Statistical Relational Learning to Predict Primary Myocardial Infarction from Electronic Health Records.
Publication
, Conference
Weiss, JC; Page, D; Peissig, PL; Natarajan, S; McCarty, C
Published in: Proc Innov Appl Artif Intell Conf
2012
Electronic health records (EHRs) are an emerging relational domain with large potential to improve clinical outcomes. We apply two statistical relational learning (SRL) algorithms to the task of predicting primary myocardial infarction. We show that one SRL algorithm, relational functional gradient boosting, outperforms propositional learners particularly in the medically-relevant high recall region. We observe that both SRL algorithms predict outcomes better than their propositional analogs and suggest how our methods can augment current epidemiological practices.
Duke Scholars
Published In
Proc Innov Appl Artif Intell Conf
ISSN
2154-8080
Publication Date
2012
Volume
2012
Start / End Page
2341 / 2347
Location
United States
Citation
APA
Chicago
ICMJE
MLA
NLM
Weiss, J. C., Page, D., Peissig, P. L., Natarajan, S., & McCarty, C. (2012). Statistical Relational Learning to Predict Primary Myocardial Infarction from Electronic Health Records. In Proc Innov Appl Artif Intell Conf (Vol. 2012, pp. 2341–2347). United States.
Weiss, Jeremy C., David Page, Peggy L. Peissig, Sriraam Natarajan, and Catherine McCarty. “Statistical Relational Learning to Predict Primary Myocardial Infarction from Electronic Health Records.” In Proc Innov Appl Artif Intell Conf, 2012:2341–47, 2012.
Weiss JC, Page D, Peissig PL, Natarajan S, McCarty C. Statistical Relational Learning to Predict Primary Myocardial Infarction from Electronic Health Records. In: Proc Innov Appl Artif Intell Conf. 2012. p. 2341–7.
Weiss, Jeremy C., et al. “Statistical Relational Learning to Predict Primary Myocardial Infarction from Electronic Health Records.” Proc Innov Appl Artif Intell Conf, vol. 2012, 2012, pp. 2341–47.
Weiss JC, Page D, Peissig PL, Natarajan S, McCarty C. Statistical Relational Learning to Predict Primary Myocardial Infarction from Electronic Health Records. Proc Innov Appl Artif Intell Conf. 2012. p. 2341–2347.
Published In
Proc Innov Appl Artif Intell Conf
ISSN
2154-8080
Publication Date
2012
Volume
2012
Start / End Page
2341 / 2347
Location
United States