“Learning from Multi-Institutional Data—A Practical Guide”
In the webinar “Learning from Multi-Institutional Data—A Practical Guide”, Dr. Jayashree Kalpathy-Cramer will share her experience developing robust and trustworthy algorithms, handling challenges including a lack of repeatability, explainability, generalizability, and the potential for bias. She will review examples of privacy-preserving learning from multi-institutional data sets and discuss successes as well as directions for future research.
Approaches such as federated learning can improve the robustness of algorithms by providing a framework where the trained models have been exposed to multi-institutional data sets without the need for data sharing.
This webinar is part of the monthly NIH Data Sharing and Reuse Seminar Series hosted by the NIH Office of Data Science and Strategy.
Dr. Kalpathy-Cramer is currently an associate professor of radiology at Harvard Medical School and a co-director of the Quantitative Translational Imaging in Medicine (QTIM) Lab and the Center for Machine Learning at the Martinos Center. She is the incoming chief of the new Division of Artificial Medical Intelligence in Ophthalmology at the University of Colorado School of Medicine.
Upcoming Events
- Envisioning a Future Toward More Equitable Trials: Artificial Intelligence and Its Implications in Health EquitySeptember 09, 2024 - September 10, 2024Impact of the Molecular Characterization Initiative on Pediatric CNS TumorsSeptember 10, 2024AI and Global OncologySeptember 24, 2024NCI’s Clinical and Translational Data Commons: Your Resource for Cancer DiscoverySeptember 25, 2024NCI Office of Data Sharing’s Annual Data Sharing Symposium: Driving Cancer Advances Through Impactful ResearchOctober 16, 2024The Cancer Research Data Commons 2024 Fall Symposium: Ten Years of Empowering Cancer ResearchersOctober 16, 2024 - October 17, 2024