Framework for Smart Electronic Health Record- Linked Predictive Models to Optimize Care for Complex Digestive Diseases.

摘要

Our objective is to utilize de identified database constructed from the world-wide Military Electronic medical record for datasets (constructed for clinical purposes and not research) specific to patients with Crohn's disease (CD) and acute pancreatitis (AP). Using the collected data we will develop Bayesian Network (BN) models to predict outcomes in CD and AP (death, surgeries, hospitalizations, etc). Once our model is developed we hope to apply our model at an outside institution, specifically University of Pittsburgh Medical Center (UPMC) who will be conducting a similar experiment, testing our model on their EMR.