Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Sep 16;100(16):adv00260.
doi: 10.2340/00015555-3624.

Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis

Oscar Zaar  1 , Alexander Larson, Sam Polesie, Karim Saleh, Mikael Tarstedt, Antonio Olives, Andrea Suárez, Martin Gillstedt, Noora Neittaanmäki
Affiliations

Evaluation of the Diagnostic Accuracy of an Online Artificial Intelligence Application for Skin Disease Diagnosis

Oscar Zaar et al. Acta Derm Venereol. .

Abstract

Artificial intelligence (AI) algorithms for automated classification of skin diseases are available to the consumer 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 diagnoses, 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.

Keywords: dermatology; online diagnostics; skin disease; artificial intelligence.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: OZ, KS, AO, AS and MAT previously worked as consultants for iDoc24, the company developing Skin Image SearchTM.

Figures

Fig. 1
Fig. 1
The overall diagnostic accuracy of the Skin Image Search™ application. The scores 0–5 are colour-coded by different shades of blue with darker shades portraying more accurate scores. The artificial intelligence application was able to place the correct diagnosis among the top 5 in 56.4% (294/521) of the images and failed to give the correct diagnosis in 43.6% (227/521) of the images. CI: confidence interval.
Fig. 2
Fig. 2
Diagnostic accuracy for the diagnostic groups.
Fig. 3
Fig. 3
Diagnostic accuracy for individual diagnoses. The bars are encoded with different colours depending on the given scores (0–5). Diagnoses with <10 images uploaded for classification are presented in parentheses.
See this image and copyright information in PMC

References

    1. Karimkhani C, Dellavalle RP, Coffeng LE, Flohr C, Hay RJ, Langan SM, et al. Global skin disease morbidity and mortality: an update from the Global Burden of Disease Study 2013. JAMA Dermatol 2017; 153: 406–412. - PMC - PubMed
    1. Lindberg M, Isacson D, Bingefors K. Self-reported skin diseases, quality of life and medication use. A nationwide pharmaco-epidemiological survey in Sweden. Acta Derm Venereol 2014; 94: 188–191. - PubMed
    1. Rea JN, Newhouse ML, Halil T. Skin disease in Lambeth. A community study of prevalence and use of medical care. Br J Prev Soc Med 1976; 30: 107–114. - PMC - PubMed
    1. Augustin M, Herberger K, Hintzen S, Heigel H, Franzke N, Schafer I. Prevalence of skin lesions and need for treatment in a cohort of 90 880 workers. Br J Dermatol 2011; 165: 865–873. - PubMed
    1. Janda M, Soyer HP. Can clinical decision making be enhanced by artificial intelligence? Br J Dermatol 2019; 180: 247–248. - PubMed