Search

Background: Vulvar lichen sclerosus (VLS) is a chronic inflammatory skin condition associated with significant impairment of quality of life and potential risk of malignant transformation. However, diagnosis of VLS is often delayed due to its variable clinical presentation and shame-related late consultation. Machine learning (ML)-trained image recognition software could potentially facilitate early diagnosis of VLS., Objective: To develop a ML-trained image-based model for the detection of VLS., Methods: Images of both VLS and non-VLS anogenital skin were collected, anonymized, and selected. In the VLS images, 10 typical skin signs (whitening, hyperkeratosis, purpura/ecchymosis, erosion/ulcers/excoriation, erythema, labial fusion, narrowing of the introitus, labia minora resorption, posterior commissure (fourchette) band formation and atrophic shiny skin) were manually labelled. A deep convolutional neural network was built using the training set as input data and then evaluated using the test set, where the developed algorithm was run three times and the results were then averaged., Results: A total of 684 VLS images and 403 non-VLS images (70% healthy vulva and 30% with other vulvar diseases) were included after the selection process. A deep learning algorithm was developed by training on 775 images (469 VLS and 306 non-VLS) and testing on 312 images (215 VLS and 97 non-VLS). This algorithm performed accurately in discriminating between VLS and non-VLS cases (including healthy individuals and non-VLS dermatoses), with mean values of 0.94, 0.99 and 0.95 for recall, precision and accuracy, respectively., Conclusion: This pilot project demonstrated that our image-based deep learning model can effectively discriminate between VLS and non-VLS skin, representing a promising tool for future use by clinicians and possibly patients. However, prospective studies are needed to validate the applicability and accuracy of our model in a real-world setting., (© 2024 European Academy of Dermatology and Venereology.)

Pruritus is a common symptom of cutaneous graft-versus-host disease (GVHD) following haematopoietic stem cell transplantation (HSCT). However, little is known about its prevalence, pathophysiology, perceptual characteristics, impact on quality of life and response to antipruritic therapies. The aim of this review was to determine the current knowledge on pruritus in cutaneous GVHD. The review was conducted according to the Preferred Reporting Items for Systematic Review and Meta-Analyses statement. Of the 338 studies screened, 13 were included. The prevalence of pruritus in cutaneous GVHD was reported in three studies, ranging from 37.0% to 63.8%. Only four trials used pruritus assessment tools. There was little or no information on the intensity of pruritus, its qualitative perception, the location of pruritus and the impact of pruritus on quality of life. Antipruritic treatments for GVHD-associated pruritus were mentioned in five studies (38.5%), including topical ointments (steroids, tacrolimus and calcipotriene), broadband UVB, systemic antihistamines and oral ursodeoxycholic acid. In conclusion, pruritus in cutaneous GVHD appears to be common, but very little is known about the pathophysiology, impact on quality of life and effective treatment options. Basic research and controlled clinical trials are warranted to improve knowledge and management of this important issue., (© 2023 European Academy of Dermatology and Venereology.)

Background: In the past two centuries, generations of dermatologists around the world have created an enormous number of publications. To our knowledge, no bibliometric analysis of these publications has been performed so far, nor have registered trials been analysed to anticipate future publication trends., Objectives: To determine the global distribution of national publication productivity, most published topics, institutions and funding sources contributing most to publications and to anticipate future trends based on registered clinical trials., Methods: Following pre-assessment on PubMed, Embase, Web of Science and Scopus, the number of publications for 'dermatology' was determined for each of 195 countries, normalized per 1 Mio inhabitants and bibliometrically analysed. Dermatology-related trials registered at clinicaltrials.gov were specified by the top-10 diagnoses for the top-10 countries., Results: The search yielded 1 071 518 publications between 1832 and 2019 with the top-5 diagnoses being melanoma, basal cell carcinoma, psoriasis, pruritus/itch and atopic dermatitis. The top-3 countries with highest absolute numbers of publications were the USA (30.6%), Germany (8.1%) and the UK (8.1%), whereas Switzerland, Denmark and Sweden had the highest publication rates when normalized by inhabitants. The most productive affiliation was the Harvard Medical School, the leading funding source the National Institutes of Health. Currently, maximum number of trials are registered in the USA (8111), France (1543) and Canada (1368). The highest percentage of all dermatology-related trials in a specific country were as follows: Melanoma in the Netherlands (24.8%), psoriasis in Germany (21.7%) and atopic dermatitis in Japan (15.9%)., Conclusion: The top-10 countries including the USA, Canada, a few European and Asian countries contributed more than 3/4 of all publications. The USA hold the dominant leader position both in past publication productivity and currently registered trials. While most Western countries continue to focus their research on the top-10 topics, China and India appear to prioritize their scope towards other topics., (© 2021 European Academy of Dermatology and Venereology.)