Topic: Integrating
genetics, multimodal medical imaging, and AI for high-precision risk prediction
of type 2 diabetes
Speaker: Hsin-Chou
Yang, Ph.D. Research Fellow and Director of the Institute of Statistical
Science, Academia Sinica
Time: December
24, 2025 (Wednesday), 12:10 – 14:00 p.m.
Venue: The
Management Building, 11F, AI Lecture Hall or Livestreaming https://reurl.cc/R9Ynp6
Registration: https://forms.office.com/r/YGHweb7HNT or scan QR code on poster
About the Speaker:
Dr. Hsin-Chou Yang is a statistician,
bioinformatician, and data scientist at Academia Sinica, where he is a Full
Research Fellow and Director. His work integrates methodological innovation
with biomedical applications, including major studies on the Han Chinese cohort
(Nature), AI-based diabetes prediction (Nature Communications), and COVID-19
viral subtypes (PNAS). He is an elected ISI and GYA member, recipient of
multiple national awards, active journal editor/reviewer, conference chair, and
mentor to young scientists.
Abstract:
In this talk, the speaker will share how
the team combined genetics, medical imaging, and rich health data from over
131,000 Taiwan Biobank participants to better understand and predict Type 2
Diabetes (T2D). Using AI—from deep learning on raw images to polygenic and
imaging risk scores—the study uncovered genetic links, causal relationships,
and new insights into how the body signals T2D risk. The integrated model
achieved an AUC of 0.944, demonstrating strong potential for scalable,
real-world precision health.
Organizers: Institute of Health Data Science
※ Registration needed.
