System and method for providing a patient-specific prediction model in a user application for effectiveness determinations

Patent metadata

Field	Value
Publication number	US-2020074573-A1
Application number	US-201916566129-A
Country	US
Kind code	A1
Filing date	Sep 10, 2019
Priority date	Nov 6, 2012
Publication date	Mar 5, 2020
Grant date	—

Abstract

In some embodiments, a patient dataset including digital medical images and other patient data may be obtained. The other patient data may include specific patient health data associated with a patient and historical patient data derived from a population related to the patient. The historical patient data may indicate medical inventions provided to patients of the related population, health effects of the medical interventions, and costs of the medical interventions. In some embodiments, a neural network specific to the patient may be configured for a user application using at least part of the patient dataset. As an example, the user application may include neural network. Based on the specific patient health data, health effects and intervention costs related to individual interventions for the patient may be predict via the neural network of the user application. The net health benefits for the individual interventions may be provided via the user interface based on the predicted health effects and intervention costs.

First claim

What is claimed is:

1 . A computer system for providing a patient-specific neural network in a user application, the system comprising:
one or more processors programmed with computer program instructions that, when executed, cause the system to:
collect a patient dataset comprising digital medical images and other patient data, the other patient data comprising (i) specific patient health data associated with a patient and (ii) historical patient data derived from a population related to the patient, the historical patient data indicating medical inventions provided to patients of the related population, health effects of the medical interventions, and costs of the medical interventions;
configure a neural network specific to the patient for a user application using at least part of the patient dataset, the neural network being included in the user application;
predict, via the neural network of the user application, health effects and intervention costs related to individual interventions for the patient based on the specific patient health data; and
provide, via the user application, net health benefits for the individual interventions based on the predicted health effects and intervention costs.

2 . The system of claim 1 , wherein the system is caused to:
provide the neural network in the user application; and regularly provide parameters obtained from a risk model engine as input to the neural network via the user application to cause updating of the neural network of the user application, the risk model engine being external to the user application.

3 . The system of claim 2 , wherein the risk model engine generates the parameters by regularly querying a historical patient database and processing historical patient data associated with a plurality of patients obtained via the regular querying.

4 . The system of claim 1 , wherein providing the net health benefits comprises:
using the predicted health effects and intervention costs to determine the net health benefits for the individual interventions; and generating and providing, at a user interface of the user application, a comparison of the net health benefits for the individual interventions.

5 . The system of claim 1 , wherein providing the net health benefits for the individual intervention comprises, with respect to each individual intervention of the individual interventions and each time horizon of a set of different time horizons:
determining, based on the predicted health effects and intervention costs, an accumulated cost and an accumulated health effect of the individual intervention over the time horizon for the individual intervention; providing one or more net health benefits for the individual intervention based on (i) a willingness to pay value, the accumulated cost of the individual intervention, and (iii) the accumulated health effect of the individual intervention.

6 . The system of claim 5 , wherein the system is caused to:
generating a comparison of the net health benefits for the individual interventions over the different time horizons as a function of willingness to pay; and determining, based on the comparison of the net health benefits as a function of willingness to pay, a dominating intervention that dominates the individual interventions over a range of willingness-to-pay values.

7 . The system of claim 1 , wherein the specific patient health data comprises at least one of the patient's name, age, gender, body mass index, systolic/diastolic blood pressure, relevant blood markers, and the patient's health and quality of life.

8 . A method implemented by one or more processors executing computer program instructions that, when executed, perform the method, the method comprising:
collecting a patient dataset comprising digital medical images and other patient data, the other patient data comprising (i) specific patient health data associated with a patient and (ii) historical patient data derived from a population related to the patient, the historical patient data indicating medical inventions provided to patients of the related population, health effects of the medical interventions, and costs of the medical interventions; configuring a neural network specific to the patient for a user application using at least part of the patient dataset, the neural network being included in the user application; predicting, via the neural network of the user application, health effects and intervention costs related to individual interventions for the patient based on the specific patient health data; and providing, via the user application, net health benefits for the individual interventions based on the predicted health effects and intervention costs.

9 . The method of claim 8 , further comprising:
providing the neural network in the user application; and regularly providing parameters obtained from a risk model engine as input to the neural network via the user application to cause updating of the neural network of the user application, the risk model engine being external to the user application.

10 . The method of claim 9 , wherein the risk model engine generates the parameters by regularly querying a historical patient database and processing historical patient data associated with a plurality of patients obtained via the regular querying.

11 . The method of claim 8 , wherein providing the net health benefits comprises:
using the predicted health effects and intervention costs to determine the net health benefits for the individual interventions; and generating and providing, at a user interface of the user application, a comparison of the net health benefits for the individual interventions.

12 . The method of claim 8 , wherein providing the net health benefits for the individual intervention comprises, with respect to each individual intervention of the individual interventions and each time horizon of a set of different time horizons:
determining, based on the predicted health effects and intervention costs, an accumulated cost and an accumulated health effect of the individual intervention over the time horizon for the individual intervention; providing one or more net health benefits for the individual intervention based on (i) a willingness to pay value, the accumulated cost of the individual intervention, and (iii) the accumulated health effect of the individual intervention.

13 . The method of claim 12 , further comprising:
generating a comparison of the net health benefits for the individual interventions over the different time horizons as a function of willingness to pay; and determining, based on the comparison of the net health benefits as a function of willingness to pay, a dominating intervention that dominates the individual interventions over a range of willingness-to-pay values.

14 . The method of claim 8 , wherein the specific patient health data comprises at least one of the patient's name, age, gender, body mass index, systolic/diastolic blood pressure, relevant blood markers, and the patient's health and quality of life.

15 . A non-transitory computer-readable media comprising instructions that, when executed by one or more processors, cause operations comprising:
collecting a patient dataset comprising digital medical images and other patient data, the other patient data comprising (i) specific patient health data associated with a patient and (ii) historical patient data derived from a population related to the patient, the historical patient data indicating medical inventions provided to patients of the related population, health effects of the medical int

Assignees

• Koninklijke Philips Nv

Inventors

• Op Den Buijs Jorn
• Schonenberg Maartje Helena
• Pauws Steffen Clarence

Classifications

• G06Q10/10 Primary

  Office automation; Time management · CPC title

• G06Q50/22 Primary

  Social work or social welfare, e.g. community support activities or counselling services · CPC title

• G06Q40/08

  Insurance · CPC title

• G16H40/20

  for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms · CPC title

• G16H50/30

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