Relaxing the definition of equivalent mathematical expressions to get more simpler and interpretable models
The Cava laboratory is a research group in the Computational Health Informatics Program at Boston Children’s Hospital and Harvard Medical School.
We are interested in improving the interpretability and fairness of predictive models deployed in healthcare settings. We create and study algorithms that can embed these notions when working with health data.
Join the Team! If you’re looking to do research in the areas of machine learning, interpretability, fairness, and health informatics, see the opportunities here.
Recent Posts
About our recent HUMIES award-winning algorithm for clinical prediction models
A new perspective on how this social theory relates to fair machine learning.
Recent Publications
Inexact Simplification of Symbolic Regression Expressions with Locality-sensitive Hashing
Genetic and Evolutionary Computation Conference (GECCO)
Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling
Circulation
Accuracy of deep learning models in interpreting intrapartum fetal monitoring to predict fetal acidemia
American Journal of Obstetrics and Gynecology (AJOG)