Weiss Jeremy C, Page David, Peissig Peggy L, Natarajan Sriraam, McCarty Catherine
University of Wisconsin-Madison 1300 University Ave, Madison,WI {jcweiss,page}@biostat.wisc.edu.
Marshfield Clinic Research Foundation 1000 North Oak Ave, Marshfield,WI
Proc Innov Appl Artif Intell Conf. 2012;2012:2341-2347.
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.
电子健康记录（EHRs）是一个新兴的关系领域，在改善临床结果方面具有巨大潜力。我们将两种统计关系学习（SRL）算法应用于预测原发性心肌梗死的任务。我们表明，一种SRL算法，即关系功能梯度提升，在医学相关的高召回率区域尤其优于命题学习器。我们观察到，两种SRL算法在预测结果方面都比其命题类似算法更好，并提出了我们的方法如何增强当前流行病学实践。
