The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Disparities in dermatology AI performance on a diverse, curated clinical image set
Open accessAbstract
An estimated 3 billion people lack access to dermatological care globally. Artificial intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However, most AI models have not been assessed on images of diverse skin tones or uncommon diseases. Thus, we created the Diverse Dermatology Images (DDI) dataset—the first publicly available, expertly curated, and pathologically confirmed image dataset with diverse skin tones. We show that state-of-the-art dermatology AI models exhibit substantial limitations on the DDI dataset, particularly on dark skin tones and uncommon diseases. We find that dermatologists, who often label AI datasets, also perform worse on images of dark skin tones and uncommon diseases. Fine-tuning AI models on the DDI images closes the performance gap between light and dark skin tones. These findings identify important weaknesses and biases in dermatology AI that should be addressed for reliable application to diverse patients and diseases.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In dermatology AI, annotation bias results in inconsistent disease labeling, especially related to differences in skin tone or race in 36% of cutaneous malignant neoplasms studies. Inter-annotator bias, due to varying expertise levels, further exacerbates this inconsistency by reinforcing pre-existing beliefs about normality or abnormalities88.”
From Bias recognition and mitigation strategies in artificial intelligence healthcare applications (2025) · cites this paper as [88]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Although our evaluations show stable cross-skin-tone performance without explicitly balanced training data (as shown to be necessary in a previous study63)”
From A Multimodal Vision Foundation Model for Clinical Dermatology (2025) · cites this paper as [63]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Key technical hurdles include standardizing image quality across photo acquisition methods, addressing confounding factors and artifacts in images, and developing representative datasets that span diverse patient populations (Choy et al, 2023; Daneshjou et al, 2022)”
From Artificial intelligence–enabled precision medicine for inflammatory skin diseases (2026) · cites this paper as Daneshjou et al, 2022
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Without better skin tone representation, AI severity assessment tools risk worsening health disparities, especially for darker skin tones.71”
From Assessing the performance of artificial intelligence models in evaluating inflammatory skin disease severity: a systematic review and meta-analysis (2025) · cites this paper as [71]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“However, recent studies have raised concerns about biases within these algorithms that could lead to health disparities, and potentially harm [14–16].”
From Bias in artificial intelligence algorithms and recommendations for mitigation (2023) · cites this paper as [14]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Self-citationmixup: Beyond Empirical Risk Minimization
Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017) · arXiv · doi:10.48550/arxiv.1710.09412 · Cited by 5,831
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
Sun, B., & Saenko, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_35 · Cited by 3,757
Tschandl, P., Rosendahl, C., & Kittler, H. (2018) · Scientific Data · doi:10.1038/sdata.2018.161 · Cited by 3,628
Haenssle, H. A., Fink, C., Schneiderbauer, R., Toberer, F., Buhl, T., Blum, A., Kalloo, A., Hassen, A. B. H., Thomas, L., Enk, A., et al. (2018) · Annals of Oncology · doi:10.1093/annonc/mdy166 · Cited by 1,571
Human-computer collaboration for skin cancer recognition
Tschandl, P., Rinner, C., Apalla, Z., Argenziano, G., Codella, N., Halpern, A., Janda, M., Lallas, A., Longo, C., Malvehy, J., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0942-0 · Cited by 1,024
Codella, N., Rotemberg, V., Tschandl, P., Celebi, M. E., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., Marchetti, M., et al. (2019) · arXiv · doi:10.48550/arxiv.1902.03368 · Cited by 984
Self-citationA deep learning system for differential diagnosis of skin diseases
Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0842-3 · Cited by 853
Cited by
Long, G. V., Swetter, S. M., Menzies, A. M., Gershenwald, J. E., & Scolyer, R. A. (2023) · The Lancet · doi:10.1016/s0140-6736(23)00821-8 · Cited by 746
Self-citationAlgorithmic fairness in artificial intelligence for medicine and healthcare
Chen, R. J., Wang, J. J., Williamson, D. F. K., Chen, T. Y., Lipkova, J., Lu, M. Y., Sahai, S., & Mahmood, F. (2023) · Nature Biomedical Engineering · doi:10.1038/s41551-023-01056-8 · Cited by 750
Bias in artificial intelligence algorithms and recommendations for mitigation
Nazer, L. H., Zatarah, R., Waldrip, S., Ke, J. X. C., Moukheiber, M., Khanna, A. K., Hicklen, R. S., Moukheiber, L., Moukheiber, D., Ma, H., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000278 · Cited by 621
Advances, challenges and opportunities in creating data for trustworthy AI
Liang, W., Tadesse, G. A., Ho, D., Fei-Fei, L., Zaharia, M., Zhang, C., & Zou, J. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00516-1 · Cited by 559
Self-citationShaping the future of healthcare: ethical clinical challenges and pathways to trustworthy AI
Goktas, P., & Grzybowski, A. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14051605 · Cited by 336
Metadata
- Authors
- Daneshjou, R., Vodrahalli, K., Novoa, R. A., Jenkins, M., Liang, W., Rotemberg, V., Ko, J., Swetter, S. M., Bailey, E. E., Gevaert, O., Mukherjee, P., Phung, M., Yekrang, K., Fong, B., Sahasrabudhe, R., Allerup, J. A. C., Okata-Karigane, U., Zou, J., & Chiou, A. S.
- Affiliations
- Stanford Medicine (US)
- Stanford University (US)
- Memorial Sloan Kettering Cancer Center (US)
- Department of Dermatology, Keio University School of Medicine, Tokyo, Japan.
- Chan Zuckerberg Biohub San Francisco (US)
- Corresponding author
- Daneshjou, Roxana
- Vodrahalli, Kailas
- Zou, James
- Chiou, Albert S.
- ORCID
- Venue
- Science Advances
- Published
- 2022-08-12
- Volume
- 8
- Issue
- 32
- Pages
- eabq6147-eabq6147
- ISSN
- 2375-2548 (ISSN-L)
- PMC
- PMC9374341
- OpenAlex
- W4221146266
- Cited by
- 544
- References
- 45
- Citations by year
- 2026: 214 · 2025: 165 · 2024: 104 · 2023: 55 · 2022: 5
- FWCI
- 34.40
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc
- Locations
- Science Advances (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1942926, CAREER)
- Melanoma Research Alliance
- National Cancer Institute (P30CA008748)
- National Institute of Arthritis and Musculoskeletal and Skin Diseases (T32AR007422)
- Topics
- Health Sciences › Medicine › Oncology › Cutaneous Melanoma Detection and Management
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Dermatology › Medicine and Dermatology Studies History
- Keywords
- algorithmic bias, darker skin tones, fine-tuning, skin cancer detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.