Russ College of Engineering and Technology
Faculty
Ziyang Song
Assistant Professor
Electrical Engineering and Computer Science
Biography
Dr. Song received a Ph.D. degree in computer science from McGill University. Song's current research focus is the development of trustworthy and explainable AI models to address critical biomedical challenges. In generative modelling, he focuses on time-series representation learning for biosignals, clinical measurements, and longitudinal medical records, enabling health trajectory analysis and various clinical tasks. In probabilistic modelling, his work involves interpretable medical representations to improve clinical decision-making for electronic health records.
Journal Article, Academic Journal (3)
- Yang, Z., Song, Z., Zabad, S., Legault, M., Li, Y. (2026). PheCode-guided multi-modal topic modeling of electronic health records improves disease incidence prediction and GWAS discovery from UK Biobank. 1. Briefings in Bioinformatics; 27: bbag030.
- Song, Z., Lu, Q., Xu, H., Yang, Z., Zhu, H., Buckeridge, D., Li, Y. (2025). Timelygpt: extrapolatable transformer pre-training for long-term time-series forecasting in healthcare. 64. Health Information Science and Systems; 13.
- Song, Z., Lu, Q., Zhu, H., Buckeridge, D., Li, Y. (2025). TrajGPT: Irregular Time-Series Representation Learning of Health Trajectory. IEEE Journal of Biomedical and Health Informatics.
Other (1)
- Song, Z., Lu, Q., Zhu, H., Song, Z. (2025). SMI: Semantic Medical ID for Hierarchy-Aware Concept Representation. NeurIPS Responsible Foundation Model Workshop 2025; https://openreview.net/forum?id=Z8RT75Prj1&referrer=%5Bthe%20profile%20of%20Ziyang%20Song%5D(%2Fprofile%3Fid%3D~Ziyang_Song4).