Leveraging Large Datasets and LLMs to Improve Health Equity

About this Class

The proliferation of medical data and the advancements of large language models (LLMs) promise to revolutionize healthcare; however, studying and improving health equity for all patients remains a significant challenge. In this talk, I will present recent work on two critical aspects of this evolving landscape. First, I will examine the unexpected consequences of multi-source data scaling. Counter to intuition, adding training data can sometimes reduce overall accuracy, produce uncertain fairness outcomes, and diminish worst-subgroup performance. These findings underscore the complexity of working with disparate data sources in healthcare AI. Next, I will showcase applications of LLMs to improve health equity. Through participatory design with healthcare workers and patients, we developed guiding principles for LLM use in maternal health. Additionally, we demonstrate how LLMs can help understand health disparities in treatment protocols by extracting rationales for treatment protocols using clinical notes. The talk concludes by emphasizing vigilance and ethical considerations as we advance towards more data-driven and AI-assisted healthcare.

Individuals with disabilities who need accommodation to participate in this meeting should contact: rebecca.krupenevich@nih.gov