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.

Toxic epidermal necrolysis spectrum (TENS) is a rare yet severe adverse drug reaction associated with a high mortality rate. Beyond supportive care, there is still no established therapy for TENS, although recent meta-analyses and UK guideline recommendations have attempted to offer a review of relevant literature on this difficult topic. As most directed treatments lack clear consensual evidence, care centres often resort to establishing their own strategies. As Canada's largest adult burn centre and the provincial reference centre for most burn patients in Ontario, our team at the Ross Tilley Burn Centre, in collaboration with the Department of Dermatology at Sunnybrook Health Sciences Centre, Toronto, Canada, has managed over 60 confirmed cases of TENS over the past 2 decades. We would like to share our management, experience, and present our treatment protocol that we recently established by a collaborative multidisciplinary team approach to help guide treatment of these complex patients not only in Canada but worldwide.

Background Mycosis fungoides (MF) typically has a CD4 + CD8 À T-cell phenotype. Rare cases of CD4 À CD8 + , CD4 À CD8 À , or CD4 + CD8 + immunophenotypes have been described.Little is known about the impact of MF immunophenotypes on disease behavior. MethodsWe conducted a retrospective cohort study to review all cases of MF from 2007 to 2017 from Sunnybrook Health Sciences Centre, Toronto, Canada. CD4 + CD8 À (Group 1) was compared to the three less common subtypes (Group 2) with respect to stage at diagnosis, progression, and transformation. Potential confounding factors (demographic, clinical, and laboratory parameters) were assessed.Results A total of 160 patients with confirmed MF were analyzed, including 126 CD4 + CD8 À MF (79%), 26 CD4 À CD8 + MF (16%), six CD4 + CD8 + MF (4%), and two CD4 À CD8 À MF (1%). Both groups were similar with respect to demographics and laboratory parameters at the time of diagnosis. There was no difference between patients with late stage disease (10% vs. 9%) for groups 1 and 2, respectively (P = 0.901). There was no statistically significant difference either in 5-year progression (27.7% vs. 23.5%, P = 0.283) or transformation (16.2% vs. 17.3%, P = 0.350) estimates. We did find that atypical immunophenotypes presented with different clinical morphologies and were less likely to require systemic therapy.Conclusion Our large cohort study indicates that atypical MF immunophenotypes do not seem to influence prognosis. Hypopigmented MF was more frequent in the CD4 À CD8 + group while folliculotropic MF was exclusively seen in the CD4 + CD8 À group. We believe that cases of CD8 + MF with aggressive behavior described in the literature represent misclassified primary cutaneous aggressive epidermotropic CD8 + T-cell lymphoma. The small number of patients included in the study is a limiting factor.