Sign in Subscribe
Artificial intelligence

Artificial Intelligence in Plastic Surgery: A New Era for Clinical Decision Support

Strategic Insights

— 2 min read

Researchers from the Cleveland Clinic have published a new study on the application of Artificial Intelligence (AI) in plastic surgery, specifically in the development of a domain-specific Large Language Model (LLM) called PlasticSurgeryGPT. This study aims to improve performance in clinical decision support, surgical education, and research within the field of plastic surgery. The researchers fine-tuned the pre-trained GPT-2 model on a comprehensive dataset of 25,389 plastic surgery research abstracts published between 2010 and 2024.

Key Takeaways:

  • The study aims to develop and evaluate PlasticSurgeryGPT, a dedicated LLM fine-tuned on plastic surgery literature, to enhance performance in clinical decision support, surgical education, and research within the field.
  • The researchers used a comprehensive dataset of 25,389 plastic surgery research abstracts published between January 1, 2010, and January 1, 2024, retrieved from PubMed.
  • The pre-trained GPT-2 model was fine-tuned using the PyTorch and HuggingFace frameworks, and the performance of PlasticSurgeryGPT was evaluated against the default GPT-2 model using BLEU, METEOR, and ROUGE-1 metrics.
  • PlasticSurgeryGPT demonstrated substantial improvements over the generic GPT-2 model in capturing the semantic nuances of plastic surgery text, with scores of 0.135519, 0.583554, and 0.216813, respectively, compared with GPT-2's scores of 0.130179, 0.550498, and 0.215494.
  • The study concludes that PlasticSurgeryGPT represents the first plastic surgery-specific LLM, demonstrating enhanced performance in generating relevant and accurate content compared with a general-purpose model.
  • The research team emphasizes the potential of domain-specific LLMs in improving clinical practice, surgical education, and research in plastic surgery.
  • Future studies should focus on incorporating full-text articles, multimodal data, and larger models to further enhance performance and applicability.

Statistics:

  • The study used a dataset of 25,389 plastic surgery research abstracts.
  • The pre-trained GPT-2 model was fine-tuned using the PyTorch and HuggingFace frameworks.
  • PlasticSurgeryGPT demonstrated substantial improvements over the generic GPT-2 model in capturing the semantic nuances of plastic surgery text, with scores of 0.135519, 0.583554, and 0.216813, respectively.
  • The study concludes that PlasticSurgeryGPT represents the first plastic surgery-specific LLM, demonstrating enhanced performance in generating relevant and accurate content compared with a general-purpose model.

Sources:

  • Initial Proof-of-concept Study for a Plastic Surgery-specific Artificial Intelligence Large Language Model: Plasticsurgerygpt. Aesthetic Surgery Journal, 2025.
  • Oxford Univ Press Inc, Journals Dept, 2001 Evans Rd, Cary, NC 27513, USA.
  • Sage Publications - www.sagepub.com.
  • Aesthetic Surgery Journal - aes.sagepub.com
  • Graham S. Schwarz, Cleveland Clinic, Dept. of Plastic Surgery, Cleveland, OH, United States.

Read more