Skip to content

Available Models

The Models section describes predictive models developed and deployed using the Medial Research Framework. These models are designed to identify patients at elevated risk for a range of clinical outcomes, supporting earlier interventions and improved healthcare decision-making.

Each model in this repository is built on standardized EMR data processed through the Medial Infrastructure - ensuring reproducibility, scalability, and compliance across diverse healthcare systems. The framework supports modular data pipelines, feature generation, and evaluation workflows, enabling seamless deployment of models across sites.

Most models presented here have been validated across multiple real-world datasets and healthcare partners.

What You’ll Find Here

  • Model Overviews - Brief summaries describing the clinical motivation, prediction targets, and input features.
  • Evidence - List of publication, deployments
  • Implementation Details - Intended usage and contact details

Each model page provides both conceptual and technical details, helping users understand why it was developed and in which contexts it performs best.

Model Name Model description Contact Details for Usage
LGI/Colon-Flag Detects colon cancer using age, sex, and CBCs Roche
LungFlag Detects lung cancer using age, sex, smoking information, and common blood tests Roche
GastroFlag Detects gastric cancer using age, sex, and common blood tests Roche
AAA Predicts AAA events Geisinger/TBD
FluComplications Predicts flu followed by complications such as pneumonia, hospitalization, or death TBD
Pred2D Predicts progression from prediabetes to diabetes Planned to be open source
FastProgressors Predicts rapid decline in eGFR Planned to be open source
Mortality Predicts mortality using CMS claims data TBD
Unplanned COPD Admission Prediction Model Predicts COPD hospitalization using CMS claims data TBD

Instructions for using an existing model can be found here