A global atlas of digital dermatology to map innovation and disparities
Artificial intelligence promises democratized access to dermatological care, but model reliability depends on the quality and comprehensiveness of the underlying data. Despite rapid growth in publicly available dermatology images, the field lacks quantitative indicators to measure whether new datasets expand clinical coverage or merely replicate what is already known. Existing collections are widely assumed to be biased, yet the scale and topography of these gaps have remained unquantified, leaving the community without a road map for strategic data acquisition. Here, we show, by unifying 1.1 million images from 29 public datasets into a queryable semantic atlas, that the global archive is markedly skewed and increasingly redundant: darker skin tones (Fitzpatrick V–VI) constitute only 11.0% of images, pediatric patients only 2.3%, and informational novelty has plateaued despite exponential growth, revealing where targeted data acquisition is most needed.
Authors
- Álvaro González-Jiménez (ORCID: https://orcid.org/0000-0002-1337-9430)
- Ludovic Amruthalingam (ORCID: https://orcid.org/0000-0001-5980-5469)
- Simone Lionetti (ORCID: https://orcid.org/0000-0001-7305-8957)
- Marc Pouly (ORCID: https://orcid.org/0000-0002-9520-4799)
- Philippe Gottfrois (ORCID: https://orcid.org/0000-0001-8023-3207)
- Matthew Groh (ORCID: https://orcid.org/0000-0002-9029-0157)
- Alexander Andreas Navarini (ORCID: https://orcid.org/0000-0001-7059-632X)
- Alexander Romswinkel
- Fabian Gröger (ORCID: https://orcid.org/0000-0002-9699-688X)
- G. Nikolakis
- Lea Habermacher
- Maximilian Böhm
- Sara Cerminara
Institutions
- Northwestern University (US)
- University of Basel (CH)
- Kellogg's (Canada) (CA)
- University Hospital of Basel (CH)
- Lucerne University of Applied Sciences and Arts (CH)
Publication Details
- Journal
- Nature Communications
- Published
- 2026-11-21
- DOI
- https://doi.org/10.1038/s41467-026-78602-w
- Primary Topic
- Cutaneous Melanoma Detection and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung