Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience
This addresses the reproducibility crisis in medical ML by enabling robust diagnostic models across diverse clinical settings, though it is an incremental improvement on domain adaptation methods.
The paper tackles the problem of machine learning models failing to generalize across different patient populations in neuroimaging for Alzheimer's disease, schizophrenia, and brain aging, by developing a weighted empirical risk minimization approach that uses only 10% of target group data; it achieves high accuracy, such as AUC >0.95 for AD classification and MAE <5 years for brain age prediction, outperforming existing domain adaptation techniques.
Machine learning (ML) has shown great promise for revolutionizing a number of areas, including healthcare. However, it is also facing a reproducibility crisis, especially in medicine. ML models that are carefully constructed from and evaluated on a training set might not generalize well on data from different patient populations or acquisition instrument settings and protocols. We tackle this problem in the context of neuroimaging of Alzheimer's disease (AD), schizophrenia (SZ) and brain aging. We develop a weighted empirical risk minimization approach that optimally combines data from a source group, e.g., subjects are stratified by attributes such as sex, age group, race and clinical cohort to make predictions on a target group, e.g., other sex, age group, etc. using a small fraction (10%) of data from the target group. We apply this method to multi-source data of 15,363 individuals from 20 neuroimaging studies to build ML models for diagnosis of AD and SZ, and estimation of brain age. We found that this approach achieves substantially better accuracy than existing domain adaptation techniques: it obtains area under curve greater than 0.95 for AD classification, area under curve greater than 0.7 for SZ classification and mean absolute error less than 5 years for brain age prediction on all target groups, achieving robustness to variations of scanners, protocols, and demographic or clinical characteristics. In some cases, it is even better than training on all data from the target group, because it leverages the diversity and size of a larger training set. We also demonstrate the utility of our models for prognostic tasks such as predicting disease progression in individuals with mild cognitive impairment. Critically, our brain age prediction models lead to new clinical insights regarding correlations with neurophysiological tests.