Generating Never-Event Cohorts from Patient Care Data

• US 20100153133A1
• Filed: 12/16/2008
• Published: 06/17/2010
• Est. Priority Date: 12/16/2008
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kraemer, James R., Angell, Robert Lee, Friedlander, Robert R., Hennessy, Richard
• Application Number:
  US12/335,857
• Publication Number:
  US 20100153133A1
• Time in Patent Office: Days
• US Class Current: 705/3
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

The illustrative embodiments described herein provide a computer implemented method, apparatus, and computer program product for generating never-event cohorts. In response to receiving patient care data derived from a population of patients, the patient care data is processed to form digital patient care data. The digital patient care data includes metadata describing a set of patient care patterns associated with one or more patients in the population of patients. The digital patient care data is analyzed using cohort criteria to identify a set of never-event attributes from the set of patient care patterns. The cohort criteria specifies at least one never-event attribute from the set of never-event attributes for each cohort in a set of never-event cohorts. Thereafter, a set of never-event cohorts is generated. The set of never-event cohorts is formed from members selected from the population of patients, and each member of a cohort in the set of never-event cohorts has the at least one never-event attribute in common.

Claims

1. A computer implemented method for generating never-event cohorts, the computer implemented method comprising:

responsive to receiving patient care data derived from a population of patients, processing the patient care data to form digital patient care data, wherein the digital patient care data comprises metadata describing a set of patient care patterns associated with one or more patients in the population of patients;

analyzing the digital patient care data using cohort criteria to identify a set of never-event attributes from the set of patient care patterns, wherein the cohort criteria specifies at least one never-event attribute from the set of never-event attributes for each cohort in a set of never-event cohorts; and

generating the set of never-event cohorts comprising members selected from the population of patients, wherein each member of a cohort in the set of never-event cohorts has the at least one never-event attribute in common.

2. The computer implemented method of claim 1, wherein processing the patient care data further comprises:

identifying a set of never-event patterns from the patient care patterns, wherein the set of never-event attributes are selected from the set of never-event patterns.

3. The computer implemented method of claim 1, wherein generating the set of never-event cohorts further comprises:

identifying, from the set of never-event cohorts, one or more cohorts, wherein each of the one or more cohorts is based on a unique never-event attribute selected from a set of never-event patterns.

4. The computer implemented method of claim 1 further comprising:

identifying each member of the set of never-event cohorts from the patient care attributes.

5. The computer implemented method of claim 1, wherein analyzing the digital patient care data comprises at least one of analyzing the patient care data using historical never-event patterns and analyzing the patient care data with a set of data models.

6. The computer implemented method of claim 1 further comprising:

updating historical never-event patterns with patient care patterns from the set of patient care patterns associated with a never-event attribute in the set of never event attributes.

7. The computer implemented method of claim 1, further comprising:

generating inferences based on the set of never-event cohorts, wherein the inferences indicate a cause of an associated never-event pattern.

8. A computer program product for generating never-event cohorts, the computer program product comprising:

a computer recordable-type medium;

first program instructions for processing patient care data derived from a population of patients to form digital patient care data in response to receiving the patient care data, wherein the digital patient care data comprises metadata describing a set of patient care patterns associated with one or more patients in the population of patients;

second program instructions for analyzing the digital patient care data using cohort criteria to identify a set of never-event attributes from the set of patient care patterns, wherein the cohort criteria specifies at least one never-event attribute from the set of never-event attributes for each cohort in a set of never-event cohorts;

third program instructions for generating the set of never-event cohorts comprising members selected from the population of patients, wherein each member of a cohort in the set of never-event cohorts has the at least one never-event attribute in common; and

wherein the first program instructions, the second program instructions, and the third program instructions are stored on the computer recordable-type medium.

9. The computer program product of claim 8, further comprising:

fourth program instructions for identifying a set of never-event patterns from the patient care patterns, wherein the set of never-event attributes are selected from the set of never-event patterns, and wherein the fourth program instructions are stored on the computer recordable-type medium.

10. The computer program product of claim 8, wherein the third program instructions further comprises instructions for identifying, from the set of never-event cohorts, one or more cohorts, wherein each of the one or more cohorts is based on a unique never-event attribute selected from a set of never-event patterns.

11. The computer program product of claim 8, further comprising:

fifth program instructions for identifying each member of the set of never-event cohorts from the patient care attributes.

12. The computer program product of claim 8 wherein the second program instructions further comprise instructions for at least one of analyzing the patient care data using historical never-event patterns and analyzing the patient care data with a set of data models.

13. The computer program product of claim 8 further comprising:

sixth program instructions for updating historical never-event patterns with patient care patterns from the set of patient care patterns associated with a never-event attribute in the set of never event attributes, and wherein the sixth program instructions are stored on the computer recordable-type medium.

14. The computer program product of claim 8, further comprising:

seventh program instructions for generating inferences based on the set of never-event cohorts, wherein the inferences indicate a cause of an associated never-event pattern, wherein the seventh program instructions are stored on the computer recordable-type medium.

15. An apparatus for generating never-event cohorts, the apparatus comprising:

a bus system;

a memory connected to the bus system, wherein, the memory includes computer usable program code; and

a processing unit connected to the bus system, wherein the processing unit executes the computer usable program code to process patient care data derived from a population of patients to form digital patient care data in response to receiving the patient care data, wherein the digital patient care data comprises metadata describing a set of patient care patterns associated with one or more patients in the population of patients;

analyze the digital patient care data using cohort criteria to identify a set of never-event attributes from the set of patient care patterns, wherein the cohort criteria specifies at least one never-event attribute from the set of never-event attributes for each cohort in a set of never-event cohorts; and

generate the set of never-event cohorts comprising members selected from the population of patients, wherein each member of a cohort in the set of never-event cohorts has the at least one never-event attribute in common.

16. The apparatus of claim 15, wherein the processing unit further executes the computer usable program code to identify a set of never-event patterns from the patient care patterns, wherein the set of never-event attributes are selected from the set of never-event patterns.

17. The apparatus of claim 15, wherein the processing unit further executes the computer usable program code to identify, from the set of never-event cohorts, one or more cohorts, wherein each of the one or more cohorts is based on a unique never-event attribute selected from a set of never-event patterns.

18. The apparatus of claim 15, wherein the processing unit further executes the computer usable program code for analyzing the digital patient care data for at least one of analyzing the patient care data using historical never-event patterns and analyzing the patient care data with a set of data models

19. A system for generating never-event cohorts, the system comprising:

a set of sensors, wherein the set of sensors captures facility event data, wherein the facility event data is a component of patient care data, and wherein the patient care data comprises a set of patient care patterns;

a patient care pattern processing engine, wherein the patient care pattern processing engine forms digital patient care data from the patient care data; and

a cohort generation engine, wherein the cohort generation engine generates a set of never-event cohorts from the digital patient care data, wherein each member in the set of patient care cohorts share at least one never-event attribute in common.

20. The system of claim 19, further comprising:

an inference engine, wherein the inference engine generates inferences based on the set of never-event cohorts, wherein the inferences indicate a cause of an associated never-event pattern.