JAMA+ AI Conversations Understanding Disease Trajectories With AI
Apr 9, 2026
Fang Fang, professor at Karolinska Institutet leading integrative epidemiology, studies neurodegenerative disease using Nordic cohorts and AI. She discusses using AI to map disease trajectories, leverage registries and biobanks, and apply federated learning and digital twins. The conversation covers data types, ethics, generalizability, and training the next generation of epidemiologists.
AI Snips
Chapters
Transcript
Episode notes
Lifelong Linked Data Unlocks Life Course Epidemiology
- Nordic registries enable lifelong, linkable data across health, family, and social domains.
- Fang Fang links birth records, household ties, prescriptions, and neighborhood metrics to study life-course drivers of neurodegenerative disease.
AI Fits High-Dimensional Longitudinal Population Data
- AI excels at integrating high-dimensional, multimodal longitudinal data that standard epidemiologic models struggle with.
- Fang Fang emphasizes combining Nordic-scale registries, biobanks, and cohorts to leverage AI for complex disease trajectories.
Linking Short Studies To Lifelong Registry Context
- Fang Fang describes linking short-term specialized data (like six months of movement tracking) to lifelong registries.
- This linkage lets researchers see what happened before and after the specialized measurement across families and populations.