Reducing Biases towards Minoritized Populations in Medical Curricular Content via Artificial Intelligence for Fairer Health Outcomes

2024-05-21

AAAI/ACM Conference on AI, Ethics, and Society

AI Summary

Persistent, empirically refuted misconceptions—termed “bisinformation”—circulate widely in medical education materials, exacerbating health inequities. To address this, we introduce the first large-scale, multidimensional (gender/race/age), expert-annotated gold-standard dataset for medical educational bias detection, comprising over 12,000 pages. We propose BRICC, the first dedicated framework for bisinformation identification in medical pedagogy, integrating a human-in-the-loop workflow grounded in standardized bias annotation protocols, domain-informed feature engineering, and machine learning models—including binary classification, ensemble methods, and multi-task learning. Experimental results show that our binary classifier achieves an AUC of 0.923, outperforming baselines by 27.8%; the multi-task model yields modest F1 improvements specifically for race-related bias detection. This work establishes a scalable technical pathway and methodological foundation for systematic debiasing of medical curricula.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Computer Vision: Bias, Fairness & Privacy
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Biased information (recently termed bisinformation) continues to be taught in medical curricula, often long after having been debunked. In this paper, we introduce bricc, a first-in-class initiative that seeks to mitigate medical bisinformation using machine learning to systematically identify and flag text with potential biases, for subsequent review in an expert-in-the-loop fashion, thus greatly accelerating an otherwise labor-intensive process. We have developed a gold-standard bricc dataset throughout several years containing over 12K pages of instructional materials. Medical experts meticulously annotated these documents for bias according to comprehensive coding guidelines, emphasizing gender, sex, age, geography, ethnicity, and race. Using this labeled dataset, we trained, validated, and tested medical bias classifiers. We test three classifier approaches: a binary type-specific classifier, a general bias classifier; an ensemble combining bias type-specific classifiers independently-trained; and a multi-task learning (MTL) model tasked with predicting both general and type-specific biases. While MTL led to some improvement on race bias detection in terms of F1-score, it did not outperform binary classifiers trained specifically on each task. On general bias detection, the binary classifier achieves up to 0.923 of AUC, a 27.8% improvement over the baseline. This work lays the foundations for debiasing medical curricula by exploring a novel dataset and evaluating different training model strategies. Hence, it offers new pathways for more nuanced and effective mitigation of bisinformation.

Problem

• Identifying biased content in medical curricula using AI
• Developing machine learning classifiers to detect medical misinformation
• Reducing biases in healthcare education for fairer outcomes

Innovation

• Machine learning identifies biased medical text
• Expert-in-the-loop review system accelerates debiasing
• Multitask learning model improves race bias detection