A Novel Framework to Integrate Data on Sex as a Biological Variable into Medical Education

Abstract

Background:

Empirical evidence demonstrating the influence of sex and gender on health has increased dramatically over the last two decades. Yet, the integration of this knowledge into medical school curricula remains limited. To address this gap, we used artificial intelligence (AI) to assess whether clinically relevant sex- and gender-based data were included in a pre-clerkship medical curriculum and develop recommendations for including such data in teaching materials.

Methods:

Utilizing the AI tool Humata.ai, we mapped the content of 26 clinical disciplines within the 2023–2024 Yale School of Medicine pre-clerkship curriculum. We gave the tool two commands: first, identify existing discussions related to sex as a biological variable (SABV) and gender as a social determinant of health, and second, find content areas that could benefit from including such material.

Results:

Based on a comprehensive analysis of educational materials, we successfully identified that SABV was discussed in 12 of the 26 clinical disciplines. The AI tool also identified significant gaps where data could be included on the influence of SABV on pathophysiology, pharmacology, diagnosis, and treatment. Although our AI commands evaluated both sex and gender content, the tool’s output centered on SABV.

Conclusions:

This study provides one of the first empirical demonstrations of a scalable AI framework for streamlining curricular review and enhancing the integration of clinically relevant content on SABV in medical education. AI-assisted review offers a pathway to transform clinical care by ensuring that future physicians are provided with evidence-based data showing the influence of sex on health.