A collaborative filtering approach to assess individual condition risk based on patients' social network data

Xiang Ji, Soon Ae Chun, James Geller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Healthcare research has shown that conditions are correlated with each other, for example, in patients with type-2 diabetes, chronic nephatony often results from diabetic nephropathy. This correlation is called comorbidity relationship. The comorbidity relationships are often so complex that it is difficult to comprehend them. A disease prediction model extending the collaborative filtering used in recommender systems was developed to use publicly available patients' social network data to predict such comorbidity relationships, and to help doctors as well as uninformed patients to assess potential health risks.

Original languageEnglish (US)
Title of host publicationACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics
PublisherAssociation for Computing Machinery
Pages639-640
Number of pages2
ISBN (Electronic)9781450328944
DOIs
StatePublished - Sep 20 2014
Event5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB 2014 - Newport Beach, United States
Duration: Sep 20 2014Sep 23 2014

Publication series

NameACM BCB 2014 - 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

Other

Other5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM BCB 2014
Country/TerritoryUnited States
CityNewport Beach
Period9/20/149/23/14

All Science Journal Classification (ASJC) codes

  • Health Informatics
  • Computer Science Applications
  • Software
  • Biomedical Engineering

Keywords

  • EHR
  • Recommender system
  • Social computing

Fingerprint

Dive into the research topics of 'A collaborative filtering approach to assess individual condition risk based on patients' social network data'. Together they form a unique fingerprint.

Cite this