Supervised Domain Adaptation Mitigates Cross-Ethnicity Prediction Error in Neuroimaging Based Cognitive Prediction
Lal Khakpoor, F.; van der Vliet, W.; Deng, J.; Wang, Y.; Pat, N. · neuroscience · 2026-09-07 · 原文
DOI：10.64898/2026.05.25.727742作者：5 位
Machine learning models are increasingly used to predict cognitive and clinical outcomes from neuroimaging data, yet challenges in fairness and generalizability remain. Large scale datasets are often racially and ethnically imbalanced, leading to systematic performance disparities, with models typically achieving higher accuracy for majority populations represented in the training data. In this study, we evaluated whether supervised domain adaptation methods including balanced weighting, two-stage TrAdaBoost, feature augmentation with SrcOnly prediction, and linear interpolation can mitigate these biases. Using the ABCD dataset, we assessed whether models trained on 80 MRI measures from White American participants could generalize more effectively to African American participants. All domain adaptation methods reduced prediction error for African American participants, particularly for MRI modalities with large baseline disparities (e.g., structural MRI), while offering limited improvements where initial gaps were smaller (e.g., functional connectivity). Among the approaches, balanced weighting performed best and remained stable and beneficial even when only 10 African American par
讲义
讲义·推断 依据「原文」自动生成的结构化摘要（推断），非原文表述；以原文为准。
1. 人话版
Machine learning models are increasingly used to predict cognitive and clinical outcomes from neuroimaging data, yet challenges in fairness and generalizability remain.
Large scale datasets are often racially and ethnically imbalanced, leading to systematic performance disparities, with models typically achieving higher accuracy for majority populations represented in the training data.
2. 领域脉络
本文类目：neuroscience，属于其所在研究脉络的最新进展。
3. 机制拆解
摘要未展开方法细节——精读时重点看方法/模型部分。
4. 证据与数字
Using the ABCD dataset, we assessed whether models trained on 80 MRI measures from White American participants could generalize more effectively to African American participants.
Among the approaches, balanced weighting performed best and remained stable and beneficial even when only 10 African American par
5. 反例与边界
In this study, we evaluated whether supervised domain adaptation methods including balanced weighting, two-stage TrAdaBoost, feature augmentation with SrcOnly prediction, and linear interpolation can mitigate these biases.
All domain adaptation methods reduced prediction error for African American participants, particularly for MRI modalities with large baseline disparities (e.g., structural MRI), while offering limited improvements where initial gaps were smaller (e.g., functional connectivity).
6. 跨领域连接与意外收获
思考本文机制能否迁移到你正在跟进的问题。
7. 可复用方法
把本文机制与你手头项目对照，找一个两周内能验证的最小实验。
8. 术语表
精读时把不熟的术语记入此处，作为下次回忆的锚点。