US 11,238,989 B2Granted

Personalized risk prediction based on intrinsic and extrinsic factors

AssigneeInternational Business Machines Corporation

InventorsGang Hu, Xiang Li, Hai Feng Liu, Jing Mei, Eryu Xia, En Liang Xu, Shi Wan Zhao

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems, computer-implemented methods and/or computer program products that facilitate predicting personalized risks based on intrinsic factors and extrinsic factors are provided. In one example, a computer-implemented method comprises: collecting, by a system operatively coupled to a processor, intrinsic factors and extrinsic factors associated with infectious diseases; generating, by the system, a probabilistic model based on the intrinsic factors and extrinsic factors, wherein the model incorporates node characteristics into infection probability; and refining, by the system, the model through concurrently learning respective node thresholds and hidden infection network structure of the model.

Claims20

Dependent claims

A system, comprising:

a memory that stores computer executable components;
a processor, operably coupled to the memory, and that executes computer executable components stored in the memory, wherein the computer executable components comprise:
a collection component that collects intrinsic factors and extrinsic factors associated with infectious diseases and persons;
a construction component that generates a probabilistic model for determining infection probabilities of the persons based on the intrinsic factors and extrinsic factors, wherein nodes of the probabilistic model respectively represent the persons, and the probabilistic model incorporates node characteristics of the persons into determining the infection probabilities;
and
a machine learning component that:
refines the probabilistic model through concurrently learning respective node thresholds of the nodes and hidden infection network structure of the probabilistic model resulting in a trained probabilistic model, wherein the respective node thresholds represent susceptibilities of the persons to the infectious diseases, and the hidden infection network structure comprises connections between the nodes representing interactions between the persons;
and
wherein:
the collection component collects additional intrinsic factors and additional extrinsic factor associated with a specified person, and
the machine learning component:
determines, using the trained probabilistic model, an infection probability for the specified person to become infected by an infectious disease of the infection diseases after exposure to one or more persons infected with the infectious disease, and
informs the specified person of the infection probability in association with clinical decision making regarding one or more treatments.

10 more elements

A computer-implemented method, comprising:

collecting, by a system operatively coupled to a processor, intrinsic factors and extrinsic factors associated with infectious diseases and persons;
generating, by the system, a probabilistic model for determining infection probabilities of the persons based on the intrinsic factors and extrinsic factors, wherein nodes of the probabilistic model respectively represent the persons, and the probabilistic model incorporates node characteristics of the persons into determining the infection probabilities;
refining, by the system, the probabilistic model through concurrently learning respective node thresholds and hidden infection network structure of the probabilistic model resulting in a trained probabilistic model, wherein the respective node thresholds represent susceptibilities of the persons to the infectious diseases, and the hidden infection network structure comprises connections between the nodes representing interactions between the persons;
collecting, by the system, additional intrinsic factors and additional extrinsic factor associated with a specified person;
determining, by the system, using the trained probabilistic model, an infection probability for the specified person to become infected by an infectious disease of the infection diseases after exposure to one or more persons infected with the infectious disease;
and
informing, by the system, the specified person of the infection probability in association with clinical decision making regarding one or more treatments.

4 more elements

A computer program product that facilitates predicting personalized risks based on intrinsic factors and extrinsic factors, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

collect the intrinsic factors and the extrinsic factors associated with infectious diseases and persons;
generate a probabilistic model for determining infection probabilities of the persons based on the intrinsic factors and extrinsic factors, wherein nodes of the probabilistic model respectively represent the persons, and the probabilistic model incorporates node characteristics of the persons into determining the infection probabilities;
refine the probabilistic model through concurrently learning respective node thresholds and hidden infection network structure of the probabilistic model resulting in a trained probabilistic model, wherein the respective node thresholds represent susceptibilities of the persons to the infectious diseases, and the hidden infection network structure comprises connections between the nodes representing interactions between the persons;
collect additional intrinsic factors and additional extrinsic factor associated with a specified person;
determine, using the trained probabilistic model, an infection probability the specified person to become infected by an infectious disease of the infection diseases after exposure to one or more persons infected with the infectious disease;
and
inform the specified person of the infection probability in association with clinical decision making regarding one or more treatments.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/806,757Filed 8 Nov 2017
Published: US 2019/0138691 A19 May 2019
Granted: 1 Feb 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

G16H 50/30
ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or…: for…
G06N 7/01
Computing arrangements based on specific mathematical models: probabilistic graphical models, e.g. probabilistic networks
G06N 20/00
Machine learning
G16H 50/20
ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or…: for…