Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Identifying group and individual-level risk factors via risk-driven patient stratification

a risk factor and patient technology, applied in the field of risk factor identification, can solve the problems of only yielding common risk factors by based on general population data, and not addressing individual differences of patients

Inactive Publication Date: 2014-04-03
IBM CORP
View PDF3 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The patent describes a method and system for identifying common factors that contribute to risks associated with different targets. These common factors are used to create risk levels that can help predict an individual's likelihood of developing a specific risk. By analyzing data from multiple individuals, the system is able to identify specific factors that indicate an increased risk for a particular target. This information can be used to develop personalized risk assessments for individuals, which can help with risk reduction and treatment strategies. The technical effects of this patent include improved individual risk factor identification and improved accuracy of risk assessments.

Problems solved by technology

However, methods based on general population data will only yield common risk factors and do not address individual differences of patients.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Identifying group and individual-level risk factors via risk-driven patient stratification
  • Identifying group and individual-level risk factors via risk-driven patient stratification
  • Identifying group and individual-level risk factors via risk-driven patient stratification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017]In accordance with the present principles, systems and methods for identifying individual-level risk factors are provided. Individual data and population data may be received as input. Individual data may include data for a target group or cluster. In a preferred embodiment, the target cluster is representative of a target individual or patient, e.g., to be treated or examined. Individual data may include, e.g., electronic health records, questionnaire data, genetic information, etc.

[0018]Using population data, common (i.e., global) risk factors for one or more specific risk targets (e.g., diabetes) are identified. Preferably, each risk factor is identified as being positively or negatively correlated with the risk target. Using the identified risk factors, patients from the population data are stratified into clusters. Stratifying patients into clusters may include applying, e.g., hierarchical clustering, k-means clustering, 2-step clustering, etc. Other methods of clustering...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Systems and methods for individual risk factor identification include identifying common risk factors for one or more risk targets from population data. Individuals are stratified into clusters based upon the common risk factors. A discriminability of each of the common risk factors is determined, using a processor, for a target cluster using individual data of the target cluster to provide re-ranked common risk factors as individual risk factors for the target cluster, such that the discriminability is a measure of how a risk factor discriminates its cluster from other clusters.

Description

RELATED APPLICATION INFORMATION[0001]This application is a Continuation application of co-pending U.S. patent application Ser. No. 13 / 632,659 filed Oct. 1, 2012, incorporated herein by reference in its entirety.BACKGROUND[0002]1. Technical Field[0003]The present invention relates to risk factor identification, and more particularly to identifying group-level and individual-level risk factors via risk-driven patient stratification.[0004]2. Description of the Related Art[0005]As more clinical information with increasing diversity becomes available for analysis, a large number of features can be constructed and leveraged for predictive modeling. The ability to identify risk factors related to an adverse health condition (e.g., congestive heart failure) is very important for improving healthcare quality and reducing cost. The identification of risk factors may allow for the early detection of the onset of diseases so that aggressive intervention may be taken to slow or prevent costly an...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q50/22
CPCG06Q10/0635G06Q10/0637G16H50/30G16H50/70
Inventor GOTZ, DAVID H.HSUEH, PEI-YUN S.HU, JIANYINGSUN, JIMENG
Owner IBM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com