Search AMIA.org

Learn how AI-powered "digital twin" patient models could replace traditional clinical trials, accelerating medical discovery at a fraction of the time and cost.

Dr. Yin presents ADSMoE, a novel transformer autoencoder that integrates multi-modal data—neuroimaging, genetic, protein, and clinical—to identify four biologically distinct Alzheimer's disease subtypes, validated across three major cohorts (ADNI, NACC, and UKBB).

NutriBench is a new benchmark dataset of ~12,000 annotated meal descriptions for testing AI nutrition estimation. Top LLMs matched human dietitian accuracy on carbohydrate estimation at a fraction of the time, showing strong potential for improving dietary guidance.

Large language models are transforming clinical NLP, but real-world healthcare pipelines still combine LLMs with traditional methods to turn clinical notes and patient narratives into structured evidence. This talk covers two active projects using this approach — one studying medication adherence across five diseases, another improving drug safety prediction — and discusses best practices for evaluating LLM systems in clinical settings.

In this webinar, we will learn what FACMI and FAMIA are, why they matter, and how to prepare for a successful nomination. Presenters