EHR Risk Blog · Chronic disease
Most U.S. adults live with chronic disease — risk models only help if they’re honest
Chronic disease burden in the United States is large and rising in younger adults. Predictive modeling can support research on prevention pathways—if evaluation is trustworthy.
The burden (CDC)
CDC chronic disease materials report that a large majority of U.S. adults live with at least one chronic condition, with multimorbidity common, and younger-adult prevalence rising over the last decade. Always cite the current CDC key-facts / trends page you use: cdc.gov/chronic-disease.
Where AI risk prediction fits—and where it fails
Early identification of elevated risk is a research and public-health aspiration. It fails when models are leaky (see the JAMA ICD study), miscalibrated, or unexplained. Connecting the chronic-disease need to the methods crisis is the point of this series.
How the EHR Risk Framework helps
- Teaching fixtures and BYO CSV for chronic-disease-style horizons
- Leakage audits and temporal / patient splits
- Calibration + SHAP for honest reporting practice
Sources
- CDC Chronic Disease resources — cdc.gov/chronic-disease
- Ramadan et al. JAMA Netw Open 2025 (ICD label leakage) — doi:10.1001/jamanetworkopen.2025.50454
Try the workbench
How it works A–Z Live demo Quickstart GitHub
Free demo server — it may be slow. Check it with a small amount of data. For larger workloads or freer experimentation, run locally or on your own server. Open live demo
Feedback: support@larucare.com · Cite: DOI & CITATION.cff