Understanding unwarranted variations in emergency care
The Cava laboratory is a research group interested in improving the trustworthiness of artificial intelligence (AI) models deployed in healthcare settings. We study algorithmic notions of interpretability, fairness, accuracy, and robustness in medical applications of AI.
The lab is part of the Computational Health Informatics Program at Boston Children’s Hospital, affiliated with Harvard Medical School.
Recent Papers
Iterative Learning of Computable Phenotypes for Treatment Resistant Hypertension using Large Language Models
Machine Learning for Healthcare Conference
Deciphering the influence of demographic factors on the treatment of pediatric patients in the emergency department
Preprint
Recent Posts
Taking a closer look at survival modeling with ECGs
Relaxing the definition of equivalent mathematical expressions to get simpler and more interpretable models