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
The Benefit of the Doubt Phenomenon in Emergency Triage Assignment Disparities
Preprint
Automated Echocardiographic Detection of Congenital Heart Disease Using Artificial Intelligence
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