Li Jingwei, Bzdok Danilo, Chen Jianzhong, Tam Angela, Ooi Leon Qi Rong, Holmes Avram J, Ge Tian, Patil Kaustubh R, Jabbi Mbemba, Eickhoff Simon B, Yeo B T Thomas, Genon Sarah
Institute of Neuroscience and Medicine, Brain and Behavior (INM-7), Research Center Jülich, Jülich, Germany.
Institute for Systems Neuroscience, Medical Faculty, Heinrich-Heine University Düsseldorf, Düsseldorf, Germany.
Sci Adv. 2022 Mar 18;8(11):eabj1812. doi: 10.1126/sciadv.abj1812. Epub 2022 Mar 16.
Algorithmic biases that favor majority populations pose a key challenge to the application of machine learning for precision medicine. Here, we assessed such bias in prediction models of behavioral phenotypes from brain functional magnetic resonance imaging. We examined the prediction bias using two independent datasets (preadolescent versus adult) of mixed ethnic/racial composition. When predictive models were trained on data dominated by white Americans (WA), out-of-sample prediction errors were generally higher for African Americans (AA) than for WA. This bias toward WA corresponds to more WA-like brain-behavior association patterns learned by the models. When models were trained on AA only, compared to training only on WA or an equal number of AA and WA participants, AA prediction accuracy improved but stayed below that for WA. Overall, the results point to the need for caution and further research regarding the application of current brain-behavior prediction models in minority populations.
偏向多数群体的算法偏差对将机器学习应用于精准医学构成了关键挑战。在此，我们评估了基于脑功能磁共振成像的行为表型预测模型中的此类偏差。我们使用了两个具有混合种族/民族构成的独立数据集（青春期前与成年人）来检验预测偏差。当预测模型在以美国白人（WA）为主的数据上进行训练时，非裔美国人（AA）的样本外预测误差通常高于WA。这种对WA的偏差对应于模型学习到的更多类似WA的脑-行为关联模式。当模型仅在AA数据上进行训练时，与仅在WA或相同数量的AA和WA参与者数据上进行训练相比，AA的预测准确性有所提高，但仍低于WA。总体而言，结果表明在将当前脑-行为预测模型应用于少数群体时需要谨慎并进一步研究。
