Abstract
Artificial intelligence is increasingly moving from structured clinical settings into broader real-world health applications, where data become more heterogeneous, context-dependent, and incomplete. My research explores how AI can remain reliable as the nature of available information changes across this spectrum. Starting from population-scale longitudinal healthcare records, I study how large-scale clinical data can support longitudinal health modeling and risk prediction. I then extend this perspective to physiological and biomedical measurements, where the meaning of an observation depends on subject and measurement context, including heart rate variability with individual attributes and flow cytometry across instruments. More recently, I have focused on settings where clinically relevant information is only partially or indirectly observed, exploring how foundation and generative models can reason beyond the available measurements. Across these efforts, my goal is to build AI systems that can learn from, contextualize, and reason across diverse real-world health information, translating methodological advances into practical impact across healthcare and well-being.
Bio
Huan-Yu Chen (Ray) is a Postdoctoral Researcher in the Department of Electrical Engineering at National Tsing Hua University (NTHU), Taiwan. He received his B.S. and Ph.D. degrees in Electrical Engineering from NTHU in 2018 and 2024, respectively, and conducted his doctoral research under the supervision of Prof. Chi-Chun Lee (Jeremy). He also serves as the Chief Technology Officer at AHEAD Medicine. His research focuses on Clinical AI, developing machine learning methods for heterogeneous real-world health data across clinical records, physiological signals, medical imaging, and biomedical measurements. His recent work explores context-aware learning, generative AI, and foundation models for reliable health inference across diverse data settings. He has published more than 20 peer-reviewed papers in journals and conferences, including IEEE Journal of Biomedical and Health Informatics, PLOS Digital Health, ICASSP, EMBC, ISBI, and INTERSPEECH. His research has involved collaborations with industry and healthcare partners, including Johnson & Johnson, Allianz, Cathay Financial Holdings, Cofit Healthcare, and AHEAD Medicine, covering longitudinal health risk modeling, cancer analytics, population health, and automated flow cytometry analysis. His honors include the Outstanding R&D Substitute Service Award from the Ministry of the Interior, Taiwan (2026), the NTHU Outstanding Postdoctoral Fellow Award (2025), and Second Prize in the INTERSPEECH 2018 ComParE Challenge.