Framework for Smart Electronic Health Record - Linked Predictive Models to Optimize Care for Complex Digestive Diseases
Abstract
Our objective is to utilize a 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 this collected data, we will develop Bayesian Network (BN) models to predict defined outcomes in CD and AP (death, surgeries, hospitalizations, etc.). Once our model is developed, we hope to apply the model to an outside institution, specifically University of Pittsburgh, who will be performing a similar project with the hopes of testing their model on our de-identified database. The goal would be to identify specific clinical history that would be able to accurately predict severity and morbidity associated with these gastrointestinal diseases.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2012
- Accession Number
- ADA568058
Entities
People
- Ganesh Veerappan
Organizations
- Henry M. Jackson Foundation for the Advancement of Military Medicine