Evaluating Fairness and Generalizability of Alzheimers Disease Diagnosis Models Trained on Racially Imbalanced Datasets
Neha Goud Baddam, Bizhan Alipour Pijani, Melissa Petersen, Serdar Bozdag
This study evaluates how Alzheimer's disease diagnosis models perform across racial groups and finds that models trained on one group underperform on others, but fairness techniques can reduce bias.
bioRxiv · Sep 30, 2025 · PreprintBioinformatics