The application of large language models in bariatric surgery: A scoping review

Clinical Snapshot

Key Findings

• P Value: Not applicable for scoping review

• Effect Size: Not quantified - qualitative synthesis only

• Primary Outcome: LLMs showed good performance in patient education and information provision but poor consistency with expert opinions in complex clinical decision-making

• Nnt Or Sensitivity: GPT-4 demonstrated superior performance compared to other models, with domain-specific models showing professional potential

• Confidence Interval: Not applicable for scoping review

Clinical Application

Currently feasible for educational and informational support, but not ready for independent clinical decision-making Relevant to Australian bariatric surgery practice, particularly for patient education and training programs. TGA approval would be required for any clinical decision support applications Bariatric surgery patients, healthcare professionals, and trainees in metabolic surgery programs

Abstract

BACKGROUND: Exploratory applications of large language models within the specialized field of metabolic and bariatric surgery have begun to emerge. Nevertheless, existing research remains fragmented, lacking comprehensive integration. OBJECTIVE: To conduct a scoping review of studies on the application of large language models in the field of metabolic and bariatric surgery, aiming to provide a reference for clinical practice and future research. METHODS: This scoping review adhered to the Joanna Briggs Institute methodological framework and followed the preferred reporting items for systematic reviews and meta-Analyses extension for scoping reviews (PRISMA-ScR) guidelines.PubMed, Web of Science, The Cochrane Library, Embase, CINAHL, CNKI, Wanfang, and VIP databases were searched for relevant studies, with the search timeframe from database inception to November 2025. The included literature was summarized and analyzed. RESULTS: A total of 21 English-language studies were included. LLMs were primarily applied in scenarios such as patient education and information consultation, clinical decision support, and professional knowledge assessment. While LLMs performed well in information-provision tasks, they showed low consistency with expert opinions in complex clinical tasks such as individualized surgical recommendations. Performance varied across different models, with GPT-4 generally demonstrating superior performance, and domain-specific models showing professional potential. Current research still faces challenges regarding information accuracy, readability, and clinical applicability. CONCLUSION: Large language models hold auxiliary potential in the field of metabolic and bariatric surgery, particularly for knowledge dissemination and patient education. However, their reliability in complex clinical decision-making remains limited. Future efforts should focus on conducting high-quality studies, advancing model specialization and standardized evaluation, and exploring safe and effective human-AI collaboration models.

References

1. 1.Guo, N., Li, X., Li, X., Kang, C., Gong, X., Ji, X., & Zheng, J. (2026). The application of large language models in bariatric surgery: A scoping review. PLoS One. https://doi.org/10.14740/gr2011