Active patient risk prediction

Patent metadata

Field	Value
Publication number	US-10123748-B2
Application number	US-201414527824-A
Country	US
Kind code	B2
Filing date	Oct 30, 2014
Priority date	Oct 30, 2014
Publication date	Nov 13, 2018
Grant date	Nov 13, 2018

Abstract

Electronic health records of a plurality of patients are received. A risk prediction model for a disease based on the electronic health records of the plurality of patients is created. An electronic health record of an original patient is received. A neighboring group of patients of the plurality of patients is identified, wherein the neighboring group of patients is two or more patients similar to the original patient. An ordering of the two or more patients of the neighboring group of patients is received, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient. The risk prediction model is updated based on the ordering of the two or more patients of the neighboring group of patients.

First claim

What is claimed is:

1. A method for updating a patient risk prediction model, the method comprising:
receiving electronic health records of a plurality of patients;
creating, by one or more computer processors, a risk prediction model for a disease based on the electronic health records of the plurality of patients;
receiving, by one or more computer processors, an electronic health record of an original patient;
identifying, by one or more computer processors, a neighboring group of patients of the plurality of patients, wherein the neighboring group of patients is two or more patients similar to the original patient;
generating, by one or more computer processors, a question as to a relative ordering of the two or more patients of the neighboring group of patients with respect to the original patient;
receiving an answer to the question as to the relative ordering of the two or more patients of the neighboring group of patients, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient; and
updating, by one or more computer processors, the risk prediction model based on the answer to the question as to the relative ordering of the two or more patients of the neighboring group of patients.

2. The method of claim 1 , further comprising:
estimating, by one or more computer processors, the risk that the original patient will suffer from the disease based upon the updated risk prediction model.

3. The method of claim 1 , wherein the ordering of the patients of the neighboring group of patients is a complete ordering including all patients of the neighboring group of patients or a partial ordering including at least one of the patients of the neighboring group of patients.

4. The method of claim 1 , wherein the risk prediction model for a disease based on the plurality of patients is selected from a group consisting of: constrained least square problem, a linear system of equations, or a quadratic program.

5. The method of claim 1 , wherein the risk prediction model is updated until a patient similarity converges in a constrained similarity process.

6. The method of claim 1 , wherein the risk prediction model is updated more than one time.

7. The method of claim 1 , wherein the electronic health record includes one or more of the following: demographics; medical history; medication and allergies; immunization status; laboratory test results; radiology images; vital signs; and personal statistics.

8. A computer program product for updating a patient risk prediction model, the computer program product comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to receive electronic health records of a plurality of patients;
program instructions to create a risk prediction model for a disease based on the electronic health records of the plurality of patients;
program instructions to receive an electronic health record of an original patient;
program instructions to identify a neighboring group of patients of the plurality of patients, wherein the neighboring group of patients is two or more patients similar to the original patient;
program instructions to generate a question as to a relative ordering of the two or more patients of the neighboring group of patients with respect to the original patient;
program instructions to receive an answer to the question as to the relative ordering of the two or more patients of the neighboring group of patients, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient; and
program instructions to update the risk prediction model based on the answer to the question as to the relative ordering of the two or more patients of the neighboring group of patients.

9. The computer program product of claim 8 , further comprising program instructions, stored on the one or more computer readable storage media, to:
estimate the risk that the original patient will suffer from the disease based upon the updated risk prediction model.

10. The computer program product of claim 8 , wherein the ordering of the patients of the neighboring group of patients is a complete ordering including all patients of the neighboring group of patients or a partial ordering including at least one of the patients of the neighboring group of patients.

11. The computer program product of claim 8 , wherein the risk prediction model for a disease based on the plurality of patients is selected from a group consisting of: constrained least square problem, a linear system of equations, or a quadratic program.

12. The computer program product of claim 8 , wherein the risk prediction is updated until a patient similarity converges in a constrained similarity process.

13. The computer program product of claim 8 , wherein the risk prediction model is updated more than one time.

14. The computer program product of claim 8 , wherein the electronic health record includes one or more of the following: demographics; medical history; medication and allergies;
immunization status; laboratory test results; radiology images; vital signs; and personal statistics.

15. A computer system for updating a patient risk prediction model, the computer system comprising:
one or more computer processors;
one or more computer readable storage media; and
program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
program instructions to receive electronic health records of a plurality of patients;
program instructions to create a risk prediction model for a disease based on the electronic health records of the plurality of patients;
program instructions to receive an electronic health record of an original patient;
program instructions to identify a neighboring group of patients of the plurality of patients, wherein the neighboring group of patients is two or more patients similar to the original patient;
program instructions to generate a question as to a relative ordering of the two or more patients of the neighboring group of patients with respect to the original patient;
program instructions to receive an answer to the question as to the relative ordering of the two or more patients of the neighboring group of patients, wherein the ordering of the two or more patients of the neighboring group of patients is based upon how similar each patient of the two or more patients is to the original patient; and
program instructions to update the risk prediction model based on the answer to the question as to the relative ordering of the two or more patients of the neighboring group of patients.

16. A computer system of claim 15 , further comprising program instructions, stored on the one or more computer readable storage media for execution by the at least one of the one or more computer processors, to:
estimate the risk that the original patient will suffer from the disease based upon the updated risk prediction model.

17. A computer system of claim 15 , wherein the ordering of the patients of the neighboring group of patients is a complete ordering including all patients of the neighboring group of patients or a partial ordering including at least one of the patients of the neighboring group of patients.

Assignees

• IBM

Inventors

• Li Hongfei
• Qian Buyue
• Wang Fei
• Wang Xiang

Classifications

• G16H50/30

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

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• A61B5/055

  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging · CPC title

• A61B5/7275 Primary

  Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor · CPC title

• G06F19/00

  Physics · mapped topic