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.

Open PDF

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

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Bayesian Networks
  • Biomedical Research
  • Databases
  • Department Of Defense
  • Diseases And Disorders
  • Electronic Mail
  • Gastrointestinal Diseases
  • Governments
  • Health Services
  • Information Operations
  • Instructions
  • Maryland
  • Models
  • National Governments
  • Predictive Modeling

Fields of Study

  • Medicine

Readers

  • Computational Modeling and Simulation
  • Gulf War Illness and Chronic Multisymptom Illness in Veterans.

Technology Areas

  • AI & ML
  • Microelectronics