Test-Free AI Screening for Complex Diseases Using EHR Data

What if complex diseases could be screened before symptoms become obvious, without new tests, labs, or patient questionnaires? This talk presents a zero-burden AI screening approach that uses existing EHR history to predict disease risk at the point of care. ⏱️ Key moments: 00:00 Test-free screening and ZCoR concept 02:00 Using EHR data for longitudinal risk modelling 04:30 Why early detection fails in complex diseases 06:40 Case studies: pulmonary fibrosis and disease forecasting 13:50 Additional conditions: Alzheimer’s, pancreatitis, broader applications 18:30 Interpreting the model: comorbidity patterns and explainability 21:20 Deployment, APIs, and future digital twins Ishanu Chattopadhyay (Assistant Professor of Biomedical Informatics and Computer Science at the University of Kentucky) explains how the Zero-Burden Risk Assessment framework uses longitudinal medical histories to forecast complex diseases. The approach does not require new labs, imaging, questionnaires, or patient interaction. Instead, it analyses diagnostic codes, medications, procedures, and timestamps already present in electronic health records. The session covers examples across pulmonary fibrosis, Alzheimer’s disease and related dementias, and acute pancreatitis, showing how AI can support earlier detection, population-scale screening, and better clinical trial cohort selection. The key idea is simple: early screening should not depend on more tests. It can start with the medical history patients already have. 📌 Applied Healthcare AI Summit 2026 — real-world AI deployment in healthcare, from pilots to production systems. #HealthcareAI #MedicalAI #ClinicalAI #EHR #PredictiveAnalytics #DiseaseScreening #DigitalHealth #BiomedicalInformatics