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