Abstract: Methods and systems for anomaly detection in relational databases. The methods and systems perform operations comprising: accessing a data object including a data set that has been collected over a given time interval; selecting a reference data point from the data set; computing an angle representing a data growth rate of the data set at least within the given time interval relative to the reference data point; determining that the angle representing the data growth rate of the data set within the given time interval exceeds a specified threshold; and in response to determining that the angle representing the data growth rate of the data set within the given time interval exceeds the specified threshold, triggering an anomaly detection operation.

Abstract: A computer-implemented method includes selecting a group of sets. Each set has values for immutable attributes that match values for at least one mutable attribute in a prediction request. The method includes determining a conditional covariance matrix for the group of sets. The method includes generating a deviation model based on the conditional covariance matrix. The method includes sampling the deviation model to generate multiple sets of likely mutable attribute values. The method includes automatically selecting a neural network from a set of outcome models based on the likely mutable attribute values. Each neural network includes a set of layers. Each layer includes a set of nodes. A first layer receives inputs at the set of nodes of the input layer. Each layer other than the first layer receives outputs from a preceding layer and creates modified outputs. A last layer outputs the modified outputs from the neural network.

Abstract: A smart mirror system includes a screen configured to generate a display for viewing by a user, a mirror positioned in front of the screen, a near-field-communication (NFC) card reader located behind the mirror, a network interface for communicating with a remote health data server, memory configured to store computer-executable instructions, and at least one processor configured to execute the instructions. The instructions include selectively detecting, by the NFC card reader, an NFC chip of a member card placed in proximity to the NFC card reader. The instructions include, in response to detecting the NFC chip, obtaining member information from the detected NFC chip, and authenticating the user to the remote health data server, via the network interface, according, at least in part, to the obtained member information.

Abstract: An apparatus includes processing circuitry and a memory storing instructions that, when executed by the processing circuitry, cause the apparatus to identify a plurality of components and a data flow that interconnects the plurality of components. The instructions cause the apparatus to determine a lineage of a record generated by the plurality of components based on the data flow. The lineage indicates the data flow from a first component to a second component of the plurality of components to generate the record. The instructions cause the apparatus to present, to a user, a visual depiction of the lineage of the record. The visual depiction indicates the data flow of a query through at least the first component and the second component of the plurality of the components to generate the record.

Abstract: A computer-implemented method includes determining whether historical profile data structures are stored in a database with corresponding structured supplemental data and selected health care plan option identifiers of a set of health care plan option identifiers. The method includes generating historical feature vectors using the historical data structures stored in the database or generating the historical feature vectors using created sample profile data structures. The method includes training machine learning models using the generated historical feature vectors, selecting one of the machine learning models for use in generating recommendation outputs, presenting an interactive voice interface to an entity to generate audio questions and prompts for obtaining response data from the entity, classifying voice survey responses of the entity, and generating feature vectors.

Abstract: Methods and systems for analyzing data are described. In one embodiment, a method comprises a processor receiving a data analysis algorithm over a network and executing the data analysis algorithm, the data analysis algorithm analyzing data stored in a database using machine learning to identify a database organizational format, the data analysis algorithm identifying one or more locations for a set of data stored on the database based on identifying the database organizational format, the data analysis algorithm parsing the set of data to identify whether any entries in the database associated with the set of data includes a particular value, and the data analysis algorithm communicating over the network at least a first number of entries in the database that include the particular value and a second number of entries in the database that do not include the particular value.

Abstract: A computerized analysis system includes a data retrieval module, a spike filter module, a chargemaster analysis module, and an alert module. The data retrieval module is configured to retrieve claimline data for a period of time from an input data store. The claimline data includes billing codes and prices of the billing codes associated with a provider. The spike filter module is configured to flag and filter price spikes in the claimline data. The chargemaster analysis module is configured to determine whether a changepoint exists in the billing codes in the claimline data. The chargemaster analysis module is configured to identify a chargemaster increase for the provider in response to a statistical parameter of changepoints exceeding a threshold. The alert module is configured to, in response to identification of a chargemaster increase, publish an alert that a chargemaster increase has occurred for the provider.

Abstract: An analysis system includes a data retrieval module that retrieves claimline data for a period of time. The claimline data includes multiple billing codes and corresponding prices associated with a provider. An analysis module receives the claimline data from the data retrieval module, determines whether a changepoint exists in the billing codes in the claimline data, determines a statistical parameter of changepoints per day during the period of time, and identifies a chargemaster increase for the provider in response to the statistical parameter of changepoints exceeding a threshold. An alert module, in response to identification of a chargemaster increase, publishes an alert that a chargemaster increase has occurred. The alert includes the provider's identification, a chargemaster increase date, a claimline number, a changepoint number, the billing code identification, or a price of the billing code at the changepoint. The alert transforms a user interface displayed to a user.

Abstract: An apparatus may be configured to determine an industry object model based on an industry of a data set of an enterprise; generate an archive package for an archive time point by, for each data source, determining archival data of the data source to be archived and transforming the archival data of the data source into a set of data source objects based on the industry object model, and storing, in the archive package, the data source objects for each data source; identify a subset of the data source objects to be purged based on a purge time point; and remove the subset of the data source objects from the archive package. An apparatus may also be configured to generate and store a set of global objects that are represented in the data set, and to associate the set of data source objects with the set of global objects.

Abstract: A computer system includes memory configured to store software application files, and a processor configured to execute computer executable instructions. The instructions include identifying a target software application, archiving files of the target software application, and creating, in the directory, one or more replacement executable files that correspond to one or more executable files of the target software application. The instructions include detecting, by a first replacement executable file of the one or more replacement executable files, an execution call to the first replacement executable file corresponding to a first executable file of the target software application. The instructions include, in response to detection of the detected execution call, restoring files of the target software application and forwarding the detected execution call to the first executable file of the target software application in the directory to allow the first executable file to process the detected execution call.

Abstract: A forecasting system includes a processor and memory. The memory stores a time-series data store and instructions. The instructions include, in response to receiving a forecasting request from a user device for an entity including input data, determining a measure of uncertainty associated with the input data. The input data includes a proposed action and a forecast period. The instructions include obtaining a set of historical data from the time-series data store associated with the proposed action and generating a forecast model using the set of historical data, the input data, and the measure of uncertainty to predict outcomes incrementally during the forecast period. The instructions include determining a predicted outcome using the forecast model for the entity at an end of the forecast period and, in response to the predicted outcome exceeding a threshold, generating a communication indicating the proposed action and transmitting the communication to the user device.

Abstract: A classification computing system provides adaptable taxonomies to facilitate user navigation of complex information systems. The classification computer includes a memory and a processor. The processor is configured to receive a collection of file indices from the information server. The processor is configured to apply a taxonomical classification algorithm to the collection to generate a collection of classified file indices. The classified file is associated with at least one taxonomical classification. The processor is further configured to apply a flow algorithm to the collection to generate at least one flow path used to provide a user access to a first subset of taxonomical classifications and restricts access to at least a second subset of taxonomical classifications. The flow path is responsive to user input parameters. The processor is configured to receive a user input parameter. The processor is additionally configured to provide the flow path to the user computing device.

Abstract: A computer system includes memory hardware and at least one processor. The memory hardware stores a credential database and computer-executable instructions. The credential database includes multiple user profiles and multiple credentials. Each credential specifies one or more function privileges for each user profile that has been granted the credential.

Abstract: A data movement system is provided for moving data using a data-to-file-to-data movement path. The data movement system includes a source database, a target database, a configuration database, and a data movement server. The data movement is in communication with the source database, the target database, and the configuration database. The processor is configured to receive a configuration record including source details and target details. The processor is also configured to define an extraction query based on the source details and to apply the extraction query to the source database to obtain an extraction load. The processor is further configured to generate a load file based on the extraction load, to define a load script based on the target details, and to apply the load script to the load file to obtain a load query. The processor is also configured to update the target database with the load query.

Abstract: A method for authenticating access to private health information (PHI) includes receiving a converted version of a spoken initiation of a retrieval of PHI. The method also includes requesting out-of-band authentication information from a user. The out-of-band authentication information that is requested contains different information than the spoken initiation of the retrieval of the PHI. The method also includes determining whether the out-of-band authentication information received from the user satisfies an authentication criterium associated with the user, obtaining the PHI requested by the user via the spoken initiation provided to the first device responsive to the out-of-band authentication information, and presenting the PHI requested by the user via the first device.

Abstract: A computer readable medium includes a data set with data stored in rows and N columns. Each of the rows is associated with one individual patient. Each of the N columns is associated with one type of data for patients. One or more processors is configured to: initialize missing values in M ones of the N columns with M values for the M ones of the N columns, respectively; generate M mathematical models for the M ones of the N columns having one or more missing values; for each of the rows having one or more missing values, update ones of the M values for the M ones of the N columns; and fill missing values in the M ones of the N columns with the M values, respectively.

Abstract: Methods and systems for performing operations comprising: accessing one or more data objects including a data set that has been collected over a given span of time, the data set representing a plurality of parameters corresponding to resource utilization of a given server; computing first and second statistical measures based on the plurality of parameters; obtaining current resource utilization corresponding to at least a subset of the plurality of parameters; determining a first condition in which values of the current resource utilization exceed a first threshold associated with the first statistical measure; determining a second condition in which values of the data set corresponding to a time period associated with the current resource utilization exceed a second threshold associated with the second statistical measure; and triggering an anomaly detection operation in response to determining the first and second conditions.

Abstract: A method for providing prediction based healthcare recommendations is performed by a healthcare prediction server. The method includes receiving an emergency room services request from a patient. The method also includes receiving a first portion of the plurality of historical claims data. The first portion includes associated historical outcome data. The method further includes applying a geospatial prevalence engine to the first portion of the plurality of historical claims data and the requestor location to identify at least one locally prevalent disease. The method additionally includes applying a claims processing engine to the first portion of the plurality of historical claims data and the requestor identifier to determine whether the patient is associated with at least one prior avoidable emergency room claim. The method includes predicting that the emergency room services request is associated with an avoidable visit. The method further includes transmitting an alternative services request.

Abstract: A claim editing engine for automated integration and error resolution of claim records is provided. The processor of the engine is configured to extract a set of claim components of a plurality of claim components. The processor is further configured to transform the set of claim components to conform to a standardized data format. The processor is also configured to integrate the set of transformed claim components into a set of unified claims by unifying each of the set of transformed claim components having matching claim identifiers into a unified claim. The processor is configured to apply a rule set to the set of unified claims to generate a simulation of execution of the set of claims and identify errors in the simulated execution. The processor is configured to transmit an instruction to resolve each identified error. The processor is configured to cause each resolved unified claim to be processed.

Abstract: A computer-implemented method of mapping attribute names of a source data model to a destination data model includes obtaining multiple source attribute names from the source data model, and obtaining multiple destination attribute names from the destination data model. The destination data model includes multiple attributes that correspond to attributes in the source data model having different attribute names. The method includes processing the obtained source attribute names and the obtained destination attribute names to standardize the attribute names according to specified character formatting, supplying the standardized attribute names to a machine learning network model to predict a mapping of each source attribute name to a corresponding one of the destination attribute names, and outputting, according to mapping results of the machine learning network model, an attribute mapping table indicating the predicted destination attribute name corresponding to each source attribute name.