Automated computing platform for aggregating data from a plurality of inconsistently configured data sources to enable generation of reporting recommendations

Patent metadata

Field	Value
Publication number	US-2021109915-A1
Application number	US-201916597489-A
Country	US
Kind code	A1
Filing date	Oct 9, 2019
Priority date	Oct 9, 2019
Publication date	Apr 15, 2021
Grant date	—

Abstract

Methods, apparatus, systems, computing devices, computing entities, and/or the like for generating medical research reports automatically collect data from a plurality of separate health data storage systems, standardize the received data to support at least a requested report type, apply one or more machine-learning quality control check to identify potentially inaccurate data included within the received data, and to generate the requested report based at least in part on the standardized, refined data. Moreover, one or more recommended additional reports supported by the refined data set is identified and recommended to a user based at least in part on user attributes and reports initially requested.

First claim

1 . A computer-implemented method for automatically standardizing data received from a plurality of electronic health data sources to generate one or more graphical reports, the method comprising:
receiving, by one or more processors, report initiation data identifying one or more requested reports; receiving, via a plurality of data transmission interfaces, raw health data from a plurality of health data storage systems, wherein the raw health data from each of the plurality of health data storage systems is received through corresponding data transmission interfaces collectively configured to standardize the raw health data into a single data set; applying, via the one or more processors, a machine-learning quality control check to identify inaccurate data included within the raw health data; upon identifying inaccurate data within the raw health data, remediating, via the one or more processors, the inaccurate data within the raw health data; after remediating the inaccurate data within the raw health data, generating, via the one or more processors, a refined data table comprising standardized report data relevant for the one or more requested reports, wherein the standardized report data is generated from the raw health data received from the plurality of health data storage systems; and generating one or more of the requested reports based at least in part on the refined data table.

2 . The computer-implemented method of claim 1 , further comprising:
receiving, user profile data corresponding to a user; determining, via a machine-learning algorithm, one or more additional reports supported by the refined data table; determining a relevance score for each of the one or more additional reports based at least in part on user attribute data reflected within the user profile data; determining one or more recommended additional reports selected from the one or more additional reports based at least in part on the relevance score generated for each of the one or more additional reports; generating a graphical display identifying the one or more recommended additional reports for the user.

3 . The computer-implemented method of claim 1 , further comprising:
querying a report database based at least in part on the report initiation data identifying one or more requested reports to determine standardized report data utilized to generate the one or more requested reports; and wherein generating the refined data table comprises generating table entries corresponding to the determined standardized report data utilized to generate the one or more requested reports within the refined data table.

4 . The computer-implemented method of claim 1 , wherein receiving raw health data from a plurality of health data storage systems further comprises standardizing the raw health data via Application Program Interfaces (APIs) executed by the corresponding data transmission interfaces.

5 . The computer-implemented method of claim 1 , wherein generating the one or more requested reports comprises:
determining an intended use for each of the one or more requested reports; querying a formatting database based at least in part on the intended use determined for each of the one or more requested reports to determine formatting data relevant for each of the one or more requested reports; and generating the one or more requested reports based at least in part on formatting data relevant for each of the one or more requested reports.

6 . The computer-implemented method of claim 1 , wherein receiving raw health data from a plurality of health data storage systems further comprises:
scanning each of the one or more health data storage systems to determine data formats corresponding to raw health data received from each of the one or more health data storage systems; and assigning a data transmission interface to each of the one or more health data storage systems based at least in part on the data formats determined to corresponding to raw data received from each of the one or more health data storage systems.

7 . The computer-implemented method of claim 1 , wherein generating a refined data table further comprises automatically assigning a standard procedure code for data entries within the standardized report data.

8 . A computing system comprising a non-transitory computer readable storage medium and one or more processors, the computing system configured to:
receive report initiation data identifying one or more requested reports; receive via a plurality of data transmission interfaces, raw health data from a plurality of health data storage systems, wherein the raw health data from each of the plurality of health data storage systems is received through corresponding data transmission interfaces configured to standardize the raw health data; apply a machine-learning quality control check to identify inaccurate data included within the raw health data; upon identifying inaccurate data within the raw health data, remediate the inaccurate data within the raw health data; after remediating the inaccurate data within the raw health data, generate a refined data table comprising standardized report data relevant for the one or more requested reports, wherein the standardized report data is generated from the raw health data received from the plurality of health data storage systems; and generate the one or more requested reports based at least in part on the refined data table.

9 . The computing system of claim 8 , wherein the computing system is further configured to:
receive user profile data corresponding to a user; determine, via a machine-learning algorithm, one or more additional reports supported by the refined data table; determine a relevance score for each of the one or more additional reports based at least in part on user attribute data reflected within the user profile data; determine one or more recommended additional reports selected from the one or more additional reports based at least in part on the relevance score generated for each of the one or more additional reports; generate a graphical display identifying the one or more recommended additional reports for the user.

10 . The computing system of claim 8 , wherein the computing system is further configured to:
query a report database based at least in part on the report initiation data identifying one or more requested reports to determine standardized report data utilized to generate the one or more requested reports; and wherein generating the refined data table comprises generating table entries corresponding to the determined standardized report data utilized to generate the one or more requested reports within the refined data table.

11 . The computing system of claim 8 , wherein receiving raw health data from a plurality of health data storage systems further comprises standardizing the raw health data via Application Program Interfaces (APIs) executed by the corresponding data transmission interfaces.

12 . The computing system of claim 8 , wherein generating the one or more requested reports comprises:
determining an intended use for each of the one or more requested reports; querying a formatting database based at least in part on the intended use determined for each of the one or more requested reports to determine formatting data relevant for each of the one or more requested reports; and generating the one or more requested reports based at least in part on formatting data relevant for each of the one or more requested reports.

13 . The computing system of claim 8 , wherein receiving raw health data from a plurality of health data storage systems furt

Assignees

• Unitedhealth Group Inc

Inventors

• Godden Paul J
• Boss Gregory J
• Mccandless Sarah
• Swanson Art

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/2365 Primary

  Ensuring data consistency and integrity · CPC title

• G06F16/258

  Data format conversion from or to a database · CPC title

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G16H15/00 Primary

  ICT specially adapted for medical reports, e.g. generation or transmission thereof · CPC title