Chen Zhang

97% of 184 high-impact biomedical AI studies compare cross-validated models with tests assuming fold independence; in 69% of re-analyzable studies a significant comparison does not survive correction.

This study compares brain age models and direct models for predicting Alzheimer's Disease outcomes, finding that direct models perform better despite brain age models having larger training data.

DeepResBat improves MRI data harmonization by addressing covariate distribution differences, outperforming existing methods while avoiding false associations.

This paper adapts meta-matching frameworks to translate phenotypic prediction models from large to small MRI datasets, showing significant performance improvements over classical methods.

The paper introduces multilayer meta-matching to improve phenotypic prediction in small datasets by translating models from multiple large datasets, outperforming classical methods and transfer learning.