Frontiers in Machine Learning: Saving Lives with Interpretable ML

This session is about Saving Lives Using Interpretable Machine Learning in HealthCare. It’s critical to make sure healthcare models are safe to deploy. One challenge is that most patients are receiving treatment and that affects the data. A model might learn high blood pressure is good for you because the treatment given when you have blood pressure lowers risk compared to healthier patients with lower blood pressure. There are many ways confounding can cause models to predict crazy things. In the first pre