Framework for Smart Electronic Health Record-Linked Predictive Models to Optimize Care for Complex Digestive Diseases
Abstract
Our major objective is to develop an electronic application capable of integrating and semantically standardizing electronic medical record (EMR) data to generate de-identified datasets populated with longitudinal clinical data drawn from diverse sources. In Year 1 of our project, we have successfully built the infrastructure to support this project. In year 2, we used the EMR output and selected genetic information to construct predictive models of the outcomes of complex digestive diseases using Bayesian network (BN) analysis of the generated databases. We plan on comparing performance among models generated using EMR data alone and data from disease-specific clinical research repositories (with and without genetic data). In collaboration with Walter Reed Army Medical Center, we will share our data acquisition strategies and algorithmic model development. In year 3, we built predictive models at both Walter Reed and Pittsburgh to evaluate the feasibility of sharing data and models. The integration of the two distinct patient populations will lay the groundwork for future data-sharing projects of mutual interest.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 01, 2014
- Accession Number
- ADA608042
Entities
People
- Melissa Saul
- Michael A. Dunn
Organizations
- University of Pittsburgh