Disparities in dermatology AI performance on a diverse, curated clinical image set
656 images; three models below their reported ROC-AUC; DeepDerm sensitivity 0.69 on Fitzpatrick I-II against 0.23 on V-VI; dermatologists also worse on dark skin; fine-tuning DeepDerm and HAM10000 on DDI closed the gap.
656 images; three models below their reported ROC-AUC; DeepDerm sensitivity 0.69 on Fitzpatrick I-II against 0.23 on V-VI; dermatologists also worse on dark skin; fine-tuning DeepDerm and HAM10000 on DDI closed the gap.
Written from the full text read 2026-10-15.
What our sources record
Reproduced as it was written when this source was checked, figures and all.
doi:10.1126/sciadv.abq6147. Full text read: 656 images; three models below their reported ROC-AUC; DeepDerm sensitivity 0.69 on Fitzpatrick I-II against 0.23 on V-VI; dermatologists also worse on dark skin; fine-tuning DeepDerm and HAM10000 on DDI closed the gap.