Systems and methods for real-time data ingestion to a clinical analytics platform to generate a heat map

• US 8,731,966 B2
• Filed: 09/24/2010
• Issued: 05/20/2014
• Est. Priority Date: 09/24/2009
• Status: Active Grant

• Current Assignee: Humedica Incorporated (UnitedHealth Group Incorporated)
• Original Assignee: Humedica Incorporated (UnitedHealth Group Incorporated)
• Inventors: Huang, Stanley, Pettini, Donald, Bleicher, Paul, Scharer, Ryan, Ye, Hua, Breitenstein, Agenta
• Primary Examiner(s): Chng, Joy
• Application Number:
  US12/890,018
• Publication Number:
  US 20110077973A1
• Time in Patent Office: 1,334 Days
• Field of Search: 705 2- 3
• US Class Current: 705/3
• CPC Class Codes: G06F 3/0481 based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/22 Social work or social welfare, e.g. community support activities or counselling services
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

The clinical analytics platform automates the capture, extraction, and reporting of data required for certain quality measures, provides real-time clinical surveillance, clinical dashboards, tracking lists, and alerts for specific, high-priority conditions, and offers dynamic, ad-hoc quality reporting capabilities. The clinical informatics platform may include a data extraction facility that gathers clinical data from numerous sources, a data mapping facility that identifies and maps key data elements and links data over time, a data normalization facility to normalize the clinical data and, optionally, de-identify the data, a flexible data warehouse for storing raw clinical data or longitudinal patient data, a clinical analytics facility for data mining, analytic model building, patient risk identification, benchmarking, performing quality assurance, and patient tracking, and a graphical user interface for presenting clinical analytics in an actionable format.

Claims

1. A method of ingesting and analyzing healthcare data from a plurality of data sources in real-time, comprising:

connecting to at least one data source;

retrieving data from the data source on a periodic basis to a database;

synchronizing data between the at least one data source and the database;

processing the data to identify data elements, map data elements, and normalize data elements, wherein the data elements are stored in a database,

wherein the mapping comprises assigning data to a field of a database according to a hierarchically organized lexicon of healthcare data elements, wherein multiple data element entries in the lexicon are mapped to a single field for at least one field;

linking the data elements over time to form a longitudinal data record, wherein the longitudinal data records are stored in a longitudinal data warehouse; and

analyzing the longitudinal data records with a computer processor to obtain a heat map, wherein one axis of the heat map relates to a health status and the other axis of the map relates to a prescribing pattern;

wherein the colors of the plot visually indicate the quantifiable differences in prescribing for different statuses of health.

2. The method of claim 1, wherein the periodic basis on which data are retrieved is in real-time.

3. The method of claim 2, wherein realtime is at least as frequent as every five minutes.

4. The method of claim 1, wherein the at least one data source comprises doctor'"'"'s notes from which data are retrieved using natural processing language.

5. The method of claim 1, wherein the at least one data source comprises at least one of an electronic medical record, an electronic health record, a patient medical record, ambulatory clinical data, claims data, paid claims data, adjudicated claims data, inpatient clinical data, pharmacy data, doctor'"'"'s notes, self-reported data, census data, telemetry data, a networked monitor, a home blood pressure device, a home health monitoring device, a sensor device, mortality data, an internal management system, a hospital inventory system, a clinical inventory system, a clinical guideline, a specialty management system and an order set.

6. The method of claim 1, wherein processing the healthcare data also comprises validating the healthcare data elements.

7. The method of claim 1, wherein the health status relates to a diabetic status.

8. The method of claim 1 wherein the prescribing pattern relates to a percentage of patients treated with a particular prescription.

9. The method of claim 1 wherein analyzing further comprises producing a visualization of a referral network that identifies specialists as having at least one of a particular referral rate, care outcome and cost.

10. The method of claim 1 wherein processing to normalize data elements comprises de-identifying said data elements.

11. The method of claim 1 wherein the prescribing pattern relates to an average treatment value.

12. A method of ingesting and analyzing healthcare data from a plurality of data sources in real-time, comprising:

connecting to at least one data source;

retrieving data from the data source on a periodic basis to a database;

synchronizing data between the at least one data source and the database;

processing the data to identify data elements, map data elements, and normalize data elements, wherein the data elements are stored in a database,

wherein the mapping comprises assigning data to a field of a database according to a hierarchically organized lexicon of healthcare data elements, wherein multiple data element entries in the lexicon are mapped to a single field for at least one field;

linking the data elements over time to form a longitudinal data record, wherein the longitudinal data records are stored in a longitudinal data warehouse; and

analyzing the longitudinal data records with a computer processor to obtain a co-morbidity heat map, wherein one axis of the co-morbidity heat map relates to a first health status and the other axis of the map relates to a second health status,

wherein the colors of the plot indicate the presence of a co-morbidity.

13. The method of claim 12, wherein the colors of the plot further indicate a quantification of the co-morbidity.

14. The method of claim 12, wherein the first health status is diabetes and the second health status relates to at least one of an ophthalmic disorder, a peripheral vascular disease (PVD), a Charlson co-morbidity score, a stroke, a cardiovascular disease (CVD), a renal disease, a lipid, and hypertension (HTN).

15. A method of ingesting and analyzing healthcare data from a plurality of data sources in real-time, comprising:

connecting to at least one data source;

retrieving data from the data source on a periodic basis to a database;

synchronizing data between the at least one data source and the database;

processing the data to identify data elements, map data elements, and normalize data elements, wherein the data elements are stored in a database,

wherein the mapping comprises assigning data to a field of a database according to a hierarchically organized lexicon of healthcare data elements, wherein multiple data element entries in the lexicon are mapped to a single field for at least one field;

linking the data elements over time to form a longitudinal data record, wherein the longitudinal data records are stored in a longitudinal data warehouse; and

analyzing the longitudinal data records with a computer processor to obtain a physician heat map, wherein one axis of the physician heat map represents an individual physician and the other axis of the physician heat map relates to a particular characteristic of a physician clinical practice in the care of a particular health status,

wherein the physician heat map is constructed using a self-organizing clustering algorithm which clusters physicians with similar characteristics along one axis.

16. The method of claim 15, further comprising, the algorithm clusters care characteristics along the other axis.

17. The method of claim 15, wherein the color of the plot indicate a measurement of the particular characteristic.

18. The method of claim 15, wherein the at least one data source comprises doctor'"'"'s notes from which data are retrieved using natural processing language.

19. The method of claim 15, wherein processing to normalize the data elements comprises de-identifying the data elements.

20. The method of claim 15, wherein the particular health status is diabetes and the particular characteristic relates to a charge.