Technical sharing workshop 3: Data access requests
This webinar covers the implementation of Jira Service Management as a system for managing requests for access to hospital data for research through the RI-MUHC portal. It presents the steps that let users submit consultation requests and data requests and give feedback, and explains the choices made when designing the system, including the academic and industry standards used. The speaker also presents an assessment of the current tool, its strengths and limitations, and the challenges met during its rollout. He shares lessons from the testing phase, the adjustments made and the improvements still to come. Finally, he offers recommendations for teams considering similar systems.
With Santiago Marquez and Ivana Vranic
Organized by the DALIAS community of practice.
In partnership with the FRQ and the MSSS
Date: May 7, 2025
Practical experiences with synthetic data
The application of synthetic data generation (SDG) has been increasing in recent years. With SDG, a machine learning model is trained on existing real data, and it learns the patterns in that data. The model is then used to generate new data that preserve the learned patterns. There are multiple use cases for SDG: privacy, de-biasing, and augmentation. This presentation provides an overview of SDG, how to evaluate the privacy vulnerabilities in synthetic data, methods for assessing the utility of synthetic data, as well as applications for de-biasing real-world datasets (RWD) and augmentation in clinical trials and RWD. Specific examples and a summary of evidence are reviewed.
With Khaled El Emam
Organized by the DALIAS community of practice.
Date: March 10, 2025
Using large language models locally in research
This workshop introduced researchers to generative AI tools that can run offline, such as Ollama and the Transformers library for Python.
François Pelletier is a digital entrepreneur and research professional with the medical physics research group at Université Laval. He holds a master’s degree in actuarial science (2014) and completed the microprogram in intelligent software systems (2019). His interests include personal data protection, the social impacts of digital technologies, and using local computing power for machine learning inference, especially for language models.