Identifying personalized time-varying predictive patterns of risk factors

Patent metadata

Field	Value
Publication number	US-11056218-B2
Application number	US-201615168437-A
Country	US
Kind code	B2
Filing date	May 31, 2016
Priority date	May 31, 2016
Publication date	Jul 6, 2021
Grant date	Jul 6, 2021

Abstract

Aspects of the present invention include a method, system and computer program product. The method includes identifying, by a processor, a set of global risk factors for a target event using training patients, and providing, by the processor, a disease progression timeline with defined time stamps by aligning longitudinal data of the training patients based on the defined time stamp of risk targets. The method also includes positioning, by the processor, a target patient at one of the defined time stamps on the disease progression timeline, and identifying, by the processor, at least one of the training patients similar to the target patient with the same one of the defined time stamps on the disease progression timeline. The method further includes calculating, by the processor, a time-varying predictive pattern of at least a portion of the global set of risk factors for the target patient along the disease progression timeline.

First claim

What is claimed is:

1. A computer-implemented method comprising:
identifying, by a processor, a set of global risk factors for a target event using training patients;
providing, by the processor, a disease progression timeline with defined time stamps by aligning longitudinal data of the training patients based on the defined time stamp of risk targets, wherein the longitudinal data of the training patients is obtained from the medical records of the training patients, and wherein the target event is a hospitalization of the target patient triggered by one disease of an interaction of different diseases;
positioning, by the processor, a target patient at one of the defined time stamps on the disease progression timeline, wherein a number of defined time stamps associated with the target event is based at least in part on an investigation of a health care provider;
identifying, by the processor, at least one of the training patients similar to the target patient with the same one of the defined time stamps on the disease progression timeline;
calculating, by the processor, a respective time-varying predictive pattern of at least a portion of the set of global risk factors for the target patient along the disease progression timeline; and
displaying, by the processor, respective rows of the time-varying predicative patterns for the target patient, wherein the rows are segmented based on time intervals from a current time interval to a future time interval, and wherein each segment describes a time-based risk score for the target patient via a visual pattern.

2. The computer-implemented method of claim 1 wherein the calculated time-varying predictive pattern of at least a portion of the set of global risk factors comprises a calculated time-varying predictive pattern of multiple risk factors within the set of global risk factors.

3. The computer-implemented method of claim 1 wherein the target event comprises an event related to certain diseases that afflicts humans.

4. The computer-implemented method of claim 1 wherein positioning, by the processor, a target patient at one of the defined time stamps on the disease progression timeline comprises assessing the risk target of the target patient after a certain time following an onset event and positioning the target to the one of the defined time stamps according to an amount of time to the onset event.

5. The computer-implemented method of claim 1 wherein positioning, by the processor, a target patient at one of the defined time stamps on the disease progression timeline comprises assessing the risk target of the target patient with no occurrence of an onset event.

6. The computer-implemented method of claim 5 wherein assessing the risk target of the target patient with no occurrence of an onset event comprises calculating similarity scores of the target patient to the training patients at a number of different time stamps, wherein one of the different time stamps is selected to position the target patient on the disease progression timeline.

7. The computer-implemented method of claim 6 wherein the similarity scores are calculated by a distance or similarity method.

8. A system comprising:
a processor in communication with one or more types of memory, the processor configured to:
identify a set of global risk factors for a target event using training patients;
provide a disease progression timeline with defined time stamps by aligning longitudinal data of the training patients based on the defined time stamp of risk targets, wherein the longitudinal data of the training patients is obtained from the medical records of the training patients, and wherein the target event is a hospitalization of the target patient triggered by one disease of an interaction of different diseases;
position a target patient at one of the defined time stamps on the disease progression timeline, wherein a number of defined time stamps associated with the target event is based at least in part on an investigation of a health care provider;
identify at least one of the training patients similar to the target patient with the same one of the defined time stamps on the disease progression timeline; and
calculate a respective time-varying predictive pattern of at least a portion of the set of global risk factors for the target patient along the disease progression timeline; and
displaying respective rows of the time-varying predicative patterns for the target patient, wherein the rows are segmented based on time intervals from a current time interval to a future time interval, and wherein each segment describes a time-based risk score for the target patient via a visual pattern.

9. The system of claim 8 wherein the processor configured to calculate a time-varying predictive pattern of at least a portion of the set of global risk factors comprises the processor configured to calculate a time-varying predictive pattern of multiple risk factors within the set of global risk factors.

10. The system of claim 8 wherein the target event comprises an event related to certain diseases that afflicts humans.

11. The system of claim 8 wherein the processor being configured to position a target patient at one of the defined time stamps on the disease progression timeline comprises the processor being configured to assess the risk target of the target patient after a certain time following an onset event and position the target to the one of the defined time stamps according to an amount of time to the onset event.

12. The system of claim 8 wherein the processor being configured to position a target patient at one of the defined time stamps on the disease progression timeline comprises the processor being configured to assess the risk target of the target patient with no occurrence of an onset event.

13. The system of claim 12 wherein the processor being configured to assess the risk target of the target patient with no occurrence of an onset event comprises the processor being configured to calculate similarity scores of the target patient to the training patients at a number of different time stamps and to select one of the different time stamps to position the target patient on the disease progression timeline.

14. The system of claim 13 wherein the similarity scores are calculated by a distance or similarity method.

15. A computer program product comprising:
a non-transitory storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising:
identifying, by a processor, a set of global risk factors for a target event using training patients;
providing, by the processor, a disease progression timeline with defined time stamps by aligning longitudinal data of the training patients based on the defined time stamp of risk targets, wherein the longitudinal data of the training patients is obtained from the medical records of the training patients, and wherein the target event is a hospitalization of the target patient triggered by one disease of an interaction of different diseases;
positioning, by the processor, a target patient at one of the defined time stamps on the disease progression timeline, wherein a number of defined time stamps associated with the target event is based at least in part on an investigation of a health care provider;
identifying, by the processor, at least one of the training patients similar to the target patient with the same one of the defined time stamps on the disease progression timeline; and
calculating, by the processor, a time-varying predictive pattern of at least a portion of the

Assignees

• IBM

Inventors

• Hu Jianying
• Ng Kenney
• Perer Adam
• Wang Fei
• Wang Yajuan

Classifications

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H10/60 Primary

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