2024 | Pranvera Sulejmani, Olivia Negris, Valeria Aoki, Chia-Yu Chu, Lawrence Eichenfield, Laurent Misery, Ana Mosca, Raquel Leão Orfali, Markéta Saint Aroman, Jean-François Stalder, Magdalena Trzeciak, Andreas Wollenberg, Peter Lio
A letter to the editor discusses the use of large language models (LLMs), such as ChatGPT, in responding to patient queries about atopic dermatitis (AD). AD is a common chronic skin condition with significant global health impacts. Despite advances in treatment, patients often report poor quality of life and inadequate disease control. Effective patient education is crucial for treatment adherence and quality of life, but physicians face increasing workloads from patient inquiries. LLMs like ChatGPT can serve as a resource for patients and caregivers, offering responses that are often rated higher in quality and empathy than those from physicians. A study evaluated ChatGPT-4's responses to 99 common AD-related questions from 11 dermatologists. The responses were assessed by international dermatologists and scored on a Likert scale, with scores ranging from 8.18 to 10, indicating high satisfaction. Most responses acknowledged that ChatGPT is not a physician and directed users to healthcare providers. While no harmful information was found, some responses were incomplete or deviated from evidence-based medicine. The study suggests that LLMs can provide high-quality, reliable responses to patient questions without special training. Given the increasing demands on physicians, AI may become a valuable resource for patients. The authors note that knowledge about the quality of responses from different LLMs can help inform clinicians and patients. The study was supported by various pharmaceutical companies, and there are potential conflicts of interest. The authors declare that the research was conducted without commercial or financial relationships that could be construed as a potential conflict of interest. The data supporting the findings are available upon request.A letter to the editor discusses the use of large language models (LLMs), such as ChatGPT, in responding to patient queries about atopic dermatitis (AD). AD is a common chronic skin condition with significant global health impacts. Despite advances in treatment, patients often report poor quality of life and inadequate disease control. Effective patient education is crucial for treatment adherence and quality of life, but physicians face increasing workloads from patient inquiries. LLMs like ChatGPT can serve as a resource for patients and caregivers, offering responses that are often rated higher in quality and empathy than those from physicians. A study evaluated ChatGPT-4's responses to 99 common AD-related questions from 11 dermatologists. The responses were assessed by international dermatologists and scored on a Likert scale, with scores ranging from 8.18 to 10, indicating high satisfaction. Most responses acknowledged that ChatGPT is not a physician and directed users to healthcare providers. While no harmful information was found, some responses were incomplete or deviated from evidence-based medicine. The study suggests that LLMs can provide high-quality, reliable responses to patient questions without special training. Given the increasing demands on physicians, AI may become a valuable resource for patients. The authors note that knowledge about the quality of responses from different LLMs can help inform clinicians and patients. The study was supported by various pharmaceutical companies, and there are potential conflicts of interest. The authors declare that the research was conducted without commercial or financial relationships that could be construed as a potential conflict of interest. The data supporting the findings are available upon request.