Display options
Cite
Wang F, Liu C, Wang Y, et al. A Graph Based Methodology for Temporal Signature Identification from HER. AMIA Annu Symp Proc. 2015;2015:1269-78
Wang, F., Liu, C., Wang, Y., Hu, J., & Yu, G. (2015). A Graph Based Methodology for Temporal Signature Identification from HER. AMIA ... Annual Symposium proceedings. AMIA Symposium, 20151269-78.
Wang, Fei, et al. "A Graph Based Methodology for Temporal Signature Identification from HER." AMIA ... Annual Symposium proceedings. AMIA Symposium vol. 2015 (2015): 1269-78.
Wang F, Liu C, Wang Y, Hu J, Yu G. A Graph Based Methodology for Temporal Signature Identification from HER. AMIA Annu Symp Proc. 2015 Nov 05;2015:1269-78. eCollection 2015. PMID: 26958267; PMCID: PMC4765704.
Copy Download .nbib Format: NLM
Share it on

AMIA Annu Symp Proc. 2015 Nov 05;2015:1269-78. eCollection 2015.

A Graph Based Methodology for Temporal Signature Identification from HER.

AMIA ... Annual Symposium proceedings. AMIA Symposium

Fei Wang, Chuanren Liu, Yajuan Wang, Jianying Hu, Guoqiang Yu

Affiliations

  1. Department of Computer Science and Engineering, University of Connecticut.
  2. Decision Sciences & MIS Department, Drexel University.
  3. Healthcare Analytics Research Group. IBM T. J. Watson Research Center.
  4. Department of Electrical and Computer Engineering, Virginia Tech, Email: [email protected] , [email protected] , [email protected] , [email protected] , [email protected].

PMID: 26958267 PMCID: PMC4765704

Abstract

Data driven technology is believed to be a promising technique for transforming the current status of healthcare. Electronic Health Records (EHR) is one of the main carriers for conducting the data driven healthcare research, where the goal is to derive insights from healthcare data and utilize such insights to improve the quality of care delivery. Due to the progression nature of human disease, one important aspect for analyzing healthcare data is temporality, which suggests the temporal relationships among different healthcare events and how their values evolve over time. Sequential pattern mining is a popular tool to extract time-invariant patterns from discrete sequences and has been applied in analyzing EHR before. However, due to the complexity of EHR, those approaches usually suffers from the pattern explosion problem, which means that a huge number of patterns will be detected with improper setting of the support threshold. To address this challenge, in this paper, we develop a novel representation, namely the temporal graph, for event sequences like EHR, wherein the nodes are medical events and the edges indicate the temporal relationships among those events in patient EHRs. Based on the temporal graph representation, we further develop an approach for temporal signature identification to identify the most significant and interpretable graph bases as temporal signatures, and the expressing coefficients can be treated as the embeddings of the patients in such temporal signature space. Our temporal signature identification framework is also flexible to incorporate semi-supervised/supervised information. We validate our framework on two real-world tasks. One is predicting the onset risk of heart failure. The other is predicting the risk of heart failure related hospitalization for patients with COPD pre-condition. Our results show that the prediction performance in both tasks can be improved by the proposed approaches.

References

  1. Lancet. 1989 Jun 10;1(8650):1309-12 - PubMed
  2. JAMA. 1996 May 22-29;275(20):1557-62 - PubMed
  3. Artif Intell Med. 1996 Jul;8(3):267-98 - PubMed
  4. Artif Intell Med. 2007 Jan;39(1):1-24 - PubMed
  5. Cardiovasc Res. 2007 Jan 15;73(2):298-309 - PubMed
  6. AMIA Annu Symp Proc. 2009;2009:452-6 - PubMed
  7. Nat Rev Genet. 2012 Jun;13(6):395-405 - PubMed
  8. J Am Med Inform Assoc. 2013 Jan 1;20(1):117-21 - PubMed
  9. IEEE Trans Pattern Anal Mach Intell. 2013 Feb;35(2):272-85 - PubMed
  10. PLoS One. 2013;8(6):e66341 - PubMed
  11. J Biomed Inform. 2014 Apr;48:148-59 - PubMed
  12. J Biomed Inform. 2014 Dec;52:199-211 - PubMed

Publication Types