Abstract: An improved adherence monitoring system increases the efficiency for obtaining patient adherence information. The improved adherence monitoring system reduces network traffic with regards to the communication of patient adherence information. The improved adherence monitoring system automates an adherence notification pathway. The improved adherence monitoring system can increase patient adherence by increasing the efficiency of medication therapy. The improved adherence monitoring system may also increase the efficiency by which patient adherence information is disbursed.

Abstract: A non-invasive computer-aided diagnosis system generates a diagnosis of mild cognitive impairment, a disease state which often leads to the development of Alzheimer's disease. The system uses as inputs both functional positron emission tomography and structural magnetic resonance imaging data, reconstructs a model of the patient's cortex, uses machine-learning techniques to generate probabilities for mild cognitive impairments for local cortical regions, uses machine-learning techniques to fuse the local diagnoses to generate a global diagnosis based on each imaging modality, then uses machine-learning techniques to fuse the modality-specific global diagnoses to generate a final global diagnosis.

Abstract: Disclosed herein are system, method, and computer program product embodiments for providing a data collection and integration system. An embodiment operates by determining that first data and second data retrieved from a first and second data sources are stored in a database. Both the first data and the second data are each categorized, and at least a portion of the first one of the categories includes identical information for both the first data and the second data. On a visual interface, a visual representation of the categorized first data is displayed simultaneously with the categorized second data, including the categorized identical information, and input indicating whether the identical information refers to a same entity is received. The database and the visual interface are updated based on the input.

Abstract: A computer system generates a clinical summary for a patient based on machine learning. One or more templates are generated, each indicating medical information for a corresponding clinical summary with respect to a medical condition of a patient. Preferences for medical information for each corresponding clinical summary are learned based on a history of desired medical information for clinical summaries for the medical condition. The learned preferences are applied to the one or more templates. A clinical summary is generated with respect to the medical condition of the patient based on the one or more templates with the learned preferences. Embodiments of the present invention further include a method and program product for generating a clinical summary for a patient based on machine learning in substantially the same manner described above.

Abstract: A medical data managing apparatus includes processing circuitry. The processing circuitry generates network access data based on patient information of a patient. The processing circuitry acquires the reference data from a data generating device via a communication network constructed based on the network access data, and checks the reference data against benchmark data included in the patient information. The processing circuitry acquires, when it is determined that the reference data and the benchmark data represent same patient as a result of the check, the multiple non-DICOM data from the data generating device via the constructed communication network. The processing circuitry classifies each of the multiple non-DICOM data into first non-DICOM data to be registered in a data archive apparatus or other second non-DICOM data, and displays the first non-DICOM data and the second non-DICOM data on a display in different display modes.

Abstract: Systems, methods, and devices, including computer-readable media, for managing operation of devices in complex systems and changing environments. In some implementations, a server system stores data indicating management plans for each of a plurality of different devices, each management plan indicating a device-specific set of program states for programs in a predetermined set of programs. The server system alters the management plans and enforces interdependence of the programs, and the server system generates a customized instruction that alters operation of the device according to the device-specific set of program states assigned in the altered management plan for the device. The server system causes each device to perform one or more operations of the device determined according to the device-specific set of program states assigned in the altered management plan for the device.

Abstract: Contract tracing systems and methods for infectious disease tracking are disclosed. An infectious disease tracking system includes a plurality of user devices, each user device configured to detect, using a wireless communication module, a signal emitted by another one of the plurality of user devices. The user device can determine that a strength of the signal exceeds a predetermined event initiation signal strength threshold corresponding to a physical proximity between users of the devices and can store a contact tracing event record in response to determining that the strength of the signal exceeds the predetermined event initiation signal strength threshold. The user device can transmit the contact tracing event records to a data center where they can be stored and used to identify close contacts when an index case of an infectious disease is identified.

Abstract: A computer implemented method modifies a unit of medical equipment based on never-event cohorts, where a never-event is a preventable error experienced by a patient while receiving medical care. One or more processors process patient care data to form digital patient care data. The processor(s) analyze the digital patient care data using cohort criteria to identify a set of never-event attributes from the set of patient care patterns. The processor(s) receive, from a set of sensors, facility event data that describe an electrical fault in a unit of medical equipment used on patients in the patient care facility in order to modify the digital patient care data, and then modify the unit of medical equipment in order to correct the electrical fault based on the modified digital patient care data.

Abstract: Methods and apparatus, including computer program products, are provided for processing analyte data. In some exemplary implementations, there is provided a method. The method may include selecting at least one module from among a plurality of modules, the selection performed based on metadata including one or more of the following rules: whether the at least one module can be used with a type of device, whether the at least one module can be used with a glycemic state of a host, and whether the at least one module can be used with an expected volume of data generated by the type of device; and generating a report including the selected at least one module configured to present information representative of the glucose concentration level measured in the host. Related systems, methods, and articles of manufacture are also disclosed.

Abstract: Electronic messages, such as emails, often ask questions, ask that a task be done, or assign a task. The responsive messages often forget to answer the questions and the responders often forget to calendar tasks. Advances in natural language processing provide computers the ability to notice the questions and task requests/assignments. Automated analysis of the messages can detect and highlight questions, can provide for draft responses addressing every question, and can provide for getting tasks calendared.

Abstract: A system comprises a toolset to render a protocol, such as an industry clinical treatment guideline, into a process map. The process map includes a workflow having a time-based series of steps determined from the protocol. The system performs recursive matching to match events in electronic medical records (EMRs) to nodes in threads in the protocol map to determine protocol compliance. The EMRs include unstructured data, and specialized query objects may be generated to retrieve relevant data for the process map from the unstructured EMR data.

Abstract: A system, method, server, and computer readable medium for tracking goal progression. Input establishing accounts for providers serving a client is received. The client is an individual receiving treatment or assistance. The accounts are stored in a server available through one or more networks. The client is assigned to one or more of the providers in response to selections from an administrator. Goals and a plan of action are established for the client in response to treatments and assistance required. Data associated with the client received from the providers is compiled. A determination is made whether thresholds associated with the goals are being met based on the compiled data.

Abstract: A system, method, and computer-readable media are provided for facilitating clinical decision making, and in particular, decision making based on a third party's clinical situation by determining and providing useful, up-to-date information, such as patient-related information to a decision maker. In one embodiment, a user first identifies an information item concerning a patient. Based on that item, a reference pointer, which identifies the information item, is generated. The reference pointer is communicated to the user's mobile device. Subsequently, the user's mobile device receives updates related to the reference pointer.

Abstract: A dental charting system and method of generating a dental chart are provided. The dental charting system comprises a display unit, an input unit and an output unit. The display unit is configured to display a quadrant view of a set of teeth. The quadrant view comprises a quadrant subset of the set of teeth, and at least one of a diagnosis field and a procedure field for each tooth in the quadrant subset. Each tooth in the quadrant subset displayed having a crown, a root and an outline. The input unit is configured to receive an input for at least one of the diagnosis field and the procedure field for at least one tooth in the quadrant set of teeth. The output unit is configured to generate a dental chart displaying the set of teeth. Each tooth in the set of teeth displayed in a color associated with the received input for at least one of the diagnosis field and the procedure field.

Abstract: A financial management tool that includes calculated health care costs and health-based longevity to provide information to retirees to be able to calculate the amount of money that needs to be saved to cover retirement expenditures is provided with actual claims and actual related cost data from a database to increase the cost projection reliability of the tool.

Abstract: A secure medical device system (30; 30?) includes a computer processing device (42) that includes a processor, memory in communication with the processor, an interface enabling communication between the processor and a diagnostic test unit (40; 40?), a first wireless access point (48A), computer-readable instructions stored in the memory and executable by the processor providing a locally-served web site (46) that is browser accessible over the first wireless access point, and a second wireless access point (48B) operable concurrently with and independent from the first wireless access point. The locally-served web site is adapted to receive control instructions over the first wireless access point and to generate command signals transmittable over the interface to the diagnostic test unit, and the second wireless access point enables communication between the processor and an external network (36).

Abstract: Systems and methods for mapping configuration items to business functions within a corporate infrastructure are disclosed. Discovery processes to automatically create and update service maps may introduce an artificial dependency between configuration items that is not necessary to the business function represented in the service map. These unnecessary dependencies may be considered “noise” and unnecessarily complicate the service map. Using machine learning techniques and procedures to identify short lived connections embodiments in accordance with this disclosure, dependency connections that may be considered noise may be detected and flagged. Once detected, these connections may be automatically removed from the service map to improve its accuracy and usefulness. Additionally, a user interface is provided that explains the “reason codes” for identification of noise connections.

Abstract: A stateless, on-demand semantic indexing and search service for a health information exchange is provided that anticipatorily fetches data from one or more external sources, extracts semantic concepts from textual documents, and serves an in-memory semantic search index to users to ease finding of relevant patient data across a set of distributed health record data sources. Clinicians may search for not only text, but for semantic concepts, and the search index is able to return relevant results regardless of whether the source information is located inside or outside the local electronic health record. Predictive algorithms may be incorporated to pre-fetch, semantically process and index data for patients likely to be searched in an upcoming time window. Activity indicators for clinicians and patients may be utilized to pre-fetch, semantically process, and index data.

Abstract: A physiological monitor touchscreen interface presents interface constructs on a touchscreen display that are particularly adapted to finger gestures so to change at least one of a physiological monitor operating characteristic and a physiological touchscreen display characteristic.

Abstract: Resolving conflicting data among data objects associated with a common entity includes assigning an ordered sequence of data analysis processes to a corresponding data field of a plurality of data objects associated with a common entity. At least two of the data objects include different values for the corresponding data field, and each data analysis process performs a different technique to resolve conflicts between different values of data. The ordered sequence of data analysis processes is executed to determine a consensus value to serve as a value for the corresponding data field of each of the plurality of data objects. The data analysis processes are successively executed in the ordered sequence until the consensus value is determined for the corresponding data field.

Abstract: Computer systems, devices, and associated methods of serializing a web page that is of a first format and includes a plug-in including properties of a second format are disclosed herein. In one embodiment, a method includes identifying, in a manifest for the plug-in, properties for inclusion in the first format in a serialized web page. The manifest may also include metadata associated with the properties in the list of properties. The method includes formatting the properties, including associated property values and metadata, in the first format and adding the formatted properties to the serialized web page. The plug-in properties not included in the manifest can be added to the serialized web page in the second format.

Abstract: The present disclosure discloses method and a critical event managing system for managing time-critical events associated with critical devices. The critical event managing system identifies time-critical events from plurality of events based on predetermined factors related to the plurality of events. The plurality of events is determined from first procedural sequences identified from procedural narration by a practitioner and stored protocol manual. At least one of missed and incorrect events are determined based on comparison between reference and observed values associated with critical devices. A revised execution plan is provided iteratively based on historical data, data provided by practitioner, first procedural sequences, and metadata associated with plurality of parameters.

Abstract: Generally, the present disclosure is directed to anonymizing patient data in a multi-modality medical processing system. The method and system described herein automatically remove information from medical data that could identify the patient from which it was acquired, so as to protect the privacy of the patient. Specifically, the anonymizing is performed without intervention from a human to limit errors and incomplete information deletion. Further, data sets in different medical modalities may be anonymized at the same time, and multiple patient cases corresponding to different patients may be anonymized at the same time to increase efficiency.

Abstract: According to some embodiments, a selection server is in communication with a potential communication device database and a currently participating device database, the potential communication device database storing information about communication devices associated with a transition from a first state to a second state, including at least one communication address associated with each communication device. The selection server may automatically identify a communication device as meeting a pre-determined criteria and copy information about the identified communication device from the potential communication device database to the currently participating device database.

Abstract: Systems and methods for generating a graphical interface and tracking patient adherence to a medical treatment plan are presented. The graphical interface may present to a patient the medical treatment plan. The patient may receive scores and points based on adherence to the medical treatment plan. The medical treatment plan may be updated based on the patient's scores, adherence to the medical treatment plan, and progress.

Abstract: The present invention relates to a method and a system (400) for filling a closed container (200) with a fixative solution. The system comprises a container (200) comprising a container body (230) for receiving a biological specimen, a lid (220) for selectively closing the container body (230) and a port (100) forming a unidirectional barrier in a direction from the inside (IC) to the outside (OC) of the closed container (200). The system further comprises a dispensing apparatus (500) having a filling nozzle (300) for dispensing the fixative solution. The filling nozzle (300) is relatively moveable with respect to the container (200) between a retracted position and a filling position to fill the container (200) with the fixative solution.

Abstract: Techniques for extracting clinical entities from clinical documents are provided. In some embodiments, a non-transitory machine-readable medium stores a program. The program receives a clinical document partitioned into a set of sections. Each section in the set of sections includes a plurality of terms. The program further identifies a section in the set of sections. The program also determines a subset of a plurality of entity recognizers based on a classification of the section. Each entity recognizer in the plurality of entity recognizers is configured to identify terms in the section as being associated with a particular type of data. The program further sends the section to the subset of the entity recognizers for processing. The program also generates a clinical statement based on terms identified in the section by the subset of the plurality of entity recognizers.

Abstract: Disclosed is a parking management system that includes a central database in communication with a server, at least one user device, at least one merchant console, and a parking gate controller device over a network. The central database is provided to receive and store data from a plurality of parking systems. A processor is provided for analyzing the data received by the central database. A dynamic data engine is provided for analyzing the data from the plurality of parking systems and generating dynamic pricing data. A targeted promotion engine is provided for analyzing user data and generating a targeted promotion. The dynamic pricing data may be provided to the user device to allow a user to book a parking space from one of the parking systems. The targeted promotion may be provided to the user device to allow the user to select a promotion offered from a merchant.

Abstract: There is a need for solutions that increase efficiency and reliability of medical record processing systems. This need can be addressed, for example, by receiving a free-form primary provider input from a primary provider profile; detecting one or more information deficiencies in the primary provider input, wherein each information deficiency indicates a respective query; for each identified information deficiency of the one or more information deficiencies, identifying a supportive profile associated with the respective information deficiency, causing the supportive profile computing entity associated with the respective supportive provider profile to present an audiovisual interface that includes an indication of the respective query associated with the information deficiency, and receiving a supportive provider input from each supportive provider profile; and generating a collaborative record for the primary provider input based on the primary provider input and each received supportive provider input.

Abstract: The present disclosure provides a video identification method, a video identification device and a storage medium. The video identification device extracts an image and an optical flow from a video, classifies the image by using a first machine learning model to obtain a first classification result, classifies the optical flow by using a second machine learning model to obtain a second classification result, wherein a depth of the first machine learning model is larger than a depth of the second machine learning model, and fuses the first classification result and the second classification result to obtain the identification result of the video.

Abstract: A method for de-identifying protected health information (PHI) associated with electronic medical records (EMRs) based on a common analysis structure (CAS) is provided. The method may include detecting a system event associated with a system comprising the EMRs. The method may further include in response to detecting the system event, detecting a first CAS associated with the EMRs. The method may further include extracting first CAS data associated with the first CAS, wherein the first CAS data comprises unstructured data associated with the EMRs and normalized annotations based on CAS objects that are associated with the unstructured data. The method may further include obfuscating the unstructured data associated with the first CAS. The method may also include generating a second CAS comprising the obfuscated unstructured data and a copied version of the normalized annotations, wherein the copied version of normalized annotations are correlated with the obfuscated unstructured data.

Abstract: In some implementations a computer-accessible medium includes a multimedia-document integration module that includes a heterogeneous distinction identifier between a first multimedia-document and a second multimedia-document and includes an integrator of the first multimedia-document and the second multimedia-document into an integrated multimedia-document, a data capture module that includes a data-extractor of the integrated multimedia-document, a query module that includes a query-generator encapsulated in a corresponding number of enquiry/inquiry transmissions, the enquiry/inquiry transmissions being short-message-service text-messages, a communication-subsystem that includes a transmitter of the enquiry/inquiry transmissions to an external device and receiver of an acknowledgement transmission or a negative-acknowledgement transmission from the external device, the acknowledgement/negative-acknowledgement transmission being a short-message-service text-message, and, a variance analytic module that includ

Abstract: An application file defines a first data object that identifies a fast healthcare interoperability resources (FHIR) server and a second data object that identifies a data type associated with the FHIR server. Based on the first data object and the second data object, a FHIR model requests data of the data type from the FHIR server. The FHIR server provides the requested data, which is received by the FHIR model. Based on the received data, the FHIR model generates data in a user interface (UI) control format and provides the generated data to a UI module that causes a UI to be presented. The FHIR model supports binding of complete entities such as patients or organizations to a UI. This binding enables the requesting of whole entities from a FHIR endpoint, provision of the entity data to the UI, and updating the FHIR data.

Abstract: Methods and systems of monitoring and managing a facility including a plurality of end point devices. One system includes an end point device including an electronic processor, the electronic processor powered by an energy source local to the end point device. The electronic processor is configured to receive data from at least one electro-mechanical element of a fixture associated with the facility, the data related to an operation of the fixture. The electronic processor is also configured to convert the data pursuant to a networking protocol. The electronic processor is also configured to enable, over a network associated with the networking protocol, transmission of the converted data for virtual processing.

Abstract: A computer-implemented method includes receiving a message of a pharmacy customer wherein the message includes a text string, and generating a set of one or more intents corresponding to the pharmacy customer by analyzing the text string using a trained machine learning model, wherein each of the one or more intents correspond to a respective desired action pertaining to the pharmacy order. The machine learning model may be a classification model. The method further includes generating at least one response message based on the set of intents corresponding to the pharmacy customer and transmitting the at least one response message to a mobile device associated with the pharmacy customer. The set of one or more intents may be chosen from a list of commonplace pharmacy customer intents.

Abstract: A computing system receives geolocation information indicating aggregated locations of mobile devices configured to move in a geographic area. The geolocation information comprises measured location(s) for a given mobile device of the mobile devices. The system generates a time series representing mobility network graphs over a first time period. The time series is generated by, for each subperiod in the time series, generating data representing estimated movement of member(s) of a population between locations within the geographic area. The estimated movement is estimated based on the geolocation information and a total population for the geographic area. The system generates metric(s) derived from the time series. The system determines contamination information indicating a respective contamination status for locations for each subperiod of the time series. The system generates a computer model to predict changes in the contamination information in a second time period subsequent to the first time period.

Abstract: Mechanisms are provided for implementing a disambiguation engine for disambiguating content. Electronic content is received from a corpus of electronic content, and analyzed to identify an ambiguous portion of content. The ambiguous portion of content is a portion of the electronic content whose meaning is not made explicit in the ambiguous portion of content. A context associated with the ambiguous portion of content is determined and a set of one or more context based ambiguous content interpretation rules associated with the determined context is applied to the ambiguous portion of content to generate an interpretation of the ambiguous portion of content. The ambiguous portion of content is annotated based on the interpretation to generate disambiguated electronic content which is stored for processing as part of a subsequent operation.

Abstract: Systems, methods, and computer-readable media having computer-executable instructions embodied thereon for providing cloud rules and an alerting framework are provided. In embodiments, one or more rules associated with one or more healthcare information systems are received. The one or more rules each designate an initiating and at least one target application. One or more actions are associated to each target application. The initiating application is monitored for a trigger associated with the one or more rules. In embodiments, the trigger causes the one or more actions to be communicated to each target applications. In embodiments, the one or more actions initiate various changes in a display associated with each target application.

Abstract: A method and system of audibly broadcasting responses to a user based on user queries about a specific patient molecular report, the method comprising receiving an audible query from the user to a microphone coupled to a collaboration device, identifying at least one intent associated with the audible query, identifying at least one data operation associated with the at least one intent, associating each of the at least one data operations with a first set of data presented on the molecular report, executing each of the at least one data operations on a second set of data to generate response data, generating an audible response file associated with the response data and providing the audible response file for broadcasting via a speaker coupled to the collaboration device.

Abstract: A computer system utilizes a dataset to support a research study. Regions of interestingness are determined within a model of data records of a first dataset that are authorized for the research study by associated entities. Data records from a second dataset are represented within the model, wherein the data records from the second dataset are relevant for supporting objectives of the research study. Data records from the second dataset that fail to satisfy de-identification requirements are removed. A resulting dataset is generated that including the first dataset records within a selected region of interestingness and selected records of the second dataset within the same region. The second dataset records within the resulting dataset are de-identified based on the de-identification requirements. Embodiments of the present invention further include a method and program product for utilizing a dataset to support a research study in substantially the same manner described above.

Abstract: A computer system utilizes a dataset to support a research study. Regions of interestingness are determined within a model of data records of a first dataset that are authorized for the research study by associated entities. Data records from a second dataset are represented within the model, wherein the data records from the second dataset are relevant for supporting objectives of the research study. Data records from the second dataset that fail to satisfy de-identification requirements are removed. A resulting dataset is generated that including the first dataset records within a selected region of interestingness and selected records of the second dataset within the same region. The second dataset records within the resulting dataset are de-identified based on the de-identification requirements. Embodiments of the present invention further include a method and program product for utilizing a dataset to support a research study in substantially the same manner described above.

Abstract: Techniques for electronic medical record (EMR) integration are described. A middleware application may receive a command from a third-party application via an electronic network. The command may conform to a unified data format specified by a unified data model. The command may include a request to retrieve data from or write data to an EMR system. The middleware application may convert, using a mapping registrar, the command into a data format compatible with the EMR system. The middleware application may transmit, via another electronic network, the converted command to the EMR system. The middleware application may receive a response from the EMR system. The middleware application may convert, using a mapping registrar, the response into a result that may conform to the unified data format. The middleware application may transmit the converted result to the third-party application.

Abstract: A power injector system having a power injector for enabling delivery of fluid in an injection procedure to be performed on a patient may include one or more processors; a first user interface; and a second user interface. The first user interface and the second user interface may be configured to accept a plurality of user inputs associated with control of a plurality of operations of the power injector system and display information associated with the plurality of operations. One of the first user interface and the second user interface may be proximate to the power injector and the other may be remote from the power injector. The one or more processors may be programmed and/or configured to independently control the first user interface and the second user interface based on a first user input and a next user input received from the first user interface and/or the second user interface.

Abstract: Systems and methods for monitoring accurate, real-time medicament device events, performing analytics on that data, and providing notifications are described. In various embodiments, an application server receives controller medication events, analyzes the events, associated event times, and controller medication dosage plans to characterize event times and send notifications for future doses. The controller medication dosage plan may specify a dose time for a planned dose, a narrow time window comprising the dose time, and an expanded time window comprising the narrow time window and longer in duration than the narrow time window, and the events may be characterized based on their time relative to the dose time, the time windows, and other events.

Abstract: A system rapidly produces training cases for machine based learning by automatically creating training cases from a database of historical data. The system determines a plurality of attributes relevant to each of the training cases. The system identifies a first attribute of the plurality of attributes as an issue, and a second attribute of the plurality attributes as a response to the issue. The system identifies a plurality of cohort members from the database of historical data, where each cohort member comprises cohort member attributes that match a subset of the plurality of attributes. The system analyzes the cohort member attributes of each of the plurality of cohort members to identify the most frequent responses to the issue. The system creates the training cases where each training case comprises the issue and the most frequent responses. The system then trains a machine based learning system using the training cases.

Abstract: Embodiments relate to systems and methods for coordinating, arranging and/or managing transportation. These systems and methods can be used and applied in a variety of settings and industries, including healthcare, travel, hospitality, event, dining and entertainment, and others.

Abstract: A computer-implemented method for scheduling processing of an order for goods at a provider location obtains an arrival estimate for when a user associated with the order is expected to arrive at the provider location and uses the arrival estimate to schedule processing of the order. Processing may be scheduled so that completion of order processing is expected to substantially coincide with arrival of the user at the provider location. The method may also obtain an order completion estimate for when processing of the order is expected to be completed and use both the arrival estimate and the order completion estimate to schedule processing of the order. The method may update one or both of the arrival estimate and the order completion estimate. The method may be executed by a networked mobile wireless telecommunication computing device of the user, or by a data processing system associated with the provider.

Abstract: A system to remotely perform medication reconciliation for a patient in a health care facility using medication records for the patient stored in a client computing device is provided. The system can include the client computing device, servers to securely transfer medication records between the client computing device and a health care facility computer system. The servers, client computing device and a health care facility computer system communicatively coupled via the Internet.

Abstract: A system (10) for personalization of patient pathways and treatment options includes a patient information database (32) which stores patient data relating to a patient's medical records. A patient personalization system (12) receives the patient's lifestyle values and preferences and evaluates choices of pathways and treatments and a clinical decision support system (18) generates choices of pathways and treatments from the patient data and the patient's lifestyle values and preferences.

Abstract: Mechanisms are provided to implement a patient summary generation engine with deduplication of instances of medical concepts. The patient summary generation engine parses a patient electronic medical record (EMR) to extract a plurality of instances of a medical concept, at least two of which utilize different representations of the medical concept. The patient summary generation engine performs a similarity analysis between each of the instances of a medical concept to thereby calculate, for a plurality of combinations of instances of the medical concept, a similarity metric value. The patient summary generation engine clusters the instances of the medical concept based on the calculated similarity metric values for each combination of instances in the plurality of combinations of instances of the medical concept to thereby generate one or more clusters, and select a representative instance of the medical concept from each cluster in the one or more clusters.