@article{3102871,
    title = "Performance of a deep neural network in teledermatology: a single-centre prospective diagnostic study",
    author = "Muñoz-López, C. and Ramírez-Cornejo, C. and Marchetti, M.A. and Han, S.S. and Del Barrio-Díaz, P. and Jaque, A. and Uribe, P. and Majerson, D. and Curi, M. and Del Puerto, C. and Reyes-Baraona, F. and Meza-Romero, R. and Parra-Cares, J. and Araneda-Ortega, P. and Guzmán, M. and Millán-Apablaza, R. and Nuñez-Mora, M. and Liopyris, K. and Vera-Kellet, C. and Navarrete-Dechent, C.",
    journal = "Journal of the European Academy of Dermatology and Venereology",
    year = "2021",
    volume = "35",
    number = "2",
    pages = "546-553",
    publisher = "Wiley-Blackwell Publishing Ltd",
    issn = "0926-9959, 1468-3083",
    doi = "10.1111/jdv.16979",
    keywords = "adult;  Article;  artificial intelligence;  clinical assessment;  clinical evaluation;  controlled study;  deep neural network;  diagnostic accuracy;  diagnostic test accuracy study;  exposure;  female;  human;  image quality;  imaging algorithm;  major clinical study;  male;  priority journal;  prospective study;  skin defect;  teleconsultation;  teledermatology;  dermatology;  skin disease;  telemedicine, Adult;  Artificial Intelligence;  Dermatology;  Female;  Humans;  Male;  Neural Networks, Computer;  Prospective Studies;  Skin Diseases;  Telemedicine",
    abstract = "Background: The use of artificial intelligence (AI) algorithms for the diagnosis of skin diseases has shown promise in experimental settings but has not been yet tested in real-life conditions. Objective: To assess the diagnostic performance and potential clinical utility of a 174-multiclass AI algorithm in a real-life telemedicine setting. Methods: Prospective, diagnostic accuracy study including consecutive patients who submitted images for teledermatology evaluation. The treating dermatologist chose a single image to upload to a web application during teleconsultation. A follow-up reader study including nine healthcare providers (3 dermatologists, 3 dermatology residents and 3 general practitioners) was performed. Results: A total of 340 cases from 281 patients met study inclusion criteria. The mean (SD) age of patients was 33.7 (17.5) years; 63% (n = 177) were female. Exposure to the AI algorithm results was considered useful in 11.8% of visits (n = 40) and the teledermatologist correctly modified the real-time diagnosis in 0.6% (n = 2) of cases. The overall top-1 accuracy of the algorithm (41.2%) was lower than that of the dermatologists (60.1%), residents (57.8%) and general practitioners (49.3%) (all comparisons P < 0.05, in the reader study). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained, the balanced top-1 accuracy of the algorithm (47.6%) was comparable to the dermatologists (49.7%) and residents (47.7%) but superior to the general practitioners (39.7%; P = 0.049). Algorithm performance was associated with patient skin type and image quality. Conclusions: A 174-disease class AI algorithm appears to be a promising tool in the triage and evaluation of lesions with patient-taken photographs via telemedicine. © 2020 European Academy of Dermatology and Venereology"
}