once the doctor has specified the preferred modes of interaction, the method 1600 may include, at step 1607, asking the doctor to specify social media platforms that she/he may want to advertise their practice on. For example, the doctor may specify one of the various available social media platforms including Instagram, FB, snapchat, Twitter and the like. Once the social media platform has been specified, the method 1600 may proceed to, at step 1608, the VCN bot 1500 guiding the entire process of information collection from doctor to populate available system databases, such as the learning database discussed earlier. Along with this, some policy and other related documents may be uploaded to the VCN system 1500. Such documents may include such as documents on practice, policies, fee-structure, and the like. In some example embodiments, the entire doctor workflow may be a speech-driven process. In some other example embodiments, the doctor workflow may include a combination of input modalities such as text, speech, gesture and the like.
Once all the input modalities are done, the VCN bot 1500 is ready to add new patients and their corresponding avatars. It may be noted that though the VCN bot 1500 has been discussed in conjunction with the doctor and the patient workflows, but the VCN bot 1500 may be invoked at any time by the doctor. Additionally, at step 1609, the VCN bot 1500 may be set up for push notifications for activities including but not limited to new patient sign-ups, patient appointments or cancellations, insurance claim payment or modifications, patient feedback on social media pertaining to the doctor's practice, patient questions/comments directed to the doctor and the like.
The method 1600 is the doctor's side of the workflow for VCN 1500 set-up, and in a similar way, method 1700 illustrated in
Once the patient sets up the VCN (as shown in
In some example embodiments, the orthodontic treatment provided in accordance with the orthodontic care management solution provided by the orthodontic care management platform 102a, might have to be altered depending on how the teeth of the patient respond to the originally planned treatment. Such course corrections are common in orthodontic treatments. When such course corrections occur, the doctor may update the treatment roadmap that was part of the initial onboarding, such that the roadmap always reflects the current course of treatment. When an update is registered, the VCN system 1500 may detect the update and send push notification to the app alerting the patient to a change in the roadmap. When the patient logs in to the app the next time, such as by using their user device, the roadmap updates are presented to him or her, again using a combination of speech, text, and images/video.
In some example embodiments, the VCN bot 1500 may help the doctor in appointment scheduling. Generally, the orthodontists see their patients at fixed intervals (4 to 6 weeks apart), with the next appointment being scheduled during the current visit. Such equally-spaced visits help the operational efficiency of the doctor's back-office staff, but do not necessarily fit the needs of individual patients. In such cases, it would be beneficial if the patients could custom design their schedule, such as seeing the doctor again within 2 weeks (or even earlier) depending on the current appliance, their degree of malocclusion, and other factors. Similarly, some patients could afford to wait for a longer interval like 6 to 8 weeks for their treatment. Thus, the VCN bot 1500 may be trained with enough orthodontic knowledge to know when the next visit needs to be and will guide the doctor accordingly. Further, once the appointment date is determined, the VCN bot 1500 may be configured to auto-populate an on-device calendar for the doctor and patient, assuming that the users have given permission to the VCN 1500 during the set-up process. In some example embodiments, the VCN bot 1500 may be configured to provide demand based device manufacturing. Currently, patients are at the mercy of the orthodontic device manufacturer that the doctor has contracted with for manufacturing of the orthodontic device. If that manufacturer is backed up or otherwise unavailable, the patient's orthodontic treatment just gets delayed. However, using the orthodontic care management platform 102a disclosed in the invention, a repository of world-wide device manufacturers in multiple time zones may be available, all of whom may be well-versed with the technology needed to 3D print the device at short notice. By leveraging this world-wide network, modern communication channels, and different time zones, the system may be able to determine the best fit and ships the drawings electronically to the currently available 3D printer for manufacturing the device, such as the manufacturing unit 102b-3. Further, the distribution of workload across multiple 3D print manufacturers ensures that no single manufacturer is swamped with work while others wait for new orders. Thus, the orthodontic care management platform 102a may provide dual advantage of providing a patient plethora of manufacturing choices and for the manufacturers; the workload may be spread across different manufacturers for more efficient responses to customer demands.
In some example embodiments, the orthodontic care management platform 102a along with VCN bot 1500 may be configured to provide numerous services as outlined in the table below:
VCN Services Table
The following table provides an overview of all the services provided by the cloud-based VCN 1500. The presence of the optional 3D avatar affects how some of the services might be perceived by the user and enhances them superficially, but it is to be noted that the core functionality of all the services are invariant of the presence or absence of the avatar.
In some example embodiments, the orthodontic care management platform 102a may provide telepresence services. For example, during the orthodontic treatment, there may be certain milestones in the orthodontic treatment process that might require physical visits to the doctor's office and others where the doctor does not need to be present at the same geographical location as the patient for all steps in the treatment process. Telepresence technologies are well known in the art and may be used to provide the patient with standard care as if he or she were at the doctor's office. It may be understood that since mobile devices have advanced, two-way communication technologies are already built into them and most patients will not need anything more sophisticated than their existing mobile device and built-in cameras to avail additional advantages of the orthodontic care management platform 102a. For example, the doctor at a remote location, can virtually examine the patient's treatment progress in real time by having them show the doctor their teeth, typically by pointing and orienting the mobile device appropriately, under voice guidance either from the doctor who is online, or by the VCN 1500.
In some example embodiments, the VCN 1500 may support a dictation mode for chair side notes. In many cases in orthodontic care management solution provision, one of the more serious issues in orthodontic treatment is infection management. A doctor who examines multiple patients during the course of a single day has to be careful to change gloves and follow other appropriate sanitization procedures with the tools, etc., as they move from patient to patient. Further, a doctor who has to type in his notes into the computer beside the patient during his examination of the patient's mouth has to either remove his gloves or change gloves to avoid contaminating the keyboard and mouse—an onerous process that often gets omitted to save time and complete the patient consultation as expeditiously as possible. Unless explicit care is taken to sanitize the keyboard and mouse after each patient consultation, there is a strong possibility of cross-contamination between patients if that keyboard and mouse are touched again by the doctor while examining another patient. To avoid such inadvertent contamination, the methods and systems disclosed herein provide the capability to leverage existing speech dictation technologies, well-known to those skilled in the art, to enable the doctor to dictate his notes directly into the system, such as the orthodontic care management ecosystem 102. The VCN bot 1500 has a dictation mode and will guide the doctor through the dictation process as well as ensure that the notes are recorded in the correct location within that patient's treatment record. For example, the dictation mode may be used by the coaching avatar 1300 discussed in
In some example embodiments, the VCN system 1500 may also support speech-enabled 3D object movement. For example, during the treatment planning phase, the orthodontist may typically evaluate multiple approaches to resolving the patient's malocclusions, given the constraints, discussed later in conjunction with
Thus, the orthodontic care management ecosystem 102, in combination with (and inclusive of) the VCN bot 1500 may provide various advanced technologies for providing efficient, robust, automated, AI enabled orthodontic care management and malocclusion treatment options to the patients, in a fair, transparent, beneficial, participative and cost efficient manner.
The system 1800 may be configured to completely automate the process of correcting malocclusions in an orthodontic patient. The functionalities of the system 1800 and the various modules SC1 1801-SC31803 and all communication between these components and the user may be accomplished with the help of the VCN bot 1500 that is capable of deploying one of several input and output modalities such as speech, text, and images wherever appropriate, as discussed in
The system 1800 includes the software component SC1 1801 that may be configured to accept as input a frontal image of a human face with a smile, and output an aesthetically pleasing picture that is the closest match to the patient's needs. This may be accomplished by prior training of SC1 1801 on one or more databases containing thousands of images of smiling human faces showing teeth, using deep learning techniques such as convolutional neural networks, well-known to those skilled in the art. For this purpose, the module SC1 1801 may include a training module 1801a that may be configured to analyse the data from multiple databases 1804, wherein the databases 1804 may be designed such that they contain only those faces that have been judged as aesthetically pleasing with straight (i.e., not maloccluded) teeth, and use the data to train the module SC1 1801. The more variety of faces in this database 1804 (i.e., different demographics such as race, color, age, etc.) the more robust the training for the module SC1 1801. Once trained in this fashion, SC1 1801 may be able to accept an image only if it is that of a smiling human with teeth showing, and will reject an image if the human is not smiling or if the image is that of a toy or an animal. In the latter case, the user will be prompted to upload another image. This may be done by proper recognition of human faces.
When first invoked by the patient, SC1 1801 prompts the patient to upload their best facial image with a smile in which teeth show. SC1 1801 then analyses the picture to verify that it is indeed a human face in which teeth are showing. Once that verification is complete, the module SC1 1801 matches the input facial image with one from the dataset that has the closest match to the patient's facial features, skin color, tooth size and color, and the patient's stated goals for orthodontic treatment. The area corresponding to the straight teeth from this closest matching picture is identified. This is accomplished by using a standard graphics algorithm implemented within SC1 1801 that finds a bounding box for the area corresponding to the teeth. After this, the patient may select the best smile. This may be done by using the area captured by the bounding box, extracting it, and superimposing on the patient's picture. A specialized algorithm within SC1 1801 is included to ensure that the superimposed teeth are blended smoothly into the picture so that the patient picture looks natural. An example of superimposition of teeth with a picture in shown in
The module SC1 1801 may be configured to perform 2D-to-3D image conversion. Further, SC1 1801 may also provide an option to the patient to visualize a 3D image of their superimposed, blended picture. This may be achieved by incorporating well-known techniques to convert 2D dento-facial images to a 3D dento-facial image (example: www.selva3d.com). The 3D image may then be presented to the patient for review.
In some example embodiments, the module SC1 1801 may use affect response and immersion techniques for selecting the best smiles for presenting to the patient. One of the ways to do this is by performing, Facial Action Coding System (FACS). FACS is a commonly used approach understood to measure an individual's emotional response by studying facial behavior. The contraction of specific facial muscles described by action units (AU) can be related to the patient's affective response. The system 1800 may be configured to incorporate FACS to measure and analyze a patient's response to various simulations of their corrected smile at the start of the orthodontic treatment. The system 1800 may be designed to achieve the following objectives:
1. Evaluate patient's likability of a smile based upon action unit analysis
2. Patient's immersion behavior: how interested are they in evaluating their smiles?
3. Patient's eye movements/gaze analysis: what particular aspects of the smile do they like or dislike?
4. Provide facial muscle training and feedback
5. Perform a sentiment analysis based upon facial expressions
As already mentioned above, the module SC1 1801 may be configured for converting 2D images of the patient to 3D. Further, augmented reality techniques may be used to simulate the various corrected smiles of the patient. The displacement of the individual's facial action units in response to various simulations of the corrected smile and facial changes will be recorded, measured, and analyzed. The displacement of the pertinent action units is related to emotional states including, but not limited to, happiness, sadness, surprise, disgust, fear, and anger. These responses will be related to the likability of the smile. Machine learning techniques, such as those described in Bartlett et al and Yan Tong et al., which are herein incorporated in their entirety by reference, will be applied to classify the facial expressions of the patient. The system 1800 is trained on a dataset of facial expressions from several hundred people.
In some example embodiments, eye movement and gaze may be evaluated to understand what features the patient focuses on or avoids—avoidance implies dislike. Eye gaze detection and tracking techniques described in A. Perez et al (2015), Selker et al (2001), and Cuong et al (2010) which are herein incorporated in their entirety by reference are well-known to those skilled in the art, with some techniques requiring nothing more than an inexpensive webcam to capture images. The system 1800 may be configured to use such eye-gaze detection techniques to determine where the patient is focusing their attention on their simulated smiles.
In some example embodiments, immersion measures the interest level of the patient. Wearable biosensors (worn on the forearm, or other convenient location on the body) capture neural signals associated with attention (such as increases in heart rate and electro dermal activity) and vagal tone (increases in heart rate variability). Software associated with these sensors measures these signals, analyses them, and quantifies them on a 0-10 scale, with a higher score signifying greater immersion. Such physiological sensor and software combinations are well-known to those skilled in the art such as in Zak and Barraza (2018), which are herein incorporated in their entirety by reference. The VCN 1500 may be configured to guide the patient and doctor by a combination of speech, text, and image modalities, as described in
Further, the module SC1 1801 may provide a plurality of care management options. The care management options may include screening the patient's ability to self-manage their own care based upon factors that include but are not limited to the patient's desires, severity of malocclusions, and cost. Furthermore, SC1 1801 may also provide the patient with other care management approaches that may include: a hybrid approach involving limited professional supervision at identified points of care, or comprehensive professional management through the entire care cycle, involving regular doctor visits. The determination of the appropriate care management path can also be accomplished by machine learning techniques. For example, a database of dento-facial images may be compiled. Each image may then be labelled based upon the appropriate care management approaches including but not limited to self-care management, hybrid or total professional management. Further, a neural network may be trained using labelled data to classify the dento-facial images based on a care management path. When the patient's dento-facial image is presented to such a trained network, it may be able to determine the recommended care management path, with a reasonably high accuracy.
The module SC1 1801 may also be linked to VCN 1500 and thus, it may be configured to leverage the interactivity and multiple input/output modalities of the VCN 1500. The VCN 1500 may be used for a variety of tasks such as collection of additional demographic information of the patient as well as information from the patient to establish their personal profile, persona, and treatment needs. This data may then be used to provide additional smart information to the patient by connecting to specific services, including but not limited to support groups, patient learning aids, and patient decision aids. SC1 1801 may also be configured to provide generation of a 3D avatar of the patient, with the patient consent as already discussed in
The system 1800 may also include a module SC2 1802 that may be configured for automated setup of malocclusions to establish a target occlusion. For this, SC2 1802 may be configured to automatically suggest the steps to be taken to treat a malocclusion. This is accomplished by either using a series of 2D images of the teeth or face and/or a 3D scan of the teeth, or creating an output that provides a sequence of orthodontic steps that must be taken to treat the malocclusion. Thus, the module SC2 1802 may enable correction of the malocclusion from its initial state to its target state using a sequence of steps described in conjunction with the optimization algorithm 2200 based on a constraint logic problem illustrated in
The constraint logic problem described in
For instance, if we consider a tooth that needs to be moved 1 mm to the right and is blocked by a second tooth, to accomplish the movement of the first tooth, the second tooth has to be moved first and soon and so forth. The problem of treating a malocclusion is termed a planning problem. A planning problem has the following components: an initial state, a final state, and the “move or displacement”. The relation between the two states informs us if one state can be reached from another state by a single move (for example, moving a tooth 1 mm to the right). The planning problem thus seeks to find the sequence of moves or displacements that will take us from the initial state to the final or target state. Planning problems can be modelled as a constraint satisfaction problem (CSP). Constraint Logic Programming over Finite Domains (CLP (FD)) technology that has been widely used for solving CSPs is used. Essentially, each tooth that needs to be moved is constrained by the two teeth on each side. The teeth to be moved are driven by the patient's desire and or doctor's diagnosis and defined by boundary conditions that include, but is not limited to, the facial midline, arch-form, the class of occlusion, and the occlusal plane level.
SC2 1802 may include two major components, SSC1 1802a and SSC2 1802b. SSC1 1802a takes the input, for instance, the 3D scan in an STL file format and computes the bounding box for each tooth, using off-the-shelf tools such as Mesh Lab and Blender. SSC1 1802a uses the coordinates of the bounding box to generate the input for SSC2 1802b. SSC2 1802b will take this input and plans a sequence of steps to correct the malocclusions. SSC2 1802b subcomponent takes as input the configuration of each tooth. For each tooth, the input should describe the entirety of malocclusions that the patient has. This is captured by SSC2 through six values:
1. Crown Tipping (variable 2213 in
2. Root Tipping (variable 2214 in
3. Torqueing (variable 2215 in
4. Rotation (variable 2216 in
5. Translation (variable 2217 in
6. Intrusion/Extrusion (variable 2218 in
The input also consists of a pair of Boolean values (0 or 1) that tell us if the tooth is blocked from the left or the right, with respect to movement.SSC1 1802a generates these 7 values for each tooth. A normal tooth will have all values as 0. These inputs are then used by SSC2 1802b to generate the constraints, that are then solved using the CLF(FD) implementations, such as the algorithm 2200, found in most Prolog systems, well-known to those skilled in the art. The output of the constraint solver consists of a sequence of moves or displacements that indicate sequence of orthodontic actions to be taken. The possible moves are as follows: crownTip, rootTip, rotate, and translate. If the constraint solver finds no solutions, i.e., there are collisions, the subsequent analysis is done to identify whether expansion or flaring the tooth (moving it forward) can accomplish the correction to the tooth position (note all of these movements are constrained within the aforementioned boundary conditions such as midline, arch-form, etc.). If these alternatives fail, then either the boundary conditions have to be changed systematically, or more aggressive invasive strategies such as interproximal reduction (tooth shaved to reduce its size) or extraction to create space and remove collisions need to be considered. The input data is updated with these changes, and the CLP (FD) program, such as the algorithm 2200, is run again until a sequence and staged approach of the displacements is calculated and this defines the target. The sequence of movements can be temporally matched to set milestones. Other equivalent constraint solving technologies such as Integer Linear Programming or SAT-solving can also be used instead of CLP (FD).
The system 1800 also consists of module SC3 1803 that may be configured for training and feedback provision for orthodontists. In some example embodiments, the system 1800 may be configured for providing a comprehensive automated orthodontic analysis of each orthodontist's performance based on the treatment provided to patients referred to them by using the orthodontic care management platform 102a. The module SC3 1803 may be specifically developed for this purpose. SC3 1803 may be accessed by a patient. Periodically, the patient is asked to take an image or scan their teeth and upload it to SC3 1803. They may be also asked to provide a 3D scan of their teeth taken initially at the beginning of the treatment. SC3 1803 may then compute the optimal configuration at the current time based on the 3D scan. This optimal configuration may further be compared to the current pictures of the teeth uploaded by the patient. In case any major deviations are identified, and for a given orthodontist, the same error is observed repeatedly, the orthodontist is informed. Any other errors identified during the comparison will also be identified and the orthodontist and (possibly) the patient may be informed of the same.
In some embodiments, the system 1800 may also be configured for providing a patient affect response enabling system, as illustrated in
The image capture module 3001 may be configured to scan the user's facial image or take multiple photos of the user, such as the patient. The photos may then be converted to 3D by the 2D to 3D image conversion module 3002 and patient's smile may be simulated using AR techniques, by the augmented reality smile simulation module 3003. The simulated smile may be displayed to the user using multiple photos of corrected smiles, by the display module 3004. The likeness of the patient to specific smiles may be assessed by tracking their gaze by the eye-gaze tracking an emotion recognition module 3005. In some embodiments, a plurality of photos may be flashed in front of the patient showing them different arrangements of teeth. These arrangements may be reflected on the images of the patient themselves or on another subject. The module 3005 may then track patients' emotion and follow their eye-gaze to understand their likes or dislikes.
In some embodiments, the system 1800 may comprise a context-specific patient monitoring enablement system 3100, as illustrated in
Thus, the system 1800 comprising of the modules 1801-1803 may be configured for complete, learning-enabled, constraint-based, and feedback-oriented orthodontic treatment provision to the patients of the orthodontic care management ecosystem 102. The learning-based system 1800 may also be configured for complexity evaluation of the orthodontic treatment process, as illustrated in
On the other hand, for a satisfactory image, after complexity evaluation, at step 1909, pattern recognition is done to identify a numeric figure outlining the deviations in teeth. Further, at step 1910, similar images are identified using image matching algorithms also, simultaneously; the numbers of deviations are compared against the number of occlusions. Finally, at step 1912, the complexity of malocclusion is identified on a scale of 1-10.
The complexity evaluation may further be supplemented by evaluating cost of orthodontic treatment based on complexity of malocclusion, as illustrated in the method 2000 of
The method 2000 may include, at step 2001, identifying nature of complexity of malocclusion, and based on that, at step 2002, identifying an estimated cost of treatment. Further, at step 2003, the real cost of treatment is identified, and at step 2004, the two costs are checked to see if they are equal and at step 2006, the knowledge database is updated. However, if the estimated coast is not same as the real cost at step 2005, then at step 2007, percentage of difference is identified on a scale of 1-10, and put in the knowledge base at step 2006. The difference is also used to calculate assurance, at step 2009, and may provide to the patient 2011 or the doctor 2012, or the insurance agents 2013 or banks 2014. In some embodiments, the knowledge database may be queried, such as at 2008, to identify the root cause of difference between estimated vs. real cost and based on that, at step 2010, various factors such as increased treatment visits, appliance breakage and the like may be evaluated and provided to the various stakeholders mentioned earlier, that are the patient 2011 or the doctor 2012, or the insurance agents 2013 or banks 2014.
The cost estimation may be used to identify patient's treatment financing options, such as illustrated in the method 2100 of
The method 2100 may include, at step 2101, identifying patient's estimated cost, and at step 2102, identifying patient's credit history and credit score. Further, the two are provided as inputs to the intelligent care navigator, that is the VCN 1500, at step 2103, and at step 2104, the VCN 1500 may provide this data as input to the competing financing institutions. The competing financing institutions also keep receiving information about the patient's personal reputation, at step 2110. Further, at step 2105; the VCN 1500 uses the information provided by the competing financing institutions, which may include bids for financing the patient treatment cost, to a best financing option selection algorithm, using which, at step 2106, best financing option is selected. Further, this option may be presented to the patient, who may, at step 2107, select the best option. Further, the VCN 1500 performs continuous monitoring of patient's finances, payment schedules and provides feedback in managing finances to pay on time and maintain a credit score. This information is also kept stored, at step, 2109, in one or more learning databases. These databases may be configured for providing patient's financial information, such as their credit score, their payment history, payment dues and the like, from time to time to requesting modules of the overall system. These modules may be such as, doctor side interface 2111, cost estimation algorithm 2112, patient credit score based module 2113 and the like.
Thus, the orthodontic care management ecosystem 102 may be configured for providing treatment cost estimation and financing options for patients, based on the algorithms outlined in the methods 2000 and 2100.
In some example embodiments, the orthodontic care management ecosystem 102a may also be configured for providing chairside context-specific patient monitoring, as disclosed in
In some example embodiments, the orthodontic care management platform 102a may be configured for providing as an output, the orthodontic appliance 103, which may be equipped with sensors, as illustrated in
Further, the result of placing multi-sensor devices along with various attachments may be to achieve desired tooth movements, as depicted in
The gyroscope sensors, BLE chips, and shielding enclosures for such multi-sensor devices are well-known to those skilled in the art. The use of such multi-sensor devices to measure teeth movement during orthodontic treatment, as described in this invention, is indeed novel.
In some example embodiments, the orthodontic care management platform 102a may be configured for context-driven marketing patient support and marketing. The orthodontic care management platform 102a may be configured to customize and personalize orthodontic care for individual patients by tailoring the doctor's websites that are accessed from the patient's smartphones to their specific needs and treatment plan. This is possible since the patient's data, treatment plan, and treatment history will be available to the cloud backend once the patient completes registration with that doctor's practice. Since the website is owned by the doctor and the patient will almost always access it from the app on their smartphones, the website can be customized for each patient by populating key sections of it with information specific to the patient's treatment. For example, if the patient has a specific type of malocclusion, then the website might contain videos and other information pertaining to that type of malocclusion only. As another example, the customized website might contain information on the insurance coverage and payment plan (installments, lump-sum, etc.) specific to that patient. Yet another example would be language customization. Or yet another may connect the patient to disease-specific support groups. A patient who is not well-versed in English might find the website in their native language a lot easier to understand and navigate. For such a patient, the entire website may be served up in their native language, with an option to switch to English. Such customizations may make it easier for patients to get useful information about their treatment but also creates stickiness—they are more likely to come back to that website or seek treatment with the doctor who has such customizable websites.
In some example embodiments, the orthodontic care management platform 102a may be configured for automatic treatment planning for the patient based on the design of the target plan, for example as provided by the design unit 102a-5. The automatic planning is also illustrated by the exemplary user interface 2500 snapshots provided in
In some example embodiments, the orthodontic care management platform 102a may be configured for providing automatic treatment options by considering the patient's wants or needs, patient's economic stipulations, patient's treatment time considerations, the doctor's skills and preferences, and diagnosis based upon the soft tissue, skeletal, dental, functional, medical and dental history, biological and physiological status, psychosocial profile, and current evidence. Each of these elements can be considered as a constraint logic problem. So, the methodology described earlier in
In some example embodiments, establishing the target setup is accomplished automatically with the objective of maximizing aesthetics, function and stability, cost-effectiveness of care, efficiency of tooth movement, and patient safety. In some example embodiments, this may be accomplished by designing minimal interventional and invasive treatment care approaches that may include, but are not limited to, minimizing tooth movement or displacements, designing personalized orthodontic appliances, minimizing disruptions of the patient's lifestyle such as the frequency of visits to the doctor or pain associated with the use of appliances and minimizing time in treatment. The order of staging orthodontic treatment, for instance, “does space closure precede alignment?”, and the sequence of tooth movement, that is, “which tooth or teeth should move first?”, is performed automatically. In addition, the sequence of tooth movement is designed strategically and automatically with the goal of establishing the shortest path towards the target position and with a minimal number of collisions. The nature of tooth movement to achieve maximum efficiency and stability such as tipping versus translation are also considered in the design of the plan. In addition, for each major milestone in treatment, timelines are developed automatically. Further, the appliance systems to achieve specific care goals in orthodontic treatment are also automatically designed. These appliances are generally designed to create statically determinate force systems to apply controlled and predictable forces to the teeth. Common combinations of fixed appliances, aligners, and removable appliances with temporary anchorage devices and elastics may be considered to achieve these goals. Other features considered in the design of these appliances include achieving maximum safety and reliability in performance, modularity, minimal adjustments or changes, maximize patient comfort, and ease of installation and use by the operator and cost-effectiveness. The design and manufacture of these appliances is done strategically in terms of defining the shortest path of tooth movement to achieve the desired target. Also considered is the path that involves the least number of tooth collisions, and the most effective type of tooth displacement such as tipping versus translation. The time-bounded treatment milestones are provided to the patient to allow the doctor and patient to follow the progress of care. Further, in some embodiments, appropriate checklists for each milestone to be accomplished during the course of treatment are developed. Additionally, key performance indicators for the individual patient and doctor to measure progress in care are shared with the doctor.
In some example embodiments, the system 1800 may also be configured to provide alternative treatment approaches based upon reprioritizing the input parameters discussed above and allows for complete interactivity. Furthermore, the system 1800 allows for planning interdisciplinary care such as combining restorative care with orthodontic care driven again by the principles of minimal invasive and interventional therapy to achieve care in the shortest period of time with maximum aesthetics, stability, and function.
In some example embodiments, the AI enabled system 1800 may allow for automatic design of appropriate therapeutic devices or appliances that are automatically designed to achieve each of the staged or sequenced events such as for alignment, space closure, root correction, jaw repositioning and orthopedics and stabilization, finishing, and retention. The preferred features considered in the design of the appliances include, but are not limited to, features that generate controlled, predictable and known force systems whose force magnitude and line of action and direction of forces can be controlled, are statically determinate, create consistent force systems, are compliant with current evidence in terms of effectiveness and efficiency, require minimal changes, are operationally safe, can fit in the mouth and do not impinge on the patient's oral tissue, are highly reliable, not prone to failure, require minimal compliance from the patient in terms of wear, cause the least amount of discomfort to the patient, are easily installed by the operator, are self-limiting in action, can be easily adjusted, are modular to allow for chair side modification if the need arises to perform concurrent tooth movements, allow for maximum aesthetics, and are made of the appropriate material from both a biosafety perspective and efficiency of force delivery and cost.
Furthermore, in some example embodiments, the AI-enabled system 1800 may also allow for the fully interactive design of the appliances such as design of novel male-female fixed and removable attachments, for brackets, aligners, removable or fixed appliances. Bracket dimensions and slot may be changed, additional hooks or slots or auxiliaries can be designed. Aligners with special features such as internal attachments within the aligner shell or external attachments on the outside of the shell can be designed. Furthermore, tooth attachments for aligners are automatically designed and their shape and form can be modified. Also, special features such as tubes, brackets, posts, telescopic structures, hooks, and buttons can be designed into the aligner. These features can be designed into the appliance or as separate parts that may be attached or fixed to the aligner at a later stage. Structural features in the aligners may be modified; these include, but are not limited to, sectional aligners, cutout aligners, space between aligners and tooth or any contact surface hybrid aligners with springs, aligners with bite blocks, jaw repositioning aligners, monobloc aligners and the like. Also, the internal or external topography of the aligners can be designed by creating flat surfaces with or without inclines or even contoured surfaces. Honeycomb, lattice or corrugated structures of the aligner can also be designed. Additionally, removable appliances retainers and wires, indirect bonding trays to position to bond the attachments, appliances or guide implants in the mouth may also be designed. The capability to design polymer or composite based archwires that may be directly printed using additive printing technology are also provided Furthermore, the appliances can be designed to generate active tooth movement forces or as passive devices that generate near-zero forces based upon the treatment stage and sequence of treatment. Additionally, the design and use of the fixed appliances, aligners, and removable appliances are automatically staged and sequenced to optimize control and predictability of tooth movement, safety and cost when used in combination with the methods and systems disclosed in this invention. The software provides instructions to the doctor in the installation, use, and management of the appliances. These can be communicated via the VCN 1500 as images, text, and/or speech. Furthermore, the doctor can be trained prior to installation in the use of the appliances if they are not familiar with them through AR and VR tools and certified for appropriate skills prior to using the new devices. Similarly, the software automatically designs personalized instructions to the patients for use and management of the appliances and activates the VCN 1500 to support the care of the patient. The patient can also be given instructions in the use and management of the appliances, safety instructions, and managing emergencies using AR-VR tools already discussed.
In some example embodiments, using the system 1800, the patient or doctor may also enhance the aesthetics of the devices in use. This may be accomplished by creating veneers that are attached or built into the various orthodontic appliances to cover or mask the underlying malocclusion as it is being corrected. Tooth pontics can also be designed into or attached to the orthodontic devices to hide the extraction site(s) during space closure. Furthermore, fashion item features such as pop-culture motifs (movie and cartoon characters, emojis, etc.), colors, shape, materials coatings, and jewelry can be designed into the orthodontic appliance designed using the system 1800. Various pharmaceutical substrates to minimize tooth decalcification, pain, inflammation, whitening of the teeth and to enhance flavors to minimize the metallic plastic taste or enhance mouth freshness or minimize anti-halitosis may be designed into the appliances using a variety of carrier mechanisms such as thin films and microspheres. Additionally, probiotic bacteria may be layered into the appliances or carriers to manage oral halitosis or gingival inflammation Furthermore, coatings to minimize friction in the devices can also be designed into the appliance. Sensors may also be incorporated in the devices to manage reminders for adherence, loss of appliance, time to change the appliance and loss of force delivery.
In some example embodiments, the system 1800, such as the orthodontic care management platform 102a, may allow appropriate choice of materials based upon the design features, functionality, and use case of the orthodontic appliance. These include, but are not limited to, commonly accepted orthodontic biocompatible materials such as titanium-based alloys, stainless steel, chrome cobalt, titanium niobium, plastics, acrylics, elastomers, fiber-reinforced composites, ceramics, polymers, and silicones. Furthermore, combinations of materials of different mechanical characteristics may be blended to optimize the function of the orthodontic device design. In some example embodiments, the appliances may be printed either by using additive or subtractive computer-aided manufacturing processes. The system 1800 may automatically provide real-time feedback on product pricing and the most cost-effective discounted source for the fabrication or purchase of the appliance, the shipping costs, and the ability for aggregate purchase.
In some example embodiments, the system 1800 may provide the ability to the doctor to use off-the-shelf products when appropriate and design it into the care plan. As described earlier, the personalized patient-specific VCN 1500 may be used to help, coach, and motivate the patient and provide appropriate behavioral nudges to enhance patient motivation through the course of treatment. The doctor may also modify the prescription of the VCN 1500 in terms of additional needs such as wearing elastics at a specific time period. Further, the system 1800 may be designed around training a cohort database and using it to identify rules to automate the functionality.
In some example embodiments, the system 1800 may be configured to provide prognosis, anticipatory, and therapeutic risk management. For this, the temporal nature of tooth displacement for both the active and reactive units of the dentition in response to the applied force system may be predicted. This may be accomplished by using the principles of static mechanics such as equilibrium diagrams and free-body analysis when statically determinate force systems are applied. Additional risk factors may be identified and their impact on orthodontic tooth movement is considered. Such factors may include, but are not limited to nature of the malocclusion, the spatial relationships of the teeth with respect to the point of force application, the anatomical and biological constraints, the condition of the periodontium, collisions between the teeth, mechanical material and physical characteristics of the appliances considered for use, and patient cooperation. With more complex force systems, dynamic finite element methods and Beam Theory may be used to better comprehend the nature of applied forces and to predict the response. A person skilled in the art may well recognize that these methods are well known. Using the methods and systems disclosed in the invention, any unwanted tooth movements are managed in advance by designing appliance systems that generate consistent force systems or the use of adjunctive appliances that may minimize or negate the reactive forces that may cause unwanted tooth displacement. These may include, but are not limited to, the use of appliances such as directional elastics or lingual arches or temporary anchorage devices, etc. Further, checklists are also created. These may be image, text and/or speech-based. The checklists serve as reminders to both the patient and doctor to recognize side effects early in treatment. The checklists are also accompanied with instructions to manage unwanted tooth movement. A weighted prioritized risk analysis of the likelihood of any spurious tooth movement occurring at any point in time is calculated and provided to the practitioner and patient in advance. These are shared with the VCN 1500 as well who takes the role both of a therapeutic nurse and a patient coach to remind the patient periodically to check for spurious tooth movement and/or wear appliances such as elastics to check against the unwanted tooth movement. As the risk level of the patient increases, the monitoring intensity becomes more intense. This automatically triggers a change in the frequency of visits to the doctor and both the doctor's and patient's appointment calendars are automatically updated to reflect this need. Additionally, the involvement of the VCN 1500 care services intensifies.
Further, besides mechanical factors, the patients risk profile includes consideration of biological factors such as presence of bone loss, root desorption, oral hygiene condition, decalcification, type and magnitude of planned orthodontic treatment, medical history, educational level, and psychosocial profile. The risk profile of the patient is compared against a cohort sample of patients to further delineate the potential nature and extent to which the patient treatment prognosis is favorable or not in response to the intervention. Additionally, learning from the cohort patient group is shared with the doctor to better manage patient care and augment patient safety.
Further, in some embodiments, the orthodontic care management platform 102a, that is to say, the system 1800 may provide for patient monitoring and management. Patient care management may have both a patient-directed and a doctor-directed component facilitated with the participation of the VCN 1500. Thus, using the methods and systems disclosed in the invention, treatment progress may be measured at five levels: the patient's current status against the initial state, the current status against the planned final outcome, the current status against the predicted status at this stage in the treatment plan, the current status against the status at the previous appointment, and the current status against a similar cohort of patients. Input data from the patient at any point in treatment includes a series of 2D images of the dentition. These images are transformed into 3D images using either photogrammetric or convolutional neural network (CNN) techniques as already discussed. These are well known approaches to transform raster images to vector images. This requires training the CNNs with 2D images from large databases consisting of images from several hundreds or thousands of patients. The CNNs are able to automatically extract features of interest from these images to create the 3D models. In other embodiments of the invention, 3D scans of the dentition maybe taken as well, wherever feasible. It is now possible to capture 3D images with a smartphone (such as those running Apple iOS and Android operating systems). Therefore, in some embodiments of the invention, the patients will be expected to take 3D images with their smartphones during the entire treatment process. The current progress scans are then superimposed automatically over the initial or the planned outcome or images captured at the last appointment using a variety of approaches. These include least mean square or the best fit method, superimposition over relatively fixed anatomical landmarks such as the mid-palatine rogue in the maxilla, or implants that maybe present or placed in the patient's mouth. The mid-palatine rogue and a small area dorsal to it are unique to each person and do not positionally change or remodel during the course of treatment. Therefore, they collectively serve as a unique personal signature to superimpose upon as a reference to measure and analyze relative displacement of the teeth accurately, reproducibly and with precision for each patient as disclosed in Vasilakos et al, Sivaraj A, and Dong-Soon Choi, which are herein incorporated in their entirety by reference. As such, by using the rogue as points of reference, it is straightforward to map the current state of the patient's teeth to the original 2D image taken at the beginning of the treatment cycle by aligning the 2D images with respect to the mid-palatine rogue to determine progress (or lack thereof). Similarly, in the mandible, the mandibular tori or the maxillary mandibular mask when using cone beam data have been shown to be relatively stable reference points for superimposition, as disclosed in An, K., Ruellas, A C et al, which is herein incorporated in their entirety by reference. Alternatively, in some other embodiments, relative tooth movement in 3D space can also be calculated with respect to the reference arch and a tracking history of the nature of tooth movement to this point in time is graphically created The tracking history is used to define whether treatment is on course and refine the predictive analytics regarding time to completion of the care cycle or refine the prediction for the anticipated treatment response at the next visit.
Generally, 3D image capture capability may not be widely available yet to all patients, since not everyone can afford the latest smartphones with 3D image capture technology. For such patients, scanning their mouth to create a 3D model of the teeth is a time-consuming process typically done in the doctor's office with expensive equipment (not currently available to them). Therefore, 2D images of the patient's teeth are more commonly used during the various stages of the treatment cycle, after the initial 3D scan. This is more so in cases where the patient is remote and can easily take 2D images of their teeth themselves and transmit the 2D images to the doctor at regular intervals. For this reason, in some embodiments of our invention, a variant of a technique called ‘UV mapping’ well-known to those skilled in the art of 3D graphics and gaming, can be used to project the 2D images of the patient's teeth onto the original 3D scan. While UV mapping is used in the 3D graphics field to project a 2D image onto a 3D model for texture mapping, we use it in our invention to identify and measure displacement of the teeth. In order to measure the displacement, a number of reference points in the 3D scan and the 2D image (that have not moved due to teeth displacement) are used. Examples of such reference points include, but are not limited to, mid-palatine rogue, points on the teeth that are not part of the orthodontic treatment and therefore have not moved since the original pre-treatment 3D scan and other stationary points, as determined by the doctor's expertise. Once these reference points are matched, then the discrepancies between the 2D projection and the original 3D model can be accurately quantified to determine the teeth movement. This is a novel application of UV mapping to the field of orthodontic care.
Regardless of which progress tracking method described above is used, the tracking history is also compared automatically to a cohort database of patients to detect any deviations. Furthermore, the doctor can select any region of interest to better understand treatment response. The VCN 1500 recognizes the changes and may share these with the patient's guardian or other professionals involved in the patient's care. It has been observed that when treatment does not track the planned events, an automatic root-cause analysis is triggered and the doctor is informed of the possible causes of the problem and potential solutions. Additionally, the doctor may activate the VCN 1500 to search from the library sources reports on similar anomalous behavior. Midcourse correction in the treatment plan is automatically generated and so are the associated appliances to correct for the anomalous response. In the case of remote patients who are largely monitoring their own care (with limited periodic doctor visits), when the doctor sees any deviations, he is able to proactively order the appropriate revised aligners and/or appliances to arrive in time for the next patient visit, shaving considerable time off the entire treatment process. This can result in several weeks of time saved for the patient. All data is captured, classified, archived, and synthesized for future use to establish doctor performance and reputation.
In some example embodiments, patterns in treatment modalities and responses are tracked and doctor-specific learning aids are automatically created to enhance the skills of the doctor through point-of-care learning. Similarly, patients are educated throughout the treatment process by visual aids and learning materials designed to help them better understand their treatment. Thus, the care management platform 102a, with its associated software described above is novel in the sense that it is discovery-driven, proactive and therefore dynamic, unlike the current static reactive care management patient care models. Through a combination of effective communication links between the patient and doctor, use of an AI-based VCN that guides both patient and doctor, targeted and personalized therapeutics, novel application of techniques like UV mapping to track patient care and knowledge management repositories to manage point-of-care learning for both doctors and patients, gains in treatment effectiveness efficiency, treatment duration, safety, and cost of care are realized for both the patient and doctors.
In some example embodiments, the system 1800 may provide statistics on manpower utilization and resource utilization to achieve maximum effectiveness, efficiencies, and safety in the practice environment.
A number of AI tools sets known by those skilled in the art will be used These will include but are not limited to “Neuro-Symbolic Concept Learner (NSCL) that uses neural networks to extract features from images ie compose the symbols and then use, rule-based programs offered by it to respond to and solve problems based on those symbols. Furthermore to answer questions about the objects/elements in an images ie Visual question answering (VQA) AI tools such as those offered by CLVR, may be used. Few shot AI training tools maybe used to create the talking Virtual care navigator 1500. To detect changes in images AI tools such as RepMet may also be considered. Since much of patient data is sensitive, fragmented and received from multiple sources and their privacy needs to be maintained during training it is envisioned that generative adversarial networks will be used for data synthesis.
In some example embodiments, the orthodontic care management platform 102a may also be configured for eye gaze detection, personalized hologram generation and the like.
In some example embodiments, the orthodontic care management ecosystem 102 of the present invention may help to develop orthodontic appliances that include a basic framework with extensions that can be used for space closure, intrusion, root correction, distal movement, expansion, extrusion, alignment, retention and stabilization. These movements can be performed concurrently or in tandem. In several embodiments, the basic framework is envisaged to include longitudinal, arch shaped and transverse components that may be attached to teeth of a patient using relatively fixed or removable means as defined above. The components may include bent portions and be combined with each other using several attachment mechanisms as discussed earlier. In such scenarios, the framework will act as a passive (non-force applying) structure and will be adapted to receive other active elements/member that are capable of force applications. These active elements may include structure that is capable of at least partial elastic or elastomeric deformation. Alternately, the framework itself may have components or portions such as aligners and segmental aligners that may be capable of applying a non-zero force. However, in such a scenario as well, the framework would still be able to receive active elements/members. It is to be noted here that the orthodontic appliances are envisaged to include one or more of the framework and the additional active components. Also it is envisaged that an orthodontic appliance designed for one region of the teeth (such as buccal or labial) may be implementable to another region with very basic modifications without departing from the scope of the invention
The key advantages offered by the orthodontic appliances and their embodiments discussed above include ability to generate statically determinate forces and moments. Another advantage is that the setups may be modified to generate different kinds of tooth movements and may implement as labial or lingual appliances without any significant design changes. Moreover, the appliances may be easily produced using material very known in the art. Additional deformable members, elements, portion including springs, elastic bands and chain may also be deployed for additional axial forces and moments. Also, the attachments may be chosen to be easily removable or long-lasting.
It is further an objective of the invention to develop a computer implemented method and a computer system to enable a collaborative environment in which a patient, in collaboration with a doctor and several third part services is able to plan their orthodontic treatment, receive training, design and build customized orthodontic appliances and manage their entire care lifecycle on their own. Further, all the data that is retrieved, received or generated is stored in a secure database and distributed ledger/blockchain technologies may be leveraged to safeguard especially the privacy, authenticity and financial aspects of the orthodontic treatment. Advantages of such an approach includes customized care corresponding to specific needs of the patient, such as allergens, blood type, body type and pre-existing conditions/ailments, verification of authenticity from time to time, ability to conduct audits whenever needed and ability to perform philanthropic research without compromising the identity of the patient.
In some embodiments, the computer-implemented orthodontic care management system 102 may be configured to allow access to archived research papers in repositories and provide automatically synthesis of patient specific information. The system 102 may also provide updates on any new findings related to specific treatment within the local database at the doctor's site and provide the doctor with an alert message to make them aware of the updated information.
Further, the system 102 may be configured to provide value driven plans that may be designed automatically and/or interactively with doctor considering choices defined by the doctor such as but not limited to optimal stability, optimal function, optimal aesthetics and the like. The system 102 may designed also to automatically provide financial, functional and operational metrics and analytics for the practice based upon users choice of metrics.
In some embodiments, the system 102 may be configured to optimize the supply chain and delivery of customized appliances or orthodontic conventional appliances with the patients scheduled visits to maintain a just in time inventory.
In some embodiments, the system may provide backup of all data, including patient data such as demographic data, disease history and the like, to develop a better patient understanding of their malocclusion and treatment.
The features can be implemented in a computer system that includes a back-end component, such as a data server or that includes a middleware component, such as an application server or an Internet server, or that includes a front-end component, such as a client computer having a graphical user interface or an Internet browser, or any combination of them. The components of the system can be connected by any form or medium of digital data communication such as a communication network. Examples of communication networks include a LAN, a WAN and the computers and networks forming the Internet.
The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
One or more features or steps of the disclosed embodiments can be implemented using an Application Programming Interface (API). An API can define one or more parameters that are passed between a calling application and other software code (e.g., an operating system, library routine, function) that provides a service, that provides data, or that performs an operation or a computation.
The API can be implemented as one or more calls in program code that send or receive one or more parameters through a parameter list or other structure based on a call convention defined in an API specification document. A parameter can be a constant, a key, a data structure, an object, an object class, a variable, a data type, a pointer, an array, a list, or another call. API calls and parameters can be implemented in any programming language. The programming language can define the vocabulary and calling convention that a programmer will employ to access functions supporting the API.
In some embodiments, an API call can report to an application the capabilities of a device running the application, such as input capability, output capability, processing capability, power capability, communications capability, etc.
It should be understood that the techniques of the present disclosure might be implemented using a variety of technologies. For example, the methods described herein may be implemented by a series of computer executable instructions residing on a suitable computer readable medium. Suitable computer readable media may include volatile (e.g. RAM) and/or non-volatile (e.g. ROM, disk) memory, carrier waves and transmission media. Exemplary carrier waves may take the form of electrical, electromagnetic or optical signals conveying digital data steams along a local network or a publically accessible network such as the Internet.
It should also be understood that, unless specifically stated otherwise as apparent from the following discussion, it is appreciated that throughout the description, discussions utilizing terms such as “controlling” or “obtaining” or “computing” or “storing” or “receiving” or “determining” or the like, refer to the action and processes of a computer system, or similar electronic computing device, that processes and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer—system memories or registers or other such information storage, transmission or display devices.
It should be noted that where the terms “server”, “secure server” or similar terms are used herein, a communication device is described that may be used in a communication system, unless the context otherwise requires, and should not be construed to limit the present invention to any particular communication device type. Thus, a communication device may include, without limitation, a bridge, router, bridge-router (router), switch, node, or other communication device, which may or may not be secure.
It should also be noted that where a flowchart is used herein to demonstrate various aspects of the invention, it should not be construed to limit the present invention to any particular logic flow or logic implementation. The described logic may be partitioned into different logic blocks (e.g., programs, modules, functions, or subroutines) without changing the overall results or otherwise departing from the true scope of the invention. Often, logic elements may be added, modified, omitted, performed in a different order, or implemented using different logic constructs (e.g., logic gates, looping primitives, conditional logic, and other logic constructs) without changing the overall results or otherwise departing from the true scope of the invention.
A number of embodiments have been described. Nevertheless, it will be understood that various modifications may be made. Elements of one or more embodiments may be combined, deleted, modified, or supplemented to form further embodiments. As yet another example, the logic flows depicted in the figures do not require the particular order shown, or sequential order, to achieve desirable results. In addition, other steps may be provided, or steps may be eliminated, from the described flows, and other components may be added to, or removed from, the described systems. Accordingly, other embodiments are within the scope of the following claims.
The terms and descriptions used herein are set forth by way of illustration only and are not meant as limitations. Examples and limitations disclosed herein are intended to be not limiting in any manner, and modifications may be made without departing from the spirit of the present disclosure. Those skilled in the art will recognize that many variations are possible within the spirit and scope of the disclosure, and their equivalents, in which all terms are to be understood in their broadest possible sense unless otherwise indicated.
Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the embodiments shown along with the accompanying drawings but is to be providing broadest scope of consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the disclosure is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present disclosure and appended claims.
Claims
1. A computer-implemented system for providing an orthodontic care management solution, comprising:
- one or more databases configured to store data of one or more users; and
- a server including computer code for providing the orthodontic care management solution, wherein the server comprises: at least one memory configured to store the computer code, the computer code further comprising computer executable instructions for performing at least one of one or more functions comprising: receiving user data; obtaining authorization data associated with the orthodontic care management solution; determining a treatment plan based on the user data and the authorization data, wherein the treatment plan comprises one or more stages of operations; determining a sequencing plan associated with the treatment plan, based on an arrangement of the one or more stages of operations associated with the treatment plan; displaying the sequencing plan to the user; receiving feedback data associated with the treatment plan; updating the one or more databases with the feedback data; and at least one processor configured to execute the computer code to provide the orthodontic care management solution.
2. The system of claim 1, wherein the user is a doctor, a patient, a prospective patient, or a third party user.
3. The system of claim 1, wherein the computer code is accessed by using a user device.
4. The system of claim 3, wherein the at least one processor is further configured to execute the computer code for displaying a virtual avatar on a user interface of the user device.
5. The system of claim 1, wherein the at least one processor is further configured to execute the computer code for manufacturing an orthodontic appliance based on the treatment plan.
6. The system of claim 5 wherein the manufacturing comprises generating a 3D printed orthodontic appliance.
7. The system of claim 1, wherein the at least one processor is further configured to execute the computer code for performing artificial intelligence enabled operation for providing the orthodontic care management solution.
8. The system of claim 7, wherein the artificial intelligence enabled operation comprises a voice-to-action command.
9. The system of claim 7, wherein the artificial intelligence enabled operation comprises an action-to-voice command.
10. The system of claim 1, wherein the at least one processor is further configured to execute the computer code for receiving user data by scanning a facial anatomy of the user.
11. The system of claim 10, wherein the facial anatomy comprises a smile anatomy of the user.
12. The system of claim 1, wherein the at least one processor is further configured to execute the computer code for obtaining authorization data associated with the orthodontic care management solution from a third party service provider.
13. The system of claim 12, wherein the third party service provider comprises one or more of a bank, a financial institution, a seller, a buyer and a manufacturer.
14. The system of claim 1, wherein the at least one or more databases comprise at least one blockchain-enabled database.
15. A method for providing an orthodontic care management solution, comprising:
- receiving user data;
- obtaining authorization data associated with the orthodontic care management solution;
- determining a treatment plan based on the user data and the authorization data, wherein the treatment plan comprises one or more stages of operations;
- determining a sequencing plan associated with the treatment plan, based on an arrangement of the one or more stages of operations associated with the treatment plan;
- displaying the sequencing plan to a user on a user device;
- receiving feedback data associated with the treatment plan; and
- updating one or more databases with the feedback data.
16. The method of claim 15, further comprising displaying a virtual avatar on a user interface of the user device.
17. The method of claim 15, further comprising sending a command to a manufacturing device for manufacturing an orthodontic appliance based on the treatment plan.
18. The method of claim 17, wherein the manufacturing device comprises a 3D printer.
19. The method of claim 15, further comprising performing an artificial intelligence enabled operation for providing the orthodontic care management solution.
20. The method of claim 19, wherein the artificial intelligence enabled operation comprises a voice-to-action command.
21. The method of claim 20, wherein the voice-to-action command is provided by generating a virtual care navigator system.
22. The method of claim 19, wherein the artificial intelligence enabled operation comprises an action-to-voice command.
23. The method of claim 22, wherein the action-to-voice command is provided by generating a virtual care navigator system.
24. The method of claim 15, wherein receiving user data further comprises scanning a facial anatomy of the user.
25. The method of claim 24, wherein the facial anatomy comprises a smile anatomy of the user.
26. The method of claim 15, wherein obtaining authorization data associated with the orthodontic care management solution further comprises obtaining the authorization data from a third party service provider.
27. A method for providing an orthodontic care management solution, comprising:
- receiving user data;
- obtaining authorization data associated with the orthodontic care management solution;
- determining a treatment plan based on the user data and the authorization data, wherein the treatment plan comprises one or more stages of operations;
- determining a sequencing plan associated with the treatment plan, based on an arrangement of the one or more stages of operations associated with the treatment plan;
- displaying the sequencing plan to a user on a user device;
- receiving feedback data associated with the treatment plan;
- updating one or more databases with the feedback data; and
- performing an artificial intelligence enabled operation for providing the orthodontic care management solution.
28. The method of claim 27, further comprising performing an auto diagnosis of the user, wherein the user comprises a patient and the auto diagnosis comprises patient directed auto diagnosis.
29. The method of claim 27, wherein the orthodontic care management solution is provided automatically to the user based on historical user data.
30. The method of claim 27, further comprising performing one or more of automatic selection of the user data, automatic staging of the treatment plan, automatic determination of the sequencing plan, automatic designing of an orthodontic appliance, and automatic fabrication of the orthodontic appliance.
31. The method of claim 30, wherein the orthodontic appliance comprises one or more of fixed removable aligners.
32. The method of claim 27 further comprising:
- performing automatic risk analysis associated with the one or more stages of operations;
- performing automatic tracking of progress of treatment based on the sequencing plan; and
- updating the sequencing plan automatically based on the progress of the sequencing plan.
33. The method of claim 32, wherein the sequencing plan is updated based on evidence of the progress of the sequencing plan.
34. The method of claim 27, wherein updating one or more databases comprises updating learning data in the one or more databases, wherein the learning data comprises data associated with one or more of automatic point-of-care anticipatory learning, training data, and assessment double-loop learning data.
35. The method of claim 27 further comprising:
- generating a virtual care navigator associated with the user; and
- automatically providing instructions for provision of orthodontic care management solution by the virtual care navigator.
36. The method of claim 35, wherein providing the instructions by the virtual care navigator comprises providing the instructions using one or more of text, speech, and graphics.
37. The method of claim 35 further comprising providing automatic prescription generation by the virtual care navigator, based on one or more conditional data associated with the user.
38. The method of claim 27, wherein providing the orthodontic care management solution comprised providing multi-language support for the provision.
39. The method of claim 27 further comprising providing automatic reputation management for the user based on the feedback data.
40. The method of claim 27 further comprising providing a natural user interface for providing the orthodontic care management solution.
41. The method of claim 27 further comprising updating an electronic health record associated with user data.
42. The method of claim 27 further comprising searching an electronic health record associated with user data.
43. The method of claim 27 further comprising generating a personalized check list generation for the user, wherein the generalized checklist is based on the sequencing plan.
44. The method of claim 27, further comprising sending a command to a manufacturing device for manufacturing an orthodontic appliance based on the treatment plan.
45. The method of claim 44, wherein the manufacturing device comprises a 3D printer.
46. The method of claim 44, wherein the orthodontic appliance comprises a sensor-based orthodontic appliance.
47. The method of claim 27, further comprising performing one or more of image-based user tracking, text-based user tracking, gesture-based user tracking, gaze-based user tracking, speech-based user tracking, and search-based image auto-tagging and retrieval.
48. The method of claim 27 wherein receiving user data further comprises scanning a facial anatomy of the user.
49. The method of claim 48 wherein the facial anatomy of the user comprises one or more user related factors selected from a group comprising: skin aging, facial changes, wrinkles, speech training, cosmetics, burns and facial anomalies.
50. The method of claim 27 further comprises generating a 3D avatar in the likeness of the user to provide empathetic guidance throughout the treatment.
51. The method of claim 27 further comprising performing UV mapping of the user data to project 2D images of the user's teeth onto 3D scans.
52. The method of claim 27 further comprising using a sensor based orthodontic appliance to track and measure teeth movement of the user.
53. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein for providing an orthodontic care management solution, the computer-executable program code instructions comprising program code instructions for:
- receiving user data;
- obtaining authorization data associated with the orthodontic care management solution;
- determining a treatment plan based on the user data and the authorization data, wherein the treatment plan comprises one or more stages of operations;
- determining a sequencing plan associated with the treatment plan, based on an arrangement of the one or more stages of operations associated with the treatment plan;
- displaying the sequencing plan to a user on a user device;
- receiving feedback data associated with the treatment plan;
- updating one or more databases with the feedback data; and
- performing an artificial intelligence enabled operation for providing the orthodontic care management solution.
Type: Application
Filed: Aug 23, 2019
Publication Date: Feb 27, 2020
Inventor: Rohit C. Sachdeva (Plano, TX)
Application Number: 16/548,850
