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.

No abstract

Experience in visceral cutaneous and cutaneous loxoscelism of hospital management: clinical, evolution and therapeutic proposal Background: Loxoscelism is a common pathology in our environment with a broad spectrum of differential diagnoses and presentations, with potentially serious complications, even to the point of death. To date, there is no standard treatment for these patients. Aim: To describe the clinical manifestations, main complications, therapeutic management, and evolution of loxoscelism in an inpatient setting from a tertiary hospital in Chile. Methods: All patients consulting and hospitalized in the hospital of the Pontificia Universidad Católica de Chile with diagnosis of loxoscelism between 2014 to 2017 and evaluated by dermatologist were included. Review of clinical files, including symptoms, images, laboratory parameters and treatment. Results: We evaluated seventeen inpatient with loxoscelism, whose presentation responds to the national epidemiological pattern. Most cases were managed with antibiotics, systemic corticosteroids, antihistamines, and dapsone. From these, 11.8% corresponded to viscerocutaneous loxoscelism, successfully managed with supportive measures, systemic corticosteroids and antihistamines. Fifty-nine percent healed their cutaneous lesions after one month of treatment, with slight residual scarring or post inflammatory hyperpigmentation, without associated mortality in our series. Discussion: Most cases of cutaneous loxoscelism presented excellent response and rapid resolution of the disease after combined therapy with systemic corticosteroids, antibiotics and dapsone, suggesting that the use of these therapies could stop the progression of cutaneous necrosis and prevent complications associated with loxoscelism.

Dermatopathologists should be aware of these effects in order to interpret carefully cutaneous biopsy specimens of patients receiving taxanes.

Background Primary cutaneous lymphomas (PCLs) and pseudolymphomas presenting as single pink-red nodules/tumors are highly unspecific and include a wide differential diagnosis.Objective To describe the dermoscopic characteristics of PCL/pseudolymphoma. MethodsIn this retrospective, case-control study, we evaluated the dermoscopic features of patients with solitary PCL/pseudolymphoma tumors and compared them to a control group of non-lymphomatous, nonpigmented, solitary tumors (e.g., basal cell carcinoma, amelanotic melanoma, etc). ResultsWe included 14 patients with PCL/pseudolymphomas and 35 controls. T-cell and B-cell lymphoma proportions were 28.6% (n = 4) and 71.4% (n = 10), respectively.Compared to controls, most lymphomas presented dermoscopically with orange color (71.4% vs. 14.2%, P < 0.001), follicular plugs (85% vs. 2.8%, P < 0.001), and as organized lesions (85% vs. 31.4%, P = 0.001). Coexistence of orange color and follicular plugs had an odds ratio (OR) of 2.8 (P < 0.001), highly suggestive of PCL. The kappa index for independent observers was 0.66, 0.49, 0.43 for orange background, follicular plugs, and organized lesion, respectively. Histopathologic correlation was performed in six PCL cases and showed dense diffuse and perifollicular lymphocytic infiltrate in all cases and keratin plugs in five of six cases, possibly correlating with the orange color and the follicular plugs, respectively.Conclusion Primary cutaneous lymphomas/pseudolymphomas present with characteristic dermoscopic findings irrespective of immunohistochemical subtype.