Health care incident prediction

• US 8,825,568 B2
• Filed: 06/06/2012
• Issued: 09/02/2014
• Est. Priority Date: 06/06/2011
• Status: Active Grant

• Current Assignee: RLDatix North America Inc. (DATIX (Holdings) Ltd.)
• Original Assignee: Radicalogic Technologies, Inc. (DATIX (Holdings) Ltd.)
• Inventors: Smith, Mike, Malaviya, Sanjay
• Primary Examiner(s): Chen, Alan
• Assistant Examiner(s): Bharadwaj, Kalpana
• Application Number:
  US13/489,928
• Publication Number:
  US 20130144816A1
• Time in Patent Office: 818 Days
• Field of Search: 706/12
• US Class Current: 706/12
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16H 70/00 ICT specially adapted for the handling or processing of medical references

Abstract

Embodiments described herein relate to apparatuses and methods for incident prediction alerts for transmission to a health care organization system by applying rules to data sets. Each rule may define a set of data elements linked to an incident, and a processor may detect one or more sets of data elements in the data sets. The processor may normalize the data feeds, generate rules on historical data, generate prediction alerts by applying rules to near-real time data feeds, train to update rules, validate and error check rules, remove statistical noise, generate visualizations for the data feeds, and receive input and feedback data.

Claims

1. A computer implemented method for generating one or more incident prediction alerts for one or more health care organizations, the method comprising:

monitoring one or more data sets;

detecting an occurrence of a triggering event;

upon detecting the occurrence of the triggering event, developing one or more rules linked to the triggering event, wherein the triggering event comprises at least one incident that occurred or almost occurred at the one or more health care organizations; and

applying the one or more rules to the one or more data sets to detect the presence of one or more variables defined by the one or more rules;

wherein the one or more variables are linked to the conditions of the one or more health care organizations related to the at least one incident that occurred or almost occurred at the one or more health care organizations.

2. The method of claim 1 wherein the one or more data sets comprise one or more historical data sets relating to the at least one incident that occurred or almost occurred at the one or more health care organizations, and wherein developing the one or more rules comprise, for each incident that occurred or almost occurred at the one or more health care organizations, training on the one or more historical data sets to identify the one or more variables common to the at least one incident that occurred or almost occurred at the one or more health care organizations.

3. The method of claim 2 wherein the one or more data sets comprise one or more near-real time data feeds regarding machines, devices and patients of the one or more health care organizations and other data relevant to the one or more health care organizations for incident prediction.

4. The method of claim 3 further comprising normalizing the one or more near-real time data feeds, generating rules on the one or more historical data sets, generating the one or more incident prediction alerts by applying the one or more rules to the one or more near-real time data feeds, training to update the one or more rules, validating and error checking the one or more rules, removing statistical noise from the one or more near-real data feeds, generating visualizations for the one or more near-real data feeds, and receiving input and feedback data.

5. The method of claim 1 wherein the one or more rules are based on one or more pattern matching algorithms.

6. The method of claim 1 wherein each of the one or more variables comprise of a type and a value.

7. The method of claim 2 further comprising training on the one or more historical data sets to determine a probability of incident occurrence, and wherein at least one of the one or more incident prediction alerts is generated based on the probability of incident occurrence.

8. The method of claim 1, the method further comprising providing an interface for reporting occurrences of the at least one incident that occurred or almost occurred at the one or more health care organizations and receiving the one or more near-real data feeds relating to the occurrences of the at least one incident that occurred or almost occurred at the one or more health care organizations.

9. The method of claim 1, wherein the one or more incident prediction alerts comprise at least one of predictions, indications or other determinations that an incident has occurred or will likely occur.

10. A system comprising a processor and a non-transitory computer readable storage medium storing instructions which when executed by the processor, configure the processor to generate incident prediction alerts for one or more health care organizations by:

monitoring one or more data sets;

detecting an occurrence of a triggering event;

upon detecting the occurrence of the triggering event, developing one or more rules linked to the triggering event, wherein the triggering event comprises at least one incident that occurred almost occurred at the one or more health care organizations; and

applying the one or more rules to the one or more data sets to detect the presence of one or more variables defined by the one or more rules;

wherein the one or more variables are linked to the conditions of the one or more health care organizations related to the at least one incident that occurred or almost occurred at the one or more health care organizations.

11. The system of claim 10 wherein the one or more data sets comprise one or more historical data sets relating to the at least one incident that occurred or almost occurred at the one or more health care organizations, and wherein developing the one or more rules comprise for each incident that occurred or almost occurred at the one or more health care organizations, training on the one or more historical data sets to identify the one or more variables common to the at least one incident that occurred or almost occurred at the one or more health care organizations.

12. The system of claim 11 wherein the one or more data sets comprise one or more near-real time data feeds regarding machines, devices and patients of the one or more health care organizations and other data relevant to the one or more health care organizations for incident prediction.

13. The system of claim 12 wherein the processor is configured to normalize the one or more near-real time data feeds, generate rules on the one or more historical data sets, generate prediction alerts by applying the one or more rules to the one or more near-real time data feeds, train to update rules, validate and error check the one or more rules, remove statistical noise from the one or more near-real data feeds, generate visualizations for the one or more near-real data feeds, and receive input and feedback data.

14. The system of claim 10 wherein the processor is configured to develop the one or more rules based on one or more pattern matching algorithms.

15. The system of claim 10 wherein each of the one or more rules is linked to at least one of the one or more healthcare incidents, and each incident is linked to at least one of the one or more rules.

16. The system of claim 10 wherein each of the one or more variables comprise a type and a value.

17. The system of claim 11 wherein the processor is further configured to train on the one or more historical data sets to determine a probability of incident occurrence, and wherein at least one of the one or more incident prediction alerts is generated by the processor based on the probability of incident occurrence.

18. The system of claim 10 wherein the processor configured to provide an interface for reporting occurrences of the at least one incident that occurred or almost occurred at the one or more health care organizations and to receive the one or more near-real data feeds relating to the occurrences of the at least one incident that occurred or almost occurred at the one or more health care organizations.

19. The system of claim 10 wherein the one or more incident prediction alerts comprise at least one of predictions, indications or other determinations that an incident has occurred or will likely occur.

20. Non-transitory computer readable medium with instructions encoded thereon to configure a processor to generate one or more incident prediction alerts for transmission to one or more health care organization systems by:

monitoring one or more data sets;

detecting an occurrence of a triggering event;

upon detecting the occurrence of the triggering event, developing one or more rules linked to the triggering event, wherein the triggering event comprises at least one incident that occurred or almost occurred at the one or more health care organizations; and

applying the one or more rules to the one or more data sets to detect the presence of one or more variables defined by the one or more rules;

wherein the one or more variables are linked to the conditions of the one or more health care organizations related to the at least one incident that occurred or almost occurred at the one or more health care organizations.

21. The computer readable medium of claim 20 wherein the one or more data sets comprise one or more historical data sets relating to the at least one incident that occurred or almost occurred at the one or more health care organizations, and to further configure the processor to develop rules by, for each incident that occurred or almost occurred at the one or more health care organizations, training on the one or more historical data sets to identify the one or more variables common to the at least one incident at the one or more health care organization.