Paul Festor
PhD Student
Paul is a PhD student from the AI4Health CDT. His research focuses mainly on machine learning safety, with a focus on reinforcement learning, to deploy clinical decision support systems at the bedside. He got his engineer degree from the “Ecole des Mines de Nancy” (France) and his MSc degree in Computing with a specialisation in Ai and Machine Learning from Imperial College London.
Research Brief
Paul is interested in bringing machine learning to the real world in a safe way. He focuses mainly on off-policy reinforcement learning, probabilistic modelling and uncertainty estimation applied to clinical decision support systems.
Lab Publications
Assuring the safety of AI-based clinical decision support systems: a case study of the AI Clinician for sepsis treatment
2022Paul Festor, Yan Jia, Anthony C Gordon, A Aldo Faisal, Ibrahim Habli, Matthieu Komorowski
BMJ health & care informaticsMIDAS: Deep learning human action intention prediction from natural eye movement patterns
2022Paul Festor, Ali Shafti, Alex Harston, Michey Li, Pavel Orlov, A Aldo Faisal
arXiv preprint arXiv:2201.09135Levels of Autonomy and Safety Assurance for AI-Based Clinical Decision Systems
2021Paul Festor, Ibrahim Habli, Yan Jia, Anthony Gordon, A Aldo Faisal, Matthieu Komorowski
International Conference on Computer Safety, Reliability, and SecurityDeep learning human action intention classification from natural eye movement patterns
2021Ali Shafti, Paul Festor, Pavel Orlov, Mickey Li, A Aldo Faisal
Journal of VisionEnabling risk-aware Reinforcement Learning for medical interventions through uncertainty decomposition
2021Paul Festor, Giulia Luise, Matthieu Komorowski, A Aldo Faisal
IMLH - ICML 2021