Abstract
Advances in machine learning and the explosion of clinical data have demonstrated immense potential to fundamentally improve clinical care and deepen our understanding of human health. However, algorithms for medical interventions and scientific discovery in heterogeneous patient populations are particularly challenged by the complexities of healthcare data. Not only are clinical data noisy, missing, and irregularly sampled, but questions of equity and fairness also raise grave concerns and create additional computational challenges.
In this talk, I present two approaches for leveraging machine learning towards equitable healthcare. First, I examine how to address algorithmic bias in supervised learning for cost-based metrics discrimination. By decomposing discrimination into bias, variance, and noise components, I propose tailored actions for estimating and reducing each term of the total discrimination. Second, I demonstrate how to address one specific health disparity through the early detection of intimate partner violence from clinical indicators. Using a time-based model with noisy labels, we can correct for biases in data measurement to learn more clinically useful subtypes and improve prediction. The talk concludes with a discussion about how to rethink the entire machine learning pipeline with an ethical lens to building algorithms that serve the entire patient population
|