Jon Donnelly
Hello! I’m a fourth-year PhD Student in Cynthia Rudin’s interpretable machine learning lab at Duke University. I research interpretable and controllable machine learning models that empower domain experts to understand, edit, and learn from complex models. In doing so, my work supports scientific discovery and keeps experts in the loop. Across these goals, I work to achieve real-world impact by spanning the research-to-practice gap, with an emphasis on applications in healthcare.
Outside of research, I enjoy running very long distances, drinking excessive amounts of coffee, playing card/board games, cooking, and watching survivor.
Selected Publications
-
AsymMirai: Interpretable Mammography-Based Deep Learning Model for 1–5-Year Breast Cancer Risk PredictionRadiology, 2024 -
Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-TimeIn Proceedings of the Computer Vision and Pattern Recognition Conference, 2025 -
Deformable ProtoPNet: An Interpretable Image Classifier using Deformable PrototypesIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022 -
Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon EffectarXiv preprint arXiv:2510.12734, 2025