Platforms to improve computational reproducibility in biomedical research
Benjamin Haibe-Kains, UHN
Tuesday Feb 2 2021, 12:00-1:00pm
Zoom Link:听
Abstract:听As machine learning becomes a method of choice to analyze biomedical data, the field is facing multiple challenges around research reproducibility and transparency. Given the proliferation of studies investigating the applications of machine learning in biomedical research studies, it is essential for independent researchers to be able to scrutinize and reproduce the results of a study using its materials, and build upon them in future studies.听Computational reproducibility is achievable when the data can easily be shared and the required computational resources are relatively common. However, the complexity of AI algorithms and their implementation, the need for specific computer hardware and the use of sensitive biomedical data represent major obstacles in healthy-related research. In this talk, I will describe the various aspects of a biomedical study using machine learning that are necessary for reproducibility and the platforms that exist for sharing these materials with the scientific community.
听
