AI-Powered Clinical Guideline Assistant
A research team from the UBC Department of Psychiatry, with support from UBC CIC, developed a prototype AI tool that helps clinicians use the Canadian Network for Mood and Anxiety Treatments (CANMAT) guidelines more efficiently. The tool streamlines access to guideline recommendations during patient visits so clinicians have timely scientific information for decision support. Using generative artificial intelligence and large language models, the prototype supports psychiatrists as they identify suitable treatment options for mood and anxiety disorders. Designed with scalability in mind, the prototype could be applied for use with other clinical guidelines or other use cases within healthcare.
Approach
The project adopted a multidisciplinary approach integrating clinical expertise, AI innovation, and user-centered design to develop the AI prototype. The project began by exploring how generative AI and large language models (LLMs) could interpret and use the CANMAT guidelines in real-world clinical practice. Throughout the development process, the UBC CIC team provided technical leadership, project management, and strategic guidance on leveraging AWS services for scalable LLM deployment and secure data handling to ensure delivery, alignment, and continuous improvement through iterative feedback. The prototype allows clinicians to interact with clinical guidelines using natural language, enabling rapid access to relevant recommendations and evidence-based insights to support decision-making. It uses Qwen embeddings hosted on Amazon SageMaker Serverless Inference and runs a Llama model on Amazon Bedrock.
The collaboration led to important findings and the submission of a manuscript for review. The results are here: https://www.medrxiv.org/content/10.64898/2025.11.30.25341311v1.
Acknowledgements
Dr. John-Jose Nunez, Assistant Professor (Partner), UBC Department of Psychiatry
Student team – Yash Mali, Zejiao Zeng, Kayoung Heo, Grace Zhang and Jincheng Chen.
Image by Alex Green.
About the University of British Columbia Cloud Innovation Centre (UBC CIC)
The UBC CIC is a public-private collaboration between UBC and Amazon Web Services (AWS). A CIC identifies digital transformation challenges, the problems or opportunities that matter to the community, and provides subject matter expertise and CIC leadership.
Using Amazon’s innovation methodology, dedicated UBC and AWS CIC staff work with students, staff and faculty, as well as community, government or not-for-profit organizations to define challenges, to engage with subject matter experts, to identify a solution, and to build a Proof of Concept (PoC). Through co-op and work-integrated learning, students also have an opportunity to learn new skills which they will later be able to apply in the workforce.
