Machine Learning for Personalized Medicine: Predicting Primary Myocardial Infarction from Electronic Health Records

被引：50

作者：

Weiss, Jeremy C. ^{[1
]}

Natarajan, Sriraam ^{[2
]}

Peissig, Peggy L.

McCarty, Catherine A. ^{[3
]}

Page, David ^{[1
]}

机构：

[1] Univ Wisconsin, Dept Comp Sci, Madison, WI 53706 USA

[2] Wake Forest Univ, Bowman Gray Sch Med, Translat Sci Inst, Winston Salem, NC 27109 USA

[3] Essentia Inst Rural Hlth, Duluth, MN USA

来源：

AI MAGAZINE | 2012年 / 33卷 / 04期

基金：

美国国家卫生研究院;

关键词：

RISK;

D O I：

10.1609/aimag.v33i4.2438

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：33 / 45

页数：13

共 28 条

[21]

Natarajan S., 2012, WORKSH MACH LEARN CL

[22] Gradient-based boosting for statistical relational learning: The relational dependency network case [J].

Natarajan, Sriraam ;

Khot, Tushar ;

Kersting, Kristian ;

Gutmann, Bernd ;

Shavlik, Jude .

MACHINE LEARNING, 2012, 86 (01) :25-56

[23]

Neville J., 2003, P 9 KNOWL DISC DAT M

[24]

Resnic FS, 2000, J AM MED INFORM ASSN, P690

[25]

Roger VL, 2011, CIRCULATION, V123, pE18, DOI 10.1161/CIR.0b013e3182009701

[26]

Sutton R., 2000, P 14 NEUR INF PROC S

[27]

Syed Z., 2011, SCI TRANSL MED, V3

[28] Prediction of coronary heart disease using risk factor categories [J].

Wilson, PWF ;

D'Agostino, RB ;

Levy, D ;

Belanger, AM ;

Silbershatz, H ;

Kannel, WB .

CIRCULATION, 1998, 97 (18) :1837-1847

← 1 2 3 →