RESUMO
Background: Stevens-Johnson syndrome (SJS) and toxic epidermal necrolysis (TEN) are rare, life-threatening immunologic reactions. Prior studies using electronic health records, registries or reporting databases are often limited in sample size or lack clinical details. We reviewed diverse detailed case reports published over four decades. Methods: Stevens-Johnson syndrome and toxic epidermal necrolysis-related case reports were identified from the MEDLINE database between 1980 and 2020. Each report was classified by severity (i.e., SJS, TEN, or SJS-TEN overlap) after being considered a "probable" or "definite" SJS/TEN case. The demographics, preconditions, culprit agents, clinical course, and mortality of the cases were analyzed across the disease severity. Results: Among 1,059 "probable" or "definite" cases, there were 381 (36.0%) SJS, 602 (56.8%) TEN, and 76 (7.2%) SJS-TEN overlap cases, with a mortality rate of 6.3%, 24.4%, and 21.1%, respectively. Over one-third of cases had immunocompromised conditions preceding onset, including cancer (n = 194,18.3%), autoimmune diseases (n = 97, 9.2%), and human immunodeficiency virus (HIV) (n = 52, 4.9%). During the acute phase of the reaction, 843 (79.5%) cases reported mucous membrane involvement and 210 (19.8%) involved visceral organs. Most cases were drug-induced (n = 957, 90.3%). A total of 379 drug culprits were reported; the most frequently reported drug were antibiotics (n = 285, 26.9%), followed by anticonvulsants (n = 196, 18.5%), analgesics/anesthetics (n = 126, 11.9%), and antineoplastics (n = 120, 11.3%). 127 (12.0%) cases reported non-drug culprits, including infections (n = 68, 6.4%), of which 44 were associated with a mycoplasma pneumoniae infection and radiotherapy (n = 27, 2.5%). Conclusion: An expansive list of potential causative agents were identified from a large set of literature-reported SJS/TEN cases, which warrant future investigation to understand risk factors and clinical manifestations of SJS/TEN in different populations.
RESUMO
INTRODUCTION: Melanoma is the most aggressive type of skin cancer, and it may arise from a cutaneous pigmented lesion. As artificial intelligence (AI)-based teledermatology services hold promise in redefining the melanoma screening paradigm, a study that evaluates user satisfaction with a smartphone-compatible, AI-based cutaneous pigmented lesion evaluator is lacking. METHODS: Data was collected between April and May 2019 in Taiwan. To assess user satisfaction with MoleMe, an AI-based cutaneous pigmented lesion evaluator on a smartphone, users were asked to complete a questionnaire designed to evaluate four aspects, including interaction, impact on daily life, usability, and overall performance, after completing a MoleMe evaluation session. For each question, users could rank their satisfaction level from 1 to 5, with five showing strongly satisfied and one showing strongly unsatisfied. The Kruskal-Wallis and Wilcoxon rank-sum tests were used to compare user satisfaction among different age groups, genders, and risk predictions received. RESULT: A total of 1231 questionnaires were collected for analysis. Over 90% of the participants were satisfied (score = 4 or 5) and over 75% of the participants were strongly satisfied (score 5) with MoleMe, in terms of usability, interaction, and impact on daily life. The user satisfaction did not show a significant difference between genders, age groups, and risk predictions received. (all P > 0.05) CONCLUSION: With high user satisfaction regardless of age group, gender, and risk prediction received, AI-based teledermatology services on a smartphone such as MoleMe may potentially achieve widespread usage and be beneficial to both patients and physicians.