Evaluation of the diagnostic accuracy of an online artificial intelligence application for skin disease diagnosis
(2020) In Acta Dermato-Venereologica 100(16). p.1-6- Abstract
Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the con-sumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clinical images including tumours, infective and inflammatory skin diseases were collected at the Department of Dermatology at the Sahlgrenska University Hospital and uploaded for classification by the online application. The AI algorithm classified the images giving 5 differential diagno-ses, which were then compared to the diagnoses made clinically by the dermatologists and/or histologically. We included 521 images portraying 26 diagnoses. The... (More)
Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the con-sumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clinical images including tumours, infective and inflammatory skin diseases were collected at the Department of Dermatology at the Sahlgrenska University Hospital and uploaded for classification by the online application. The AI algorithm classified the images giving 5 differential diagno-ses, which were then compared to the diagnoses made clinically by the dermatologists and/or histologically. We included 521 images portraying 26 diagnoses. The diagnostic accuracy was 56.4% for the top 5 suggested diagnoses and 22.8% when only considering the most probable diagnosis. The level of diagnostic accuracy varied considerably for diagnostic groups. The online application demonstrated low diagnostic accuracy compared to a dermatologist evaluation and needs further development.
(Less)
- author
- Zaar, Oscar ; Larson, Alexander ; Polesie, Sam ; Saleh, Karim LU ; Tarstedt, Mikael ; Olives, Antonio ; Suarez, Andrea ; Gillstedt, Martin and Neittaanmäki, Noora
- organization
- publishing date
- 2020
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Artificial intelligence, Dermato-logy, Online diagnostics, Skin disease
- in
- Acta Dermato-Venereologica
- volume
- 100
- issue
- 16
- article number
- adv00260
- pages
- 6 pages
- publisher
- Medical Journals Limited
- external identifiers
-
- pmid:32852557
- scopus:85091107771
- ISSN
- 0001-5555
- DOI
- 10.2340/00015555-3624
- language
- English
- LU publication?
- yes
- id
- 63207a64-f3b4-4df3-ae28-2ac4ad5be32f
- date added to LUP
- 2021-01-08 14:08:13
- date last changed
- 2024-09-05 12:41:34
@article{63207a64-f3b4-4df3-ae28-2ac4ad5be32f, abstract = {{<p>Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the con-sumer market. Studies of their diagnostic accuracy are rare. We assessed the diagnostic accuracy of an open-access AI application (Skin Image Search™) for recognition of skin diseases. Clinical images including tumours, infective and inflammatory skin diseases were collected at the Department of Dermatology at the Sahlgrenska University Hospital and uploaded for classification by the online application. The AI algorithm classified the images giving 5 differential diagno-ses, which were then compared to the diagnoses made clinically by the dermatologists and/or histologically. We included 521 images portraying 26 diagnoses. The diagnostic accuracy was 56.4% for the top 5 suggested diagnoses and 22.8% when only considering the most probable diagnosis. The level of diagnostic accuracy varied considerably for diagnostic groups. The online application demonstrated low diagnostic accuracy compared to a dermatologist evaluation and needs further development.</p>}}, author = {{Zaar, Oscar and Larson, Alexander and Polesie, Sam and Saleh, Karim and Tarstedt, Mikael and Olives, Antonio and Suarez, Andrea and Gillstedt, Martin and Neittaanmäki, Noora}}, issn = {{0001-5555}}, keywords = {{Artificial intelligence; Dermato-logy; Online diagnostics; Skin disease}}, language = {{eng}}, number = {{16}}, pages = {{1--6}}, publisher = {{Medical Journals Limited}}, series = {{Acta Dermato-Venereologica}}, title = {{Evaluation of the diagnostic accuracy of an online artificial intelligence application for skin disease diagnosis}}, url = {{http://dx.doi.org/10.2340/00015555-3624}}, doi = {{10.2340/00015555-3624}}, volume = {{100}}, year = {{2020}}, }