My research interests can be roughly divided in two camps.
On the applied side, I am interested in problems pertaining to the safe and effective deployment of AI tools in healthcare. I have been working on testing medical AI applications in real-world settings, measuring user preparedness and requirements, building predictive models to address various clinical challenges and estimating the cost-effectiveness of AI-powered interventions, among others.
On the theoretical front, my focus is on the methodological problems arising from the real-world implementation of AI in healthcare. In this realm I am especially interested in Explainable AI, Out-Of-Distribution detection and Causal Inference.
See my Scholar profile for an up-to-date list of publications. My open-source papers can be found on this arXiv page.