Back

Advancing Fair and Explainable Machine Learning for Neuroimaging Dementia Pattern Classification in Multi-Ethnic Populations

Ho, N.-H.; Charisis, S.; Honnorat, N.; Brandigampala, S. R.; Wang, D.; Heckbert, S. R.; Fox, P. T.; Martinez, D.; Wang, D. H.; Hughes, T. M.; Archer, D. B.; Hohman, T. J.; Seshadri, S.; Davatzikos, C.; Habes, M.

2025-06-12 neuroscience
10.1101/2025.06.09.658375 bioRxiv
Show abstract

Dementia, a degenerative disease affecting millions globally, is projected to triple by 2050. Early and precise diagnosis is essential for effective treatment and improved quality of life. However, current diagnostic approaches frequently demonstrate inconsistent precision and impartiality, particularly among diverse cultural groups. This study investigates performance discrepancies in dementia classification among White American, African American, and Hispanic populations. We reveal significant cross-group bias, particularly when models trained on one group are tested on another. To address this, we introduce a novel combination of few-shot learning and domain alignment to improve model adaptability across underrepresented populations. Our results show that these techniques substantially reduce inter-group performance gaps, especially between White American and Hispanic cohorts. This finding highlights the crucial need for fairness-aware strategies and the inclusion of diverse populations in training data to ensure accurate and equitable dementia diagnoses.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.