Abstract: The present invention concerns a system for optimizing employee retirement contributions comprising an optimization computer having one or more processors configured by code executing therein to access data from one or more retirement plan participants and derive, based on the accessed data, a hierarchy of proposals to maximize one or more features of the retirement account and to transmit such a derived hierarchy, and using a remote device configured to receive the hierarchy of retirement proposals and to generate in response to the transmission, a plurality of graphical elements, each graphical element corresponding to a particular strategy.

Abstract: Method for removing personal data from a medical record includes receiving a first digital medical record associated with a first patient, the first digital medical record including personal data and medical data; generating a first fingerprint by applying a cryptographic function to at least a portion of the personal data; transferring the first fingerprint to one or more computing devices; identifying a first alias associated with the first fingerprint, wherein identifying the first alias includes at least one of determining that the first fingerprint was previously stored along with the first alias, and generating the first alias and storing the first fingerprint and the first alias; transferring the first alias to the workstation of the first user; and generating a first clean digital medical record based on the first alias and the first digital medical record.

Abstract: A method for determining a risk of decompensated heart failure in a user includes receiving a first set of data that is fixed with respect to time. A machine-learning model generates one or more initial risk factors based on the first set of data. A second set of data for the user that dynamically updates over time is received from a wearable cardiovascular physiology monitor. The machine-learning model is used to generate dynamic data classifiers based on the one or more initial risk factors. Aggregate risk scores for the user are then indicated based on an evaluation of the second set of data against the dynamic data classifiers. In this way, static electronic medical records may be combined with dynamic, real-time data from wearable cardiovascular physiology monitors to provide an accurate and continuously updating risk of decompensated heart failure for a user.

Abstract: A method includes receiving a medical report created by a medical professional at a creation time. Prior to elapsing of a fixed-length time frame starting at the creation time, report analysis data for the medical report is automatically generated via performance of a report processing function. Correction requirement notification data is generated based on the report analysis data indicating at least one correction requirement. Communication of the correction requirement notification data to the medical professional is facilitated.

Abstract: Medical devices and related patient management systems and methods are provided. An exemplary system includes a medical device to obtain measurement values for a physiological condition in a body of a patient and a computing device to identify a plurality of event patterns within a plurality of monitoring periods based on the measurement values, prioritize the plurality of event patterns based on one or more prioritization criteria, filter the prioritized list of event patterns based on one or more filtering criteria, and generate a snapshot graphical user interface display. The snapshot graphical user interface display includes a graph overlay region having a graphical representation of the measurement values with respect to a time of day and an event detection region below the graph overlay region, where the event detection region includes pattern guidance displays for event patterns of the filtered prioritized list ordered according to the prioritization.

Abstract: Techniques are described herein for drawing conclusions using free form texts and external resources. In various embodiments, free form input data (202) may be segmented (504) into a plurality of input data segments. A first input data segment may be compared (510) with an external resource (304) to identify a first candidate conclusion. A reinforcement learning trained agent (310) may be applied (512) to make a first determination of whether to accept or reject the first candidate conclusion. Similar actions may be performed with a second input data segment to make a second determination of whether to accept or reject a second candidate conclusion. A final conclusion may be presented (522) based on the first and second determinations of the reinforcement learning trained agent with respect to at least the first candidate conclusion and the second candidate conclusion.

Abstract: A clinical data interface device provides integrated portions of the electronic medical record system to identify and confirm a patient file for receiving data and personality modules for receiving and translating data from a variety of clinical device monitors for that identified patient.

Abstract: The present disclosure provides a method and system for providing medical services to a user. The method may include acquiring first information of a medical process including a plurality of sub-processes to be allocated with medical resources. The method may also include obtaining second information on medical resources, and the second information may include available time slots and locations of the medical resources. The method may further include allocating the medical resources for the medical process based on the first information and the second information. The method may also include determining, for at least one sub-process of the plurality of sub-processes of the medical process, appointment information of the at least one sub-process based on at least a portion of the second information corresponding to the medical resource allocated to the at least one sub-process.

Abstract: Hospital readmissions may be prevented. Readmission is prevented by predicting the probability of a given patient to be readmitted. The probability alone may prevent readmission by educating the patient or medical professional. The probability may be predicted during a patient stay and used to generate a workflow action item to reduce the probability, to warn, to output appropriate instructions, and/or assist in avoiding readmission. The probability may be specific to a hospital, physician group, or other entity, allowing prevention to focus on past readmission causes for the given entity.

Abstract: An approach is provided for improving a workflow by using cognitive computing. Inputs about a claim of a claimant are received. The inputs include a history of claims by the claimant, an expected cost of processing the claim, a length of time the claimant has had insurance coverage, governmental requirements associated with the claim, a fraud score associated with the claim, and a ranking and a clustering of previously processed claims. Based on the inputs and using a cognitive computing system, a set of digital workers is selected. The set of digital workers complete step(s) in a current context of a processing of the claim in a workflow. Responsive to completing the step(s), a total number of steps required in the workflow is reduced.

Abstract: In accordance with some embodiments, an alternative system for processing a data packet received via a secure pharmacy prescription claim network is provided, in which data included in the data packet as received from a pharmacy system is modified prior to being routed to a PBM. The data packet may be modified such that a first BIN/PCN is replaced by a second BIN/PCN and a Consumer Price is added. The alternative system allows for a third party to act as a switchboard for prescription claims such that requests for prescription claims received from pharmacy systems are pre-adjudicated and data packets included in the requests are modified prior to being routed to a PBM selected by the third party.

Abstract: A system and method providing device configuration using quick response (QR) and/or other machine readable codes. The system and method reduce the time and costs associated with configuring devices/equipment based on site plans while also reducing the potential for errors during the configuration process.

Abstract: A computer-implemented method and corresponding output generator for handling alarm events, generated by a subject/patient monitoring device, and generating clinician-perceptible outputs indicative of the alarm events. Alarm events are divided into non-actionable and actionable alarm events. Information on non-actionable alarm events is stored. Stored information on non-actionable alarm events is contained in a clinician-perceptible output generated in response to detecting an actionable alarm event.

Abstract: A method and system of facilitating communication within a healthcare environment is disclosed. The healthcare environment has a directory of providers and a patient census system having patients and patient events. The method and system include a database server configured and arranged to receive and store patients and patient events from the patient census system and providers from the directory, the providers automatically mapped to patients based on predetermined criteria. Patient events are recorded in the patient census system and automatically pushed to the providers mapped to the respective patient in real-time. Preferably, the patient events are pushed to mobile device carried by providers, wirelessly and in real-time. Providers may manage, create and assign patient events via the mobile device, which assigned providers receive and may act on or complete.

Abstract: A method, apparatus and computer program product are provided for providing rebate claim validation. A drug manufacturer or associated computer may receive rebate claims from pharmacy benefit managers (PBMs). The manufacturer should not be obligated to pay the rebate if the associated prescription drug was initially sold by the manufacturer under a discount program such as 340B. However, manufacturers may not be able to discern which rebate claims are associated with a discount program. A service provider utilizes adjudicated prescription claims from a contract pharmacy, and encounter data from a covered entity to validate the rebate claims and indicate to the manufacturer whether a rebate claim is associated with a discount program such as 340B.

Abstract: Systems and method for method for increasing security in online transfers by maintaining anonymity of transferors are described herein. In an embodiment, a label tracking system receives a request to generate labels for an account of an account holder. The system generates a plurality of labels in response to the request and send the plurality of labels to an account computing device which stores a mapping of labels to identification information. The system receives an allocation request from the account computing device and stores allocations for each of the generated labels. When the system receives a request to perform a transfer between two labels, without changing any items within the account and without receiving identification information corresponding to the labels, the system updates the labels by decrementing an amount allocated to the transferor label and incrementing an amount allocated to the transferee label.

Abstract: A method for generating predictions for year-over-year change in drug spending and per member per month spending and for providing the predictions via a web portal includes receiving data collected from a health plan. The data includes per member per month costs of the health plan and demographic information of members of the health plan. The method includes selecting therapeutic classes based on the per member per month costs and demographic information, segmenting the data by the therapeutic classes, and detecting patterns by analyzing the segmented data. The method includes generating models for the therapeutic classes based on the patterns, and generating predictions for year-over-year change in drug spending and per member per month spending for the therapeutic classes by utilizing the models. The method includes providing the predictions via a web portal in at least one of a displayable graphical format and a downloadable data structure.

Abstract: Disclosed is a method for setting authority for use of a brain stimulation device and a device implementing the same, and the method for setting authority for use of a brain stimulation device according to the present disclosure comprises the steps in which: a communication unit of a personal communication device receives, from a server device, a time token for which the authority for use of the brain stimulation device is set; the communication unit transmits the time token to the brain stimulation device or the server device; and after a time corresponding to the usage time of the brain stimulation device stored in the time token has elapsed, the communication unit receives, from the brain stimulation device or the server device, a message to delete the time token or to change the value of a specific field of the time token.

Abstract: Systems and methods are provided for automating the process of automatically determining appropriateness of surgical team services performed during a medical procedure. Clinical resource data with known surgical guideline indicator (SGIs) may be us used to generate and store a mapping of medical procedure codes to indications of the appropriateness of surgical team services corresponding to the medical procedure codes. A medical bill associated with an insurance claim may be analyzed to extract a medical procedure code corresponding to a surgical procedure, and an automated adjudication recommendation for the medical bill may be made based on the mapping between medical procedure codes and SGIs.

Abstract: In some instances, the disclosure provides a method for managing and updating contextual intelligent processes using artificial intelligence algorithms. The method comprises obtaining, from a user device, health information indicating a health triggering event associated with a user, obtaining event information associated with the user, determining, based on the health triggering event, one or more contextual intelligent processes for the health triggering event, retrieving one or more contextual artificial intelligence datasets, updating the one or more contextual intelligent processes with at least one new service based on inputting the health triggering event, the event information, and the one or more contextual intelligent processes into the one or more contextual artificial intelligence datasets, and performing the one or more updated contextual intelligent processes.

Abstract: Methods for dynamic routing of queued network-based communications using real-time information and machine learning are performed by systems and devices. Requests associated with fulfillments are received over a network from requestor systems, and the requests are queued in a data structure of a queue. Information that includes geolocation information from a user device of a user that is associated with the fulfillment, temporal information from the user device, or related request information associated with another request is then received over the network, and a fulfiller and a fulfillment time for the fulfillment are determined from the information. The request is provided from the queue to the fulfiller at the fulfillment time over the network.

Abstract: The subject matter herein provides a method, apparatus and computer program product that combines, in one intuitive interface, visualization user interfaces (UIs) as used for descriptive analytics, with workflow UIs as used for predictive analytics. These interfaces provide a visual workspace front-end. The workspace is coupled to a back-end that comprises a data processing engine that combines progressive computation, approximate query processing, and sampling, together with a focus on supporting user-defined operations, to drive the front-end efficiently and in real-time. The processing engine achieves rapid responsiveness through progressive sampling, quickly returning an initial answer, typically on a random sample of data, before continuing to refine that answer in the background. In this manner, any operation carried out in the platform immediately provides a visual response, regardless of the underlying complexity of the operation or data size.

Abstract: A computer-implemented system for training a subject to improve psychophysiological function for performance of stress-inducing activity includes a sensor interface device and a non-transitory, tangible computer readable storage medium storing computer program code. The sensor interface provides measurement of a physiological parameter of the subject, indicating stress in the subject. The computer readable storage medium stores computer code that provides a set of training segments presenting the subject with one or more visual, audible, or tactile prompts wherein at least one of the training segments simultaneously presents the subject with a stress-inducing prompt while inducing the subject to perform a relaxation-inducing protocol.

Abstract: Some implementations provide a computer-implemented method for identifying, from on-line postings, reports of potential adverse effects resulting from consuming a healthcare product, the method including: receiving a log of on-line postings regarding consuming the healthcare product; receiving a database comprising a healthcare taxonomy and a set of linguistic rules; analyzing, based on the healthcare taxonomy, the log of on-line postings to identify a report of at least one adverse effect resulting from consuming the healthcare product; generating a score for the identified report according to the healthcare taxonomy and the set of linguistic rules; comparing the generated score with a threshold; and in response to determining that the generated score is above the threshold, flagging the identified report as a report of a potential adverse effect.

Abstract: Systems and methods are disclosed for interacting with a prescription submission system, a cloud computing system, and a prescription processing system to transmit prescriptions to an optimal pharmacy based on user information. User information, a location, and a prescription including a treatment e.g., medicine) may be received from a user or a health care professional. A plurality of pharmacies may be identified based at least on availability of the treatment, each of the plurality of pharmacies meeting a location criterion based on the location. Treatment pricing may be identified for each of the identified plurality of pharmacies. The plurality of pharmacies and the corresponding pricing information may be transmitted to a computing device. A selected pharmacy from the plurality of pharmacies may be received, from the computing device, and, the prescription may be transmitted to be received at the selected pharmacy's prescription processing system.

Abstract: Systems, methods, and apparatuses for providing a central location to manage permissions provided to third-parties and devices to access and use user data and to manage accounts at multiple entities. A central portal may allow a user to manage all access to account data and personal information as well as usability and functionality of accounts. The user need not log into multiple third-party systems or customer devices to manage previously provided access to the information, provision new access to the information, and to manage financial or other accounts. A user is able to have user data and third-party accounts of the user deleted from devices, applications, and third-party systems via a central portal. The user is able to impose restrictions on how user data is used by devices, applications, and third-party systems, and control such features as recurring payments and use of rewards, via a central portal.

Abstract: Predictions can be provided for admission, discharge, pathway, and units for a patient during a stay at a healthcare facility. In some aspects, a computing device receives initial data regarding the patient and generates an admission or discharge prediction indicating a probability that the patient will be admitted to or discharged from the healthcare facility. The computing device segments portions of the initial data into segmented data and stores the segmented data in one or more of a plurality of segmentation categories. The computing device compares the segmented data to one or more patterns of a predictive model and, based on the comparing, generates a total length-of-stay (LOS) prediction indicating a duration of time for which the patient will stay at the healthcare facility.

Abstract: A method, an apparatus and a computer program product for evaluating demographics of viewers of live-streamed videos. A stream data of a video stream provided to an audience over the Internet via a live-streaming platform may be obtained. The stream data comprise information describing a content of the video stream. Each viewer may be identified in the video stream using a handle. Demographic information of a viewer may be estimated, automatically by a computerized device, based on the stream data and the handle of the viewer. An aggregated demographic information of the audience may be estimated based on the demographic information of a plurality of viewers comprised by the audience. Actions may be performed based on the aggregated demographic information of the audience.

Abstract: A neural network is trained with patient historical data including features of patient pathways and labels characterizing a type of the patient pathways. During a runtime phase, the trained neural network matches a current patient profile with the patient historical data to extract selected portions of clinical practice guidelines (CPGs) identified according to one or more generated CPG models, the patient pathway models, and the current patient profile.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for improving distributed monitoring using different groups of remote devices. In some implementations, a system communicates with a set of remote devices involved in a first monitoring program that involves collection of data from the remote devices over a communication network. The system identifies a pattern or similarity among monitoring data collected from a subset of the remote devices involved in the first monitoring program. The system determines that the identified pattern or similarity satisfies one or more criteria for initiating additional monitoring. In response, the system determines parameters specifying second types of data to collect in a second monitoring program. The system configures one or more devices to perform monitoring for the second monitoring program including acquiring data for the second types of data and providing the acquired data to a server over the communication network.

Abstract: A medical monitoring system for use in residential facilities, nursing homes, or home environments is disclosed. The system utilizes a variety of modules and wearable medical devices that convey vital patient information to a series of smart hubs which are connected to the cloud. In the event a change in medical status of a patient occurs, the health care workers receive an Alert notifying them of which specific patient needs attention. The system is monitored using a specialized dashboard.

Abstract: The present invention discloses a personal health record system with a process decision support function. By constructing a personal health record system with separated characteristic data extraction and characteristic data analysis, characteristic data that meets analysis requirements is expected to be rapidly obtained. A statistics query interface based on characteristic data and time logic is provided, and decision support for users is completed through steps such as characteristic matching, process classification and statistics evaluation, and process recommendation, so as to make medical big data better execute high-level information analysis and decision support functions.

Abstract: The present invention discloses a unified identification protocol for training and health, comprising: unified multipurpose identifier that serves to identify individuals and the relationships established with these individuals, such as relationships with entities, professionals, products, services and transactions, generation of a multipurpose identifier, unique, non-transferable and univocally distinguishable through a computer system. The computer system that identifies them universally to avoid identification errors, based on UUID, DID and/or other formats and unify the data of the same individual existing in different systems, stored in one or several electronic devices of the individual and/or their legal guardians and, additionally, in one or more cloud services, certify access permissions granted/revoked to the different data compartments in the profile of the individual and the authenticity of the data, carried out in one or more distributed data ledger technologies or blockchains.

Abstract: A system and computer-implemented method for detecting and addressing billing fraud by an asserted provider of a good or service based on location data associated with card-based financial transactions by an asserted recipient and collected, stored, analyzed, and acted on by a payment card network to determine and respond to a likelihood of fraud. A computer stores locations of the recipient based on uses of a payment card over a time period, and determines a location of the provider based on location data associated with a card reader at a particular time at which the good or service was allegedly provided. The computer compares the two locations for the particular time and generates a fraud score based on a likelihood that the recipient was physically capable of being at the provider location at the particular time, and based on the score, may notify the recipient and decline the payment request.

Abstract: Computer-implemented systems and methods automatically track the dynamic composition of a patient-care team by combining and harvesting information from at least two electronic audit trails: (1) a trail recording access to electronic medical records (EMR), e.g., read-access to patient data, electronic prescriptions and physician orders, etc., and (2) a trail recording electronic communications (email, text messages, etc.) regarding and referencing the patient.

Abstract: Systems and methods are disclosed for reducing redundancy in medical database management. An example system may include an application program interface communicatively linked to a user interface associated with each of: a plurality of hospital information systems, a plurality of source devices associated with each of the plurality of hospital information systems, and a plurality of electronic data management systems. The system may further include a mapping module configured to map lexical tokens between patient-specific data forms used by each of the system components. An example method may performed by a computing device having one or more processors may include receiving, from the source devices, patient-specific health data; generating updates to patient-specific electronic health records (EHR) for patients; generating patient-specific electronic data capture (EDC) data associated with the patients, and updating electronic data management systems with the patient-specific EDC data.

Abstract: Embodiments in the present disclosure relate generally to computer network architectures for machine learning, artificial intelligence, and risk adjusted performance ranking of healthcare providers. Embodiments of computer network architecture automatically make risk adjusted performance rankings of healthcare service providers and generate and transmit reports of the rankings. Embodiments may generate such rankings either occasionally on demand, or periodically, or as triggered by events such as an update of available data for such forecasts. Embodiments may include a combination of third-party databases to generate the updated forecasts for pending patient clinical episodes, and to drive the forecasting models for the same, including social media data, financial data, socio-economic data, medical data, search engine data, e-commerce site data, and other databases.

Abstract: The present disclosure is directed to an instrument kit tracking system that includes a housing that has tracking electronics that is contained in either a compartment or wall of the medical instrument kit or in a standalone unit that is affixed to a medical instrument kit to contain and protect an electronic device from external temperatures between 120-135° C.; where the medical instrument kit contains at least one medical instrument. The internal temperature of the instrument kit tracking system is maintained such that the electronic device contained therein is operable when the external temperature is between 120-135° C. A further layer, such as of a thickness of 1 mm, resides between the electronic device and the outer walls of the compartment or module. Access to the tracking electronics may also be selectively lockable.

Abstract: Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of receiving attribute data comprising a set of unstructured attribute data and a set of structured attribute data, analyzing the set of unstructured attribute data by processing through a first set of one or more Long Short Term Memory (LSTM) layers, to obtain an unstructured semantic signature, analyzing the set of the structured attribute data by processing through a first set of one or more Convolutional Neural Network (CNN) layers, to obtain a structured semantic signature, analyzing the unstructured semantic signature and the structured semantic signature, and classifying the item in one or more item categories. Other embodiments are disclosed herein.

Abstract: A system for enhanced personal property replacement (i) builds a virtual inventory of personal belongings, such as by performing object recognition techniques on mobile device digital images with the customer's permission or affirmative consent; (ii) receives user preferences transmitted from their mobile device; (iii) receives a request from the user to handle an insurance claim after an insurance-related event; (iv) determines items to purchase for the user based upon the user preferences, and/or the extent of damage; and/or (v) transmits, to a retailer remote server a virtual order for the items to be delivered to the user at a temporary (hotel) or permanent (home) address. Insurance claim monies may be used to pay for the items. As a result, after an event (e.g., fire, tornado, hurricane), household or other goods may be automatically purchased and delivered to a customer to alleviate the negative impact of the event on their life.

Abstract: A server may maintain information about entities such as medical entities. A user device can send search queries to the server to obtain information about a particular medical entity. The server and/or the user device may maintain information relating to the particular medical entity in a manner that a relationship between the particular medical entity and the user device can be obfuscated from the server. By doing so, privacy of a user of the user device can be protected.

Abstract: A system (100) includes an end point prediction engine (150) that predicts an end point (302) using a machine learning model (132) and one or more clinical report objects (152) for a patient, wherein the machine learning model inputs the one or more clinical report objects and outputs the predicted end point according to phrases or n-grams in the one or more clinical report objects. An end point visualization interface (160) visualizes the predicted end point (302) using a scorecard (162) or a timeline (164). An end point modeling engine (130) generates the machine learning model from training data that includes validated end points (122) and clinical report objects (116).

Abstract: The present disclosure provides systems and methods for automatically generating telemedicine platforms for providers. A marketplace of healthcare services and associated pricing and other terms is made available to employers, individuals, and/or health insurance companies. Employers and/or health insurance companies can select a subset of options from the marketplace to create a customizable sub-marketplace of healthcare services to offer to their employees or insureds. Providers may modify their offerings in the marketplace to fit within guidelines established by the employers or health insurance companies to be automatically included in the sub-marketplace of healthcare services.

Abstract: A method is for comparing reference values in medical imaging processes of different medical imaging devices. In an embodiment, the method includes providing a data base of reference values, each reference value of the data base being assigned to a defined global identification specifying the medical imaging process; creating a label for the medical imaging process at a local medical imaging device using the defined global identification; and providing a mapping assigning a local identification to the defined global identification, for supporting the creation of the label for the medical imaging process.

Abstract: A property analyzer device may include (1) a receiver configured to receive property identification information from a mobile device, the received property identification information including a picture of the property and/or a property location; (2) a retriever configured to retrieve property-related information from multiple property sources (such as public record databases, websites, or an internal company database) based upon the received property identification information; (3) a processor configured to consolidate the retrieved property-related information into a consolidated property-related image of the property; and (4) a transmitter configured to transmit the consolidated property-related image to the mobile device for review by a user.

Abstract: A healthcare system, platform and methods for providing enhanced medical diagnostics and treatment are herein provided. The platform includes a healthcare knowledge graph database for storing a medical hybrid knowledge graph, the hybrid knowledge graph including healthcare data from one or more ontology-based knowledge graphs and clinical data from one on more sources; a data processing engine running a diagnostic algorithm, designed to process a patient condition data and to process a hybrid knowledge graph database, and select one or more pathways on the knowledge graph to generates one or more differential diagnoses for suspected disorders, which relate to the given patient condition; and a user interface to enable an end user to view results output by the data processing engine.

Abstract: A computer network implemented system for improving the operation of one or more biofeedback computer systems is provided.

Abstract: Information about a medical provider's locations, brands, and gateways can be received (e.g., via an online portal). This information can be used to generate a data object that represents relationships between the locations, the brands, and the gateways. This data object can be maintained in a database base that is searchable by a user device. For example, a user of the user device may search the database to identify a medical provider where the user obtains care. Once identified, other systems can be used to connect the user device to a gateway associated with the medical provider in order to download electronic health record data associated with the user.

Abstract: A multi-vendor risk relationship data store may contain electronic records representing a plurality of risk relationships between multiple vendors and an enterprise and, for each risk relationship, an electronic record identifier and a set of attribute values. An information sharing portal computer server may exchange an information request with a remote vendor platform. The information request may be, for example, associated with an employee of a sponsor associated with the vendor platform. The server may process the information request via a customized vendor-specific information sharing portal interface display and execute an algorithm to adjust, based on at least one attribute value, interactions with the vendor platform via the portal interface display. The server may also aggregate information associated with a plurality of vendor platforms and transmit the aggregated information to a remote administrator device associated with the enterprise.

Abstract: There is provided a computer implemented method for generating summary images from 3D medical images, comprising: receiving a 3D medical image, dividing the 3D medical images into a sequence of a plurality 2D images, computing a similarity dataset indicative of an amount of similarity between each pair of the plurality of 2D images, segmenting the similarity dataset into a plurality of slabs by minimizing the amount of similarity between consecutive slabs and maximizing the amount of similarity within each slab, aggregating, for each respective slab, the plurality of 2D images into a respective summary image, and presenting on a display, the respective summary image.