Development of a Bariatric Surgery Specific Artificial Intelligence Large Language Model: BariatricSurgeryGPT
Surgical Innovation · 2026
DOI: 10.1177/15533506251400130 ↗Kurz gefasst
Fachartikel in der Zeitschrift Surgical Innovation, 2026. Verfasst von Berk B Ozmen und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic Surgery, Cleveland Clinic, Cleveland, OH, USA. Hauptthemen laut MEDLINE: Bariatric Surgery, Artificial Intelligence. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 34 Literaturangaben.
Abstract (Originalsprache)
Background
Commercially available large language models (LLMs) have demonstrated impressive capabilities in processing vast datasets and generating coherent narratives. However, their lack of domain-specific knowledge limits their reliability in clinical applications. This study aimed to develop and evaluate BariatricSurgeryGPT, a fine-tuned LLM specifically tailored for bariatric surgery to provide more accurate and clinically relevant responses to bariatric surgery-related questions.
Methods
We obtained 8764 bariatric surgery research abstracts published between January 1, 2020, and January 1, 2024, from PubMed. These abstracts were preprocessed and tokenized to fine-tune a pre-trained GPT-2 model using PyTorch and HuggingFace frameworks. The model’s performance was evaluated using BLEU, METEOR, and ROUGE-1 scores on 20 clinically relevant bariatric surgery questions, each tested across nine temperature settings (0.1-0.9) for both the fine-tuned and baseline GPT-2 models, yielding 360 total evaluation instances.
Results
BariatricSurgeryGPT demonstrated consistent improvements over the baseline GPT-2 model across all metrics. The fine-tuned model achieved a BLEU score of 0.165 (vs 0.147 for baseline, 12.8% improvement), a METEOR score of 0.633 (vs 0.585, 8.2% improvement), and a ROUGE-1 score of 0.267 (vs 0.243, 9.7% improvement). These improvements indicate enhanced precision, recall, and semantic relevance in generating bariatric surgery-specific content.
Conclusion
BariatricSurgeryGPT represents the first domain-specific LLM for bariatric surgery and demonstrates the feasibility of developing specialty-specific AI tools with improved accuracy for clinical applications. The specialty-specific models could enhance surgical education through interactive learning tools, improve patient communication via personalized educational materials, and support clinical decision-making by providing evidence-based information synthesis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Plastic Surgery, Cleveland Clinic, Cleveland, OH, USA.
- Department of Computer and Data Sciences, Case School of Engineering, Case Western Reserve University, Cleveland, OH, USA.
- Digestive Disease Institute, Cleveland Clinic, Cleveland, OH, USA.
ORCID-Profile: Berk B Ozmen, Graham S Schwarz
Zitieren
APA
Ozmen, B. B., Berber, I., Dang, J. T., Schwarz, G. S., & Kroh, M. (2026). Development of a Bariatric Surgery Specific Artificial Intelligence Large Language Model: BariatricSurgeryGPT. Surgical Innovation. https://doi.org/10.1177/15533506251400130
Vancouver
Ozmen BB, Berber I, Dang JT, Schwarz GS, Kroh M. Development of a Bariatric Surgery Specific Artificial Intelligence Large Language Model: BariatricSurgeryGPT. Surgical Innovation. 2026. doi:10.1177/15533506251400130
BibTeX
@article{Ozmen2026,
author = {Ozmen, Berk B and Berber, Ibrahim and Dang, Jerry T and Schwarz, Graham S and Kroh, Matthew},
title = {Development of a Bariatric Surgery Specific Artificial Intelligence Large Language Model: BariatricSurgeryGPT},
journal = {Surgical Innovation},
year = {2026},
doi = {10.1177/15533506251400130}
}
EUVIMED