Relational learning for sustainable health

Sustainable healthcare is a global need and requires better value–better health–for patients at lower cost. Predictive models have the opportunity to greatly increase value without increasing cost. Concrete examples include reducing heart attacks and reducing adverse drug events by accurately predicting them before they occur. In this paper we examine howaccurately such events can be predicted presently and discuss a machine learning approach that produces accurate such predictive models.

Duke Scholars

Author David Page Biostatistics & Bioinformatics, Division of Biostatistics