Abstract: A system of machine learning (“ML”) models for making actionable predictions regarding low-incidence events, including a generative ML model that produces synthetic minority-class records to form an augmented training data set, a predictive ML model that has been trained on the augmented training data set, a certainty ML model that produces a certainty estimate, and an explanatory model that produces an explanation. A method for producing actionable predictions of a low-incidence event by applying ML models to imbalanced class data by producing a prediction by a predictive ML model that has been trained on a data set comprising synthetic minority-class data records produced by a generative ML model, and producing a certainty estimate and an explanation. At least one of the certainty estimate or explanation determines an effective or appropriate response to the prediction. The low-incidence event may comprise risk of opioid use disorder.

Abstract: A distributed system includes one or more servers configured to provide computing devices access to portals hosted by the one or more servers, where the portals include a patient intake portal accessible by a first computing device located at an office of an intake dentist or orthodontist, and an approving portal accessible by a second computing device remote from the first computing device. The distributed system includes a dental aligner fabrication system including a fabrication computing device and dental aligner fabrication equipment. The patient intake portal is configured to provide a plurality of status updates to the intake dentist or orthodontist regarding a status of the patient, where the plurality of status updates include an indication that the dental aligners have been sent to the patient.

Abstract: Described herein are database systems including one or more remote analytical instruments operably connected to one or more servers. The instruments can transmit rich data to the servers, and the one or more servers can compile a database of the rich data. One or more processors associated with the servers can be configured to execute a data analytics program on the database to identify a stochastic phenomenon or to process the data and present in real-time at a location of the one or more instruments comparison information about the instruments.

Abstract: A method for providing a lung disease risk measure in a Computer Aided Diagnosis system is described. The method comprising the steps of: receiving a plurality of inputs for a subject, each input comprising at least one image showing all or part of the lungs of a patient and a time stamp for the image, where the inputs are obtained at varying intervals; analysing the inputs to assess temporal changes in the images using at least one of an input data encoder and a time stamp encoder; inputting the output of at least one of the encoders to a score calculator to calculate a risk score; outputting the risk score indicating the lung disease risk for the subject. A Computer Aided diagnosis system for implementing the method is also described.

Abstract: This patent disclosure provides various embodiments of combining multiple modalities of non-text surgical data in forms of videos, images, and audios in a meaningful manner so that the combined data can be used to perform comprehensive data analytics for a surgical procedure. In some embodiments, the disclosed system can begin by receiving two or more modalities of surgical data during the surgical procedure. The system then time-synchronizes the two or more modalities of surgical data to generate two or more modalities of time-synchronized surgical data. Next, the system converts each modality of the time-synchronized surgical data into a corresponding array of values of a common format. The system then combines the two or more arrays of values to generate a combined set of values. The system subsequently performs comprehensive data analytics on the combined set of values to generate a surgical decision for the surgical procedure.

Abstract: A method, computer program product, and system are disclosed. The method, when implemented in a computer system, includes obtaining patient information (where the patient information comprises symptom information), and identifying a medication. The medication is identified by searching a medication information database using the symptom information.

Abstract: Techniques are disclosed to predict medical device failure based on operational log data. Log data associated with a plurality of devices comprising a population of devices each having a same target part subject to failure. For each of at least a subset of the plurality of devices replacement dates on which the target part was replaced in that device are determined. A set of logged event data with prescribed severity is extracted from the log data for said plurality of devices. A subset of the logged event data is identified as being associated with impending failure of the target part. The subset of the logged event data is transformed into a normalized form. The normalized subset of the logged event data is used to generate a failure prediction model to predict failure of the target part in a device based on the current event logs from that device.

Abstract: Techniques are disclosed for determining a risk assessment corresponding to a level of risk that a user of a service organization has or will develop a condition. The techniques include receiving user data associated with a user record of a user. The techniques further include inputting the user data into a trained prediction model of a user condition prediction system. The user data may include a plurality of data points, weighted relative to each other, that respectively correspond to one of a plurality of categories. The techniques further include determining, by the trained prediction model, a risk assessment of a user condition based on the user data. The risk assessment may then be provided to a user device of a user service agent for use coordinating user service.

Abstract: Technologies are provided for classifying detected events as labeled event combinations. Input data for different combinations of detected events are received at a server system, and each combination of detected events is processed at the server system. Processing can include classifying that combination of detected events at a classifier to map that combination of detected events to a probability of an increased insulin delivery demand or a probability of a decreased insulin delivery demand, and labeling each classified combination of detected events with a label to generate a corresponding labeled event combination that has the probability of the increased insulin delivery demand or the probability of the decreased insulin delivery demand. Each labeled event combination can be stored in storage as a database of labeled event combinations, and selected ones of the labeled event combinations can be processed at a client application to generate an output result.

Abstract: At least some embodiments provide illustrative systems and methods that may enable formulation optimization using one or more processor(s) that may be programmed to: receive an amino acid formulation request for an amino acid combination for a hydration beverage, the amino acid formulation request having a first set of optimization criteria including a first water uptake metric for glucose and a taste profile metric associated with a score indicative of an effect on a taste profile of the hydration beverage; access a second set of optimization criteria, including an expression pattern for receptors in the intestine, a second water uptake metric for the amino acid formulation, and amino acid data of each amino acid; and generate an optimized amino acid-based formulation utilizing a hydration beverage optimization engine to optimize a concentration of one or more amino acids based on the first and second sets of optimization criteria.

Abstract: A system for alimentary provisioning includes a computing device configured to provide an alimentary instruction set including a plurality of target nutrient quantities, receive, from each alimentary provider device of a plurality of alimentary provider devices, a plurality of provider ingredients, generate a plurality of ingredient combinations, wherein each ingredient combination is a combination of two or more provider ingredients of the plurality of provider ingredients, and select a plurality of beneficial ingredient combinations from the plurality of ingredient combinations, wherein selecting each ingredient combination of the plurality of ingredient combinations includes determining a nutrient listing corresponding to each ingredient combination of the plurality of ingredient combinations, creating a distance metric from the nutrient listing to the alimentary instruction set, and selecting at least an ingredient listing that minimizes the distance metric, and selecting the plurality of beneficial ingre

Abstract: Automatically generating a structured medical note during a remote medical consultation using machine learning. A provider tele-presence device may receive audio from a medical provider. A medical documentation server may be coupled to the network. A machine learning network receives audio data from the provider tele-presence device, the machine learning network generating a structured medical note based on the received audio data, and wherein the structured medical note is stored in the medical documentation server in association with an identity of a patient.

Abstract: Sepsis is one of the most prevalent causes of mortality in Intensive Care Units (ICUs) and delayed treatment is associated with increase in death and financial burden. There is no single laboratory test or clinical sign that by itself can be considered diagnostic of sepsis. The present disclosure provides discriminating domain specific continuous and categorical features that can reliably classify a subject being monitored into a sepsis class or a normal class. A combination of physiological parameters, laboratory parameters and demographic details are used to extract the discriminating features. Even though the parameters may be sporadic in nature, the systems and methods of the present disclosure make use of a sliding time window to generate continuous features that capture the trend in the sporadic data; and a binning approach to generate categorical features to discriminate deviation from the normal class and facilitate timely treatment.

Abstract: A method is provided for lowering blood sugar in a subject in need thereof by administering a gliflozin Sodium-Glucose Cotransport 2 inhibitor pharmaceutical composition to a subject qualified for over-the-counter access to the gliflozin Sodium-Glucose Cotransport 2 inhibitor pharmaceutical composition. In some embodiments, the gliflozin Sodium-Glucose Cotransport 2 inhibitor pharmaceutical composition includes empagliflozin, canagliflozin, and ertugliflozin. In some embodiments, the gliflozin Sodium-Glucose Cotransport 2 inhibitor pharmaceutical composition includes (2S,3R,4R,5S,6R)-2-[4-chloro-3-[(4-ethoxyphenyl)methyl]phenyl]-6-(hydroxymethyl)oxane-3,4,5-triol or a pharmaceutically acceptable salt thereof.

Abstract: A method is provided for lowering blood sugar in a subject in need thereof by administering a biguanide anti-hyperglycemic pharmaceutical composition to a subject qualified for over-the-counter access to the biguanide anti-hyperglycemic pharmaceutical composition. In some embodiments, the biguanide anti-hyperglycemic pharmaceutical composition includes N,N-dimethylimidodicarbonimidic diamide, or a pharmaceutically acceptable salt thereof. In some embodiments, the biguanide anti-hyperglycemic pharmaceutical composition includes metformin hydrochloride.

Abstract: Example methods, apparatus, and articles of manufacture to estimate costs of prescriptions are disclosed herein. An example computer-implemented method, executed by a processor, to estimate a cost of a prescription for a medication includes receiving, with a processor, a prescription for a medication for a patient, receiving, with the processor from an entity, a request for an estimated cost for the prescription, processing, with a machine learning model, the prescription to determine the estimated cost of the medication for the patient, and providing, with the processor, the estimated cost to the entity.

Abstract: A method includes receiving information associated with a stimulus, the information associated with the stimulus comprising first information associated with a medical claim for services provided to a patient and second information associated with a provider that provided the services to the patient; and predicting, using an artificial intelligence engine, when an event will occur in response to the stimulus.

Abstract: In some examples, user models are generated to represent experience of users with respect to their roles. Models that represent conditions are also generated. As part of generating a support element for a particular user, a triggering event is detected (e.g., an update to a user record), a condition is identified, a condition model and a user model are compared to identify a condition preparedness score. This score is used to generate the support element, which is shared with a user device of the user.

Abstract: A false positive removal engine is provided. The false positive removal engine receives detected objects in one or more images. A machine learning classifier computer model, configured with first operational parameters to implement a first operating point, processes the received input to classify each detected object as being a true positive or a false positive to generate a first set of object classifications. If the first set is empty, the false positive removal engine outputs the first set as a filtered list of objects; otherwise the ML classifier computer model is configured with second operational parameters to implement a second operating point, different from the first operating point, which then processes the received input to classify each detected object and generate a second set of objects classified as true positive, which is output by the false positive removal engine as the filtered list of objects.

Abstract: The technologies described herein are generally directed to facilitating operation of a health network control system. In accordance with one or more embodiments, systems described herein can include a processor, and a memory that can store executable instructions that, when executed by the processor, can facilitate performance of operations that can include facilitating receiving, from transceiver of a second device, a first signal that can describe an event related to treatment of the treatment subject. Further, the operations can include, based on an analysis of the subject information, the event information and facility information representative of a group of treatment facilities, selecting a treatment facility that can perform the treatment of the treatment subject, resulting in a selected treatment facility, and facilitating communicating via a second signal to the transceiver of the second device, selected facility information corresponding to the selected treatment facility.