Computation and Informatics in Biology and Medicine (CIBM) Seminar:
Accurate prediction of future onset of disease from Electronic Health Records (EHRs) has important clinical implications. The arrival times of clinical events come at semi-irregular intervals and makes the prediction task challenging. In this talk I discuss two statistical machine learning methods that predict future onset of myocardial infarction, or heart attack. The first leverages the relational nature of EHRs. The second provides an explicit representation of continuous time, capturing the irregular arrival times of clinical events. I will discuss the relative advantages of each method and how these ideas may help shape the future customization of health care. function on real and simulated data.