ChatGPT in Dermatology: A Comprehensive Systematic Review

Background: In recent years, the field of dermatology has adopted the latest technologies to enhance patient care and medical education. Mobile technology and social media platforms have revolutionized the delivery of services, and AI-based procedures are poised to become part of dermatologists' daily routines. There are already numerous papers on the use of the latest conversational AI tool, ChatGPT, in dermatology, and a systematic analysis of these studies can yield valuable insights. Objective: To comprehensively evaluate the literature on the various applications of ChatGPT in dermatology and related areas. Methods: We searched PubMed, Cochrane Library, EuropePMC, medRxiv, arXiv, biorXiv, Dimensions AI, Semantic Scholar, and Google Scholar, to obtain articles published up until May 15, 2023. The eligibility criteria focused on studies examining the use of ChatGPT in dermatology-related areas. To address the risks of bias, we employed a meticulous selection process, incorporating diverse information sources, including preprints, in multiple languages. In addition to full-text articles, acknowledgments and supplemental material were also examined to ensure a thorough analysis. The synthesis of findings utilized network analysis and thematic synthesis methodologies. Results: There was a total of 87 manuscripts that fulfilled eligibility requirements. Over a third of them (36%) acknowledged the assistance of ChatGPT in writing, data analysis or software development. About a quarter (24%) were case reports describing dermatological manifestations and complications. ChatGPT demonstrated successful performance answering questions related to dermatology, ranging from excellent in cancer to barely passable in specialized and lesser-known dermatology areas, although its performance improved with GPT 4. There are advancements in interactive learning, integrations with image-based AI, and enhancing language models for dermatology applications. Conclusions: There has been a remarkable surge in the adoption of ChatGPT in areas related to dermatology, especially in writing case reports. As researchers are aware of safety and uncertainty, a continued feedback loop for reporting errors is crucial for the ongoing improvement and training of AI models, ensuring their reliability and effectiveness in the field. ### Competing Interest Statement The authors have declared no competing interest. ### Clinical Protocols ### Funding Statement This study did not receive any funding ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Data produced in the present work are contained in the manuscript (Appendix 1). Additional data are available upon reasonable request to the author.