Abstract: To improve the care and outcomes of patients with type-2 diabetes mellitus, a machine learning based pharmacotherapy decision support system (PDSS) was developed. The PDSS predicts the probability of achieving treatment goals based on multiple patient parameters, uses the standards-based OpenCDS decision support framework, and is integrated with the electronic health record (EHR) via the SMART on FHIR interoperability paradigm. The accuracy and AUC of predictions were more than 0.80 and 0.87, respectively. The application has been successfully integrated with the EpicĀ® EHR.

Learning Objective 1: A clinical decision support system using a machine learning technology integrated with an electronic health record via the SMART on FHIR interoperability paradigm will be described.


Wataru Takeuchi (Presenter)
Hitachi Ltd.

Shinji Tarumi, Hitachi Ltd.
Salvador Rodriguez, University of Utah
David Shields, University of Utah
Phillip Warner, University of Utah
Michael Flynn, University of Utah
Kyle Turner, University of Utah
Farrant Sakaguchi, University of Utah
Hideyuki Ban, Hitachi Ltd.
Kensaku Kawamoto, University of Utah

Presentation Materials: