<< Back to the abstract archive
Developing A Microsurgery Literature Specific Artificial Intelligence Large Language Model With GPT-2: A Proof-of-Concept Study
Berk B. Ozmen, Graham Schwarz
Cleveland Clinic
2024-02-01
Presenter: Berk B. Ozmen
Affidavit:
Yes. All original work of the authors.
Director Name: Graham Schwarz
Author Category: Fellow Plastic Surgery
Presentation Category: Clinical
Abstract Category: General Reconstruction
BACKGROUND: Microsurgery literature demands innovative strategies to extract and synthesize relevant information for clinical use and education. Recently popular ChatGPT and artificial intelligence large language models, trained on extensive data, offer an innovative solution. In this proof-of-concept study, we aimed to develop a large language model specific to microsurgery, acting like a ChatGPT based on the current microsurgery literature.
METHODS: We developed a Python code to automate the collection of 1000 microsurgery related abstracts from PubMed. The abstracts were then preprocessed, tokenized, and formatted in Python and TensorFlow ecosystem into a structure suitable for model training. We employed the pre-trained GPT-2 model and fine-tuned on our dataset in a GPU-enabled environment, adjusting its parameters to better align with our microsurgery literature-specific data. We evaluated the performance of the resulting model based on its ability to generate coherent and contextually accurate text related to microsurgery when prompted.
RESULTS: The resulting model demonstrated promising proficiency in generating microsurgery related text, suggesting the successful integration of the microsurgery-specific knowledge from the fine-tuning process.
CONCLUSION: Our proof-of-concept study highlights the potential of large language models, like GPT-2, in microsurgery when fine-tuned with domain-specific literature. The Python code we developed offers innovative implementations of large language models and artificial intelligence in microsurgery. Future works can focus on the model's future potential in generating coherent hypotheses, summarizing literature, and explaining complex microsurgery concepts.
