Deep transfer learning for reducing health care disparities arising from biomedical data inequality

Abstract

As artificial intelligence (AI) is increasingly applied to biomedical research and clinical decisions, developing unbiased AI models that work equally well for all racial and ethnic groups is of crucial importance to health disparity prevention and reduction. However, the biomedical data inequality between different racial and ethnic groups is set to generate new health care disparities through data-driven, algorithm-based biomedical research and clinical decisions. Using an extensive set of machine learning experiments on cancer omics data, we found that current prevalent schemes of multiethnic machine learning are prone to generating significant model performance disparities between racial groups. We showed that these performance disparities are caused by data inequality and data distribution discrepancies between racial groups. We also found that transfer learning can improve machine learning model performance for data-disadvantaged racial groups, and thus provides a novel approach to reduce health care disparities arising from data inequality among racial groups.