ChatGPT in Dermatology: A Comprehensive Systematic Review

Abstract

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.

Artificial Intelligence in Biomedicine: Systematic Review

“…Notably, all of these papers either explicitly addressed the impacts of ChatGPT in medicine. Of the remaining 12 reviews, the majority (7 reviews, [9][10][11][12][13][14][15]) explored the general healthcare field, with the rest being related to medical education (1 review, [16]) or specialized medical areas such as dentistry [17,18], obstetrics and gynecology [19], dermatology [20], or public health [17] the term 'artificial intelligence' in their titles, 'nr' signifies the number of reviews, '2023' in subscript refers to papers published in 2023, and 'bh' in subscript denotes the number of papers specifically filtered from the biomedical and health fields. In this AI review, multiple subsets of articles were selected for VOSviewer analysis and visua lizati on, with their coun ts rangi ng from sever al thousand to tens of thousands.…”

“…The key findings of this systematic review underscore ChatGPT's substantial potential in transforming the medical landscape. Despite the existing constraints cand limitations, this AI tool has demonstrated successful application in areas such as authoring case reports from electronic health records [20], conducting systematic reviews [14,20,21], generating search queries, analyzing abstracts and full texts, and effectively classifying and labeling information. It also showed potential in fostering awareness and combating misinformation.…”

“…Particularly within community-based studies, unconstrained by large pharmaceutical funding or traditional academic boundaries [27], the use of AI tools like ChatGPT can offer considerable benefits. This systematic review analyzed 12 systematic reviews focusing on the application of ChatGPT in biomedical, clinical, and health-related fields [9][10][11][12][13][14][15][16][17][18][19][20]. Notably, half of these reviews referenced COVID-19 in some capacity: two included COVID-19 in discussion, while another three indirectly examined ChatGPT papers related to the pandemic.…”

“…A case report mentioned in review [20] detailed how ChatGPT was utilized to process information about a patient recently immunized with the COVID-19 vaccine. ChatGPT accurately assessed the patient's skin condition, which was warm, dry, and free of rashes or erythema, and successfully ruled out dermatological and autoimmune causes for the reported symptoms of epigastric pain and heartburn.…”

Evaluating the Diagnostic and Treatment Recommendation Capabilities of GPT-4 Vision in Dermatology

“…Recent literature underscores the strides made with GPT models in dermatology 4,5 . Kluger highlighted the potential applications of ChatGPT in dermatology, especially in accurate disease identification and differential diagnosis 5 .…”