Performance of a deep neural network in teledermatology: a single‐centre prospective diagnostic study

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.

Teledermatology During COVID-19: An Updated Review

“…This conclusion is emphasized by a study completed during COVID-19, where an AI screening tool was used to aid dermatologists in their diagnosis. In this study, AI was shown to be useful in only 11.8% of cases [63]. The significance of these studies combined is that the future of AI lies in aiding clinicians to improve patient care, not in replacing the job of dermatologists altogether.…”

“…Regardless of the hindrances to telemedicine in the future, technological advances in TD provide a positive outlook on dermatology in a post-COVID-19 world. Recent advancement of AI smartphone applications (apps) allow patients to take photos of skin lesions and receive a speculative diagnosis [63]. A 2020 review of dermatologic AI smartphone apps stated that AI allows skin cancer patients to be treated more effectively and quickly, which is significant given the increasing incidence of skin cancer.…”

Accuracy of Deep Neural Network in Triaging Common Skin Diseases of Primary Care Attention

“…In another research with 5,014 validated cases, AI obtained 76.9% accuracy in classifying 40 common dermatoses ( 17 ). Further, in a recently conducted study, 340 teledermatology images were tested for 174 different dermatological diseases, obtaining an accuracy of 41.2% ( 18 ).…”

Perilesional sun damage as a diagnostic clue for pigmented actinic keratosis and Bowen’s disease

“…This clue was detected by the methods of explainable artificial intelligence (AI) in the context of a human–computer collaboration study 11 . AI‐based decision support may augment human expertise in image‐based diagnostic medicine 14,15 . There are, however, concerns that AI may replace physicians instead of supporting them.…”

“… 11 AI‐based decision support may augment human expertise in image‐based diagnostic medicine. 14 , 15 There are, however, concerns that AI may replace physicians instead of supporting them. Instead of playing off human intelligence against artificial intelligence, it might be better to take the best of both worlds.…”