We are pleased to announce yet another successful thesis defence this week, this time to Yixin Li on successfully defending his thesis, "A Comprehensive Evaluation Framework for Synthetic ECG: Assessing Fidelity, Utility, and Privacy", April 30, 2026.
Congratulations, Yixin, on this well-deserved accomplishment!
We are pleased to congratulate one of our lab members Kateryna Padalko on the successful defence of her thesis, "Adaptive Differential Privacy Budgeting Strategy for Optimizing Synthetic Data Generation and Privacy Protection in Healthcare".
Congratulations Kateryna on this well-deserved accomplishment!
A long-time member of the GenAI for Health research lab will be featured in a keynote session at the 2026 APHEO-OPHEN Conference as part of the “Full Sailing into Artificial Intelligence!” series. His presentation will explore the use of artificial intelligence to assess the quality of AI scribe tools in infectious disease case management, highlighting the importance of evaluating emerging technologies in real-world public health settings. This work reflects the lab’s commitment to advancing innovative, data-driven approaches and showcases the impact of its members in shaping the future of AI in health systems.
Modern health care often leaves patients unsupported between visits, contributing to worsening conditions and preventable readmissions. Doro, a startup from the University of Waterloo’s Velocity program co-founded by Rastin Rassoli, is developing clinically guided AI tools to bridge these gaps by continuously supporting patients before, between, and after care. Using patient-reported data, the platform monitors symptoms, offers evidence-based mental health support, and helps clinicians maintain better visibility into patient well-being. Designed specifically for clinical use, Doro emphasizes safety, privacy, and validation, and is being tested in areas such as mental health, addiction, and chronic illness, with the goal of improving recovery and reducing strain on the health-care system.
A University of Waterloo research team is using machine learning to speed up drug development by analyzing complex pharmaceutical data and predicting drug properties, interactions, and safety outcomes. Led by Dr. Helen Chen, with PhD candidate Bing Hu and applied mathematician Dr. Anita Layton, the team integrates biological and medical knowledge into their models to improve accuracy and better reflect real-world drug behavior.
We are pleased to congratulate one of our lab members Mikayla Neeb on the successful defence of her thesis, "Use of Large Language Models (LLMs) in Qualitative Analysis: Evaluating LLMs as Assistive Coding Agents", January 16, 2026.
Congratulations Mikayla on this well-deserved accomplishment!
Developing new drugs to treat illnesses has typically been a slow and expensive process. However, a team of researchers at the University of Waterloo uses machine learning to speed up the development time.
The Waterloo research team has created "Imagand," a generative artificial intelligence model that assesses existing information about potential drugs and then suggests their potential properties.