Machine learning (ML)-based systems and methods for predicting disease

Abstract

Machine Learning (ML)-based systems and methods are described for predicting cardiovascular disease of users of specific geographic regions. In various aspects, user- specific cardiovascular data of a user may be input into an ML model trained with data of a plurality of cardiovascular risk factors specific to a population of given geographic region. The plurality of cardiovascular risk factors is subdivided into a first training data subset (preselected factors) and a second training data subset (remaining factors). The user-specific cardiovascular data of the user as input into the ML model is data of the user corresponding to the preselected subset of cardiovascular risk factors and the remaining subset of cardiovascular risk factors. The ML model outputs a user-specific cardiovascular prediction of the user. The user-specific cardiovascular prediction comprises a cardiovascular risk score of the user. The cardiovascular prediction is displayed on a graphical user interface (GUI).

Description

This paper describes a machine learning (ML)-based system and method for predicting cardiovascular disease in users within a specific geographic region. In several aspects, user-specific cardiovascular data can be input into an ML model trained using data on multiple cardiovascular risk factors for a given geographic population. These multiple cardiovascular risk factors are divided into a first subset of training data (pre-selected factors) and a second subset of training data (remaining factors). The user-specific cardiovascular data input into the ML model corresponds to the user data in the pre-selected and remaining subsets of cardiovascular risk factors. The ML model outputs a user-specific cardiovascular prediction result for that user. This prediction result includes the user's cardiovascular risk score. The cardiovascular prediction result is displayed on a graphical user interface (GUI). Abstract

Claims

PATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC CLAIMS What is claimed is:

1. A machine learning (ML)-based system for predicting cardiovascular disease, the ML-based system comprising: an ML model stored on a computer memory, the ML model trained with data of a plurality of cardiovascular risk factors, the plurality of cardiovascular risk factors subdivided into a first training data subset and a second training data subset prior to training the ML model, wherein the first training data subset comprises a preselected subset of cardiovascular risk factors, and wherein the second training data subset comprises a remaining subset of cardiovascular risk factors; a set of computing instructions stored on the computer memory and configured to access the ML model; a processor communicatively coupled to the computer memory, and the processor configured to access the set of computing instructions and the ML model, wherein the computing instructions, when executed by the processor, cause the processor to: input user-specific cardiovascular data of a user into the ML model, wherein the user is a member of a geographic region, wherein the user-specific cardiovascular data of the user as input into the ML model is data of the user corresponding to the preselected subset of cardiovascular risk factors and the remaining subset of cardiovascular risk factors, and wherein the ML model outputs a user-specific cardiovascular prediction of the user, the user-specific cardiovascular prediction comprising a cardiovascular risk score of the user; displaying, by a graphical user interface (GUI), the user-specific cardiovascular prediction.

2. The ML-based system of claim 1, wherein the ML model is a Cox proportional hazards model.

3. The ML-based system of claim 2, wherein the computing instructions are further configured, when executed by the processor, to implement or apply a gradient boostingPATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC algorithm to the second training data subset of the remaining subset of cardiovascular risk factors to enhance the Cox proportional hazards model.

4. The ML-based system of claim of any one of claims 1-3, wherein each of the plurality of cardiovascular risk factors is specific to a population of the geographic region.

5. The ML-based system of claim 4, wherein the geographic region defining the plurality of cardiovascular risk factors on which the ML model is trained comprises a plurality subregions or cohorts comprising individuals located within each respective subregion or cohort.

6. The ML-based system of any one of claims 1-5, wherein the preselected subset of cardiovascular risk factors comprises risk factors selected from one or more risk categories defining indications of cardiovascular health.

7. The ML-based system of claim 6, wherein the one or more risk categories comprise demographic factors, family history of disease, healthcare utilization, clinical laboratory testing, medication history, disease history, and drug use.

8. The ML-based system of any one of claims 1-6, wherein the preselected subset of cardiovascular risk factors have a linear relationship with the ML model, and wherein the remaining subset of cardiovascular risk factors have a non-linear relationship with the ML model.

9. The ML-based system of claim 8, wherein the preselected subset of cardiovascular risk factors comprises one or more of values related to: age, sex, family history of diabetes, accident and emergency visits per year, aspartate transaminase, alanine aminotransferase, low-density lipoprotein cholesterol, neutrophil, statins, myocardial infarction, angina, revascularization, atrial fibrillation, hypertension, and / or user history of diabetes.

10. The ML-based system of any one of claims 1-9, wherein at least a portion of the preselected subset of cardiovascular risk factors comprises imputed data generated to replace missing values, and wherein the remaining subset of cardiovascular risk factors are not imputed.PATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC 11. The ML-based system of claim 4, wherein the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region.

12. The ML-based system of any one of claims 1-11, wherein a C-statistic for the ML model has a value of at least 0.

69.

13. The ML-based system of any one of claims 1-12, wherein the user-specific cardiovascular prediction is a cardiovascular disease (CVD) risk prediction for the user in a 10- year timeframe.

14. The ML-based system of any one of claims 1-13, wherein the ML model is further trained with data of one or more drug classes identified for reducing cardiovascular disease (CVD), and wherein the user-specific cardiovascular data of the user as input into the ML model further comprises a selection of one or more of the drug classes, and wherein the user- specific cardiovascular prediction of the user comprises a CVD risk prediction that predicts the user’ s cardiovascular after using the one or more of the drug classes as selected.

15. The ML-based system of any one of claims 1-14, wherein the GUI is configured to receive the user-specific cardiovascular data of the user, and wherein the GUI is further configured to provide the user-specific cardiovascular data as input to the ML model.

16. The ML-based system of claim 15, wherein the GUI provides graphical fields or selections for selecting one or more types of drug classes for selection or generation of a user- specific plan to address the user’ s cardiovascular health.

17. The ML-based system of any one of claims 1-16, wherein the user-specific cardiovascular prediction comprises a user-specific medical prescription predicted to reduce the user’ s cardiovascular disease (CVD) risk.PATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC 18. The ML-based system of any one of claims 1-17, wherein the user-specific cardiovascular prediction causes generation of a user-specific activity predicted to reduce the user’ s cardiovascular disease (CVD) risk.

19. A machine learning (ML)-based method for predicting cardiovascular disease, the ML-based method comprising: training, by one or more processors, an ML model with data of a plurality of cardiovascular risk factors, the plurality of cardiovascular risk factors subdivided into a first training data subset and a second training data subset prior to training the ML model, wherein the first training data subset comprises a preselected subset of cardiovascular risk factors, and wherein the second training subset comprises a remaining subset of cardiovascular risk factors; inputting, by the one or more processors, user-specific cardiovascular data of a user into the ML model, wherein the user is a member of a geographic region, and wherein the user- specific cardiovascular data of the user as input into the ML model is data of the user corresponding to the preselected subset of cardiovascular risk factors and the remaining subset of cardiovascular risk factors; outputting, by the one or more processors accessing the ML model, a user-specific cardiovascular prediction of the user, the user-specific cardiovascular prediction comprising a cardiovascular risk score of the user; and displaying, by the one or more processors, the user-specific cardiovascular prediction on a graphical user interface (GUI).

20. The ML-based method of claim 19, wherein the ML model is a Cox proportional hazards model.

21. The ML-based method of claim 20, further comprising implementing or applying a gradient boosting algorithm to the second training data subset of the remaining subset of cardiovascular risk factors to enhance the Cox proportional hazards model.

22. The ML-based method of any one of claims 19-21, wherein each of the plurality of cardiovascular risk factors is specific to a population of a geographic regionPATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC 23. The ML-based method of any one of claims 19-22, wherein the geographic region defining the plurality of cardiovascular risk factors on which the ML model is trained comprises a plurality subregions or cohorts comprising individuals located within each respective subregion or cohort.

24. The ML-based method of any one of claims 19-23, wherein the preselected subset of cardiovascular risk factors comprises risk factors selected from one or more risk categories defining indications of cardiovascular health.

25. The ML-based method of claim 24, wherein the one or more risk categories comprise demographic factors, family history of disease, healthcare utilization, clinical laboratory testing, medication history, disease history, and drug use.

26. The ML-based method of any one of claims 19-25, wherein the preselected subset of cardiovascular risk factors have a linear relationship with the ML model, and wherein the remaining subset of cardiovascular risk factors have a non-linear relationship with the ML model.

27. The ML-based method of claim 26, wherein the preselected subset of cardiovascular risk factors comprises one or more of values related to: age, sex, family history of diabetes, accident and emergency visits per year, aspartate transaminase, alanine aminotransferase, low-density lipoprotein cholesterol, neutrophil, statins, myocardial infarction, angina, revascularization, atrial fibrillation, hypertension, and / or user history of diabetes.

28. The ML-based method of any one of claims 19-27, wherein at least a portion of the preselected subset of cardiovascular risk factors comprises imputed data generated to replace missing values, and wherein the remaining subset of cardiovascular risk factors are not imputed.

29. The ML-based method of any one of claims 19-28, wherein the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region.PATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC 30. The ML-based method of any one of claims 19-29, wherein a C-statistic for the ML model has a value of at least 0.

69.

31. The ML-based method of any one of claims 19-30, wherein the user-specific cardiovascular prediction is a cardiovascular disease (CVD) risk prediction for the user in a 10- year timeframe.

32. The ML-based method of any one of claims 19-31, wherein the ML model is further trained with data of one or more drug classes identified for reducing cardiovascular disease (CVD), and wherein the user-specific cardiovascular data of the user as input into the ML model further comprises a selection of one or more of the drug classes, and wherein the user- specific cardiovascular prediction of the user comprises a CVD risk prediction that predicts the user’ s cardiovascular after using the one or more of the drug classes as selected.

33. The ML-based method of any one of claims 19-32, wherein the GUI is configured to receive the user-specific cardiovascular data of the user, and wherein the GUI is further configured to provide the user-specific cardiovascular data as input to the ML model.

34. The ML-based method of claim 33, wherein the GUI provides graphical fields or selections for selecting one or more types of drug classes for selection or generation of a user- specific plan to address the user’ s cardiovascular health.

35. The ML-based method of any one of claims 19-34, wherein the user-specific cardiovascular prediction comprises a user-specific medical prescription predicted to reduce the user’ s cardiovascular disease (CVD) risk.

36. The ML-based method of any one of claims 19-35, wherein the user-specific cardiovascular prediction causes generation of a user-specific activity predicted to reduce the user’ s cardiovascular disease (CVD) risk.PATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC 37. A tangible, non-transitory computer-readable medium storing computing instructions for predicting cardiovascular disease, that when executed by one or more processors cause the one or more processors to: train an ML model with data of a plurality of cardiovascular risk factors, the plurality of cardiovascular risk factors subdivided into a first training data subset and a second training data subset prior to training the ML model, wherein the first training data subset comprises a preselected subset of cardiovascular risk factors, and wherein the second training subset comprises a remaining subset of cardiovascular risk factors, input user-specific cardiovascular data of a user into an ML model stored on a computer memory, wherein the user is a member of a geographic region, and wherein the user-specific cardiovascular data of the user as input into the ML model is data of the user corresponding to the preselected subset of cardiovascular risk factors and the remaining subset of cardiovascular risk factors, output, by the ML model, a user-specific cardiovascular prediction of the user, the user- specific cardiovascular prediction comprising a cardiovascular risk score of the user; and display, by a graphical user interface (GUI), the user-specific cardiovascular prediction.

38. The tangible, non-transitory computer-readable medium of claim 37, wherein the ML model is a Cox proportional hazards model.

39. The tangible, non-transitory computer-readable medium of claim 38, wherein the computing instructions are further configured, when executed by the processor, to implement or apply a gradient boosting algorithm to the second training data subset of the remaining subset of cardiovascular risk factors to enhance the Cox proportional hazards model.

40. The tangible, non-transitory computer-readable medium of any one of claims 37- 39, wherein each of the plurality of cardiovascular risk factors is specific to a population of a geographic region.

41. The tangible, non-transitory computer-readable medium of any one of claims 37- 40, wherein the geographic region defining the plurality of cardiovascular risk factors on whichPATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC the ML model is trained comprises a plurality subregions or cohorts comprising individuals located within each respective subregion or cohort.

42. The tangible, non-transitory computer-readable medium of any one of claims 37- 41, wherein the preselected subset of cardiovascular risk factors comprises risk factors selected from one or more risk categories defining indications of cardiovascular health.

43. The tangible, non-transitory computer-readable medium of claim 42, wherein the one or more risk categories comprise demographic factors, family history of disease, healthcare utilization, clinical laboratory testing, medication history, disease history, and drug use.

44. The tangible, non-transitory computer-readable medium of any one of claims 37- 43, wherein the preselected subset of cardiovascular risk factors have a linear relationship with the ML model, and wherein the remaining subset of cardiovascular risk factors have a non-linear relationship with the ML model.

45. The tangible, non-transitory computer-readable medium of claim 44, wherein the preselected subset of cardiovascular risk factors comprises one or more of values related to: age, sex, family history of diabetes, accident and emergency visits per year, aspartate transaminase, alanine aminotransferase, low-density lipoprotein cholesterol, neutrophil, statins, myocardial infarction, angina, revascularization, atrial fibrillation, hypertension, and / or user history of diabetes.

46. The tangible, non-transitory computer-readable medium of any one of claims 37- 45, wherein at least a portion of the preselected subset of cardiovascular risk factors comprises imputed data generated to replace missing values, and wherein the remaining subset of cardiovascular risk factors are not imputed.

47. The tangible, non-transitory computer-readable medium of any one of claims 37- 46, wherein the ML model is further trained with data defining one or more threshold risks, where each threshold risk defines a magnitude of a clinical health benefit to a user of the geographic region.PATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC 48. The tangible, non-transitory computer-readable medium of any one of claims 37- 47, wherein a C-statistic for the ML model has a value of at least 0.

69.

49. The tangible, non-transitory computer-readable medium of any one of claims 37- 48, wherein the user-specific cardiovascular prediction is a cardiovascular disease (CVD) risk prediction for the user in a 10-year timeframe.

50. The tangible, non-transitory computer-readable medium of any one of claims 37- 49, wherein the ML model is further trained with data of one or more drug classes identified for reducing cardiovascular disease (CVD), and wherein the user-specific cardiovascular data of the user as input into the ML model further comprises a selection of one or more of the drug classes, and wherein the user-specific cardiovascular prediction of the user comprises a CVD risk prediction that predicts the user’ s cardiovascular after using the one or more of the drug classes as selected.

51. The tangible, non-transitory computer-readable medium of any one of claims 37- 50, wherein the GUI is configured to receive the user-specific cardiovascular data of the user, and wherein the GUI is further configured to provide the user-specific cardiovascular data as input to the ML model.

52. The tangible, non-transitory computer-readable medium of claim 51, wherein the GUI provides graphical fields or selections for selecting one or more types of drug classes for selection or generation of a user-specific plan to address the user’ s cardiovascular health.

53. The tangible, non-transitory computer-readable medium of any one of claims 37- 52, wherein the user-specific cardiovascular prediction comprises a user-specific medical prescription predicted to reduce the user’ s cardiovascular disease (CVD) risk.

54. The tangible, non-transitory computer-readable medium of any one of claims 37- 53, wherein the user-specific cardiovascular prediction causes generation of a user-specific activity predicted to reduce the user’ s cardiovascular disease (CVD) risk.PATENT APPLICATION Attorney Docket No.: 32263 / 59457 PC 55. A machine learning (ML)-based method for predicting disease, the ML-based method comprising: training, by one or more processors, an ML model with data of a plurality of disease risk factors specific to a population of a given geographic region, the plurality of disease risk factors subdivided into a first training data subset and a second training data subset prior to training the ML model, wherein the first training data subset comprises a preselected subset of disease risk factors, and wherein the second training subset comprises a remaining subset of disease risk factors, inputting, by the one or more processors, user-specific health data of a user into the ML model, wherein the user is a member of the geographic region, and wherein the user-specific health data of the user as input into the ML model is data of the user corresponding to the preselected subset of disease risk factors and the remaining subset of disease risk factors, outputting, by the one or more processors accessing the ML model, a user-specific disease prediction of the user, the user-specific disease prediction comprising a disease risk score of the user; and displaying, by the one or more processors, the user-specific disease prediction on a graphical user interface (GUI).

Images