Abstract: Methods, computer systems, and computer-storage medium are provided for providing closed-loop intelligence. A selection of data is received, at a cloud service, from a database comprising data from a plurality of sources in a Fast Healthcare Interoperability Resources (FHIR) format to build a data model. After a feature vector corresponding to the data model is extracted, a selection of an algorithm for a machine learning model to apply to the data model is received. A portion of the selection of data is utilized for training data and test data and the machine learning model is applied to the training data. Once the model is trained, the trained machine learning model can be saved at the cloud service, where it may be accessed by others.

Abstract: Methods, computer systems, and computer-storage medium are provided for providing closed-loop intelligence. A selection of data is received, at a cloud service, from a database comprising data from a plurality of sources in a Fast Healthcare Interoperability Resources (FHIR) format to build a data model. After a feature vector corresponding to the data model is extracted, a selection of an algorithm for a machine learning model to apply to the data model is received. A portion of the selection of data is utilized for training data and test data and the machine learning model is applied to the training data. Once the model is trained, the trained machine learning model can be saved at the cloud service, where it may be accessed by others.

Abstract: Methods, computer systems, and computer-storage medium are provided for providing closed-loop intelligence. A selection of data is received, at a cloud service, from a database comprising data from a plurality of sources in a Fast Healthcare Interoperability Resources (FHIR) format to build a data model. After a feature vector corresponding to the data model is extracted, a selection of an algorithm for a machine learning model to apply to the data model is received. A portion of the selection of data is utilized for training data and test data and the machine learning model is applied to the training data. Once the model is trained, the trained machine learning model can be saved at the cloud service, where it may be accessed by others.

Abstract: Methods, computer systems, and computer-storage medium are provided for providing closed-loop intelligence. A selection of data is received, at a cloud service, from a database comprising data from a plurality of sources in a Fast Healthcare Interoperability Resources (FHIR) format to build a data model. After a feature vector corresponding to the data model is extracted, a selection of an algorithm for a machine learning model to apply to the data model is received. A portion of the selection of data is utilized for training data and test data and the machine learning model is applied to the training data. Once the model is trained, the trained machine learning model can be saved at the cloud service, where it may be accessed by others.

Abstract: Methods, systems, and computer-storage media are provided for facilitating the management of population health. A parallel processing architecture receives patient population health data from healthcare facilities along with any updated data. A high-level clinical logic is executed against the data to identify, among other things, patients in the population who qualify for health intervention programs.

Abstract: Methods, systems, and computer-readable media are provided for recreating a state of a clinical computing system for indicating that a specific activity corresponding to a patient increased prior to an event. Sets of data elements for a patient are extracted from the clinical computing system. State changes for each data element are identified. The state of the clinical computing system is recreated prior to the event by concatenating the sets of data elements based on the state changes for each respective data element.

Abstract: Methods, systems, and computer-storage media are provided for facilitating the management of population health. A parallel processing architecture receives patient population health data from healthcare facilities along with any updated data. A high-level clinical logic is executed against the data to identify, among other things, patients in the population who qualify for health intervention programs.

Abstract: Methods, computer systems, and computer-storage medium are provided for providing closed-loop intelligence. A selection of data is received, at a cloud service, from a database comprising data from a plurality of sources in a Fast Healthcare Interoperability Resources (FHIR) format to build a data model. After a feature vector corresponding to the data model is extracted, a selection of an algorithm for a machine learning model to apply to the data model is received. A portion of the selection of data is utilized for training data and test data and the machine learning model is applied to the training data. Once the model is trained, the trained machine learning model can be saved at the cloud service, where it may be accessed by others.

Abstract: Methods, systems, and computer-storage media are provided for facilitating the management of population health. A parallel processing architecture receives patient population health data from healthcare facilities along with any updated data. A high-level clinical logic is executed against the data to identify, among other things, patients in the population who qualify for health intervention programs. Using this information, healthcare facilities can implement management programs to help care for these patients.

Abstract: Methods, systems, and computer-storage media are provided for facilitating the management of population health. A parallel processing architecture receives patient population health data from healthcare facilities along with one or more documents that are in human-readable form. From the human-readable document, computer-readable code is generated that includes high-level clinical logic is executed against the population health data to identify, among other things, patients in the population who qualify for health intervention programs. Using this information, healthcare facilities can implement management programs to help care for these patients.

Abstract: Methods, systems, and computer-readable media are provided for recreating a state of a clinical computing system for indicating that a specific activity corresponding to a patient increased prior to an event. Sets of data elements for a patient are extracted from the clinical computing system. State changes for each data element are identified. The state of the clinical computing system is recreated prior to the event by concatenating the sets of data elements based on the state changes for each respective data element.

Abstract: A method, system and medium are provided for enabling re-creation of a time-ordered sequence of clinical data. Sets of data elements for a patient are received in sequence from a clinical system, and for each data element a time stamp is attached. For any given set of data elements, a maximum time stamp is determined, implying that all events in a clinical system resulting in modifications to data elements contained in the set occurred on or before the maximum time stamp. A subsequent retrieval from a clinical system yields a set of data elements in which the time stamp for each data element occurs after the maximum time stamp from the previous set.

Abstract: Methods, systems, and computer-storage media are provided for generating and populating a feature catalog for use in predictive modeling applications. The feature catalog may be populated with features extracted from data warehoused in a nested, hierarchical data structure. Extraction of features may result from applying a set of rules-based algorithms to warehoused data. Updated features may be extracted from a queue of data updates by applying the same rules-based algorithms. Predictions of future outcomes may be generated by applying predictive models to features.

Abstract: Methods, systems, and computer-storage media are provided for generating and populating a feature catalog for use in predictive modeling applications. The feature catalog may be populated with features extracted from data warehoused in a nested, hierarchical data structure. Extraction of features may result from applying a set of rules-based algorithms to warehoused data. Updated features may be extracted from a queue of data updates by applying the same rules-based algorithms. Predictions of future outcomes may be generated by applying predictive models to features.

Abstract: Methods, computer systems, and computer storage media are provided for utilizing clinical information in disparate formats or structures to generate multiple derived representations of the clinical information, each derived representation structured to meet a particular clinical need. Clinical information is aggregated from multiple, disparate data sources; the clinical information is in a first format. The information is restructured to generate a derived representation of the information; the derived representation is in a second format. The derived representation is communicated to a clinical application that meets the particular clinical need.

Abstract: Methods, systems, and computer-storage media are provided for facilitating the management of population health. A parallel processing architecture receives patient population health data from healthcare facilities along with any updated data. A high-level clinical logic is executed against the data to identify, among other things, patients in the population who qualify for health intervention programs.

Abstract: Methods, systems, and computer-storage media are provided for providing explainability to an end-user on why a particular patient failed to qualify for a health-related measure. High-level clinical logic explainability rules are generated on top of high-level clinical logic used to identify members of a population who qualify and who do not qualify for the health-related measure. The explainability rules are designed to identify which components in the high-level clinical logic are not satisfied by the patient's health data, and, more specifically, which of the components' sub-criteria disqualified the patient from the health-related measure. The output of the explainability rules is structured into an easy-to-understand format that is presented on a user interface associated with an end-user such as a clinician.

Abstract: Methods, systems, and computer-storage media are provided for generating and populating a feature catalog for use in predictive modeling applications. The feature catalog may be populated with features extracted from data warehoused in a nested, hierarchical data structure. Extraction of features may result from applying a set of rules-based algorithms to warehoused data. Updated features may be extracted from a queue of data updates by applying the same rules-based algorithms. Predictions of future outcomes may be generated by applying predictive models to features.

Abstract: A method, system and medium are provided for enabling re-creation of a state of a computing system as it existed at a selected time. A plurality of data elements are tracked including functions and reference information employed in calculating one or more of the data elements. Versions of functions and reference information are also tracked. Thereby, a time at which to recreate the state of the system is selectable and the data elements that were available at or before the selected time are identifiable. And the versions of functions and reference information that were available at the selected time are identifiable. The state of the system at the selected time can thus be reviewed or analyzed as desired.

Abstract: Methods, systems, and computer-storage media are provided for facilitating the management of population health. A parallel processing architecture receives patient population health data from healthcare facilities along with one or more documents that are in human-readable form. From the human-readable document, computer-readable code is generated that includes high-level clinical logic is executed against the population health data to identify, among other things, patients in the population who qualify for health intervention programs. Using this information, healthcare facilities can implement management programs to help care for these patients.