Large Language Models Diagnose Facial Deformity.

Autor:	Lee J; Department of Biomedical Engineering and Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY 12180, USA., Xu X; Department of Biomedical Engineering and Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY 12180, USA., Kim D; Department of Oral and Maxillofacial Surgery, Houston Methodist Research Institute, Houston, TX, 77030, USA., Deng HH; Department of Oral and Maxillofacial Surgery, Houston Methodist Research Institute, Houston, TX, 77030, USA., Kuang T; Department of Oral and Maxillofacial Surgery, Houston Methodist Research Institute, Houston, TX, 77030, USA., Lampen N; Department of Biomedical Engineering and Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY 12180, USA., Fang X; Department of Biomedical Engineering and Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY 12180, USA., Gateno J; Department of Oral and Maxillofacial Surgery, Houston Methodist Research Institute, Houston, TX, 77030, USA.; Department of Surgery (Oral and Maxillofacial Surgery), Weill Medical College, Cornell University, New York, NY, 10021, USA., Yan P; Department of Biomedical Engineering and Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY 12180, USA.
Jazyk:	angličtina
Zdroj:	MedRxiv : the preprint server for health sciences [medRxiv] 2024 Jul 11. Date of Electronic Publication: 2024 Jul 11.
DOI:	10.1101/2024.07.11.24310274
Abstrakt:	Purpose: This study examines the application of Large Language Models (LLMs) in diagnosing jaw deformities, aiming to overcome the limitations of various diagnostic methods by harnessing the advanced capabilities of LLMs for enhanced data interpretation. The goal is to provide tools that simplify complex data analysis and make diagnostic processes more accessible and intuitive for clinical practitioners. Methods: An experiment involving patients with jaw deformities was conducted, where cephalometric measurements (SNB Angle, Facial Angle, Mandibular Unit Length) were converted into text for LLM analysis. Multiple LLMs, including LLAMA-2 variants, GPT models, and the Gemini-Pro model, were evaluated against various methods (Threshold-based, Machine Learning Models) using balanced accuracy and F1-score. Results: Our research demonstrates that larger LLMs efficiently adapt to diagnostic tasks, showing rapid performance saturation with minimal training examples and reducing ambiguous classification, which highlights their robust in-context learning abilities. The conversion of complex cephalometric measurements into intuitive text formats not only broadens the accessibility of the information but also enhances the interpretability, providing clinicians with clear and actionable insights. Conclusion: Integrating LLMs into the diagnosis of jaw deformities marks a significant advancement in making diagnostic processes more accessible and reducing reliance on specialized training. These models serve as valuable auxiliary tools, offering clear, understandable outputs that facilitate easier decision-making for clinicians, particularly those with less experience or in settings with limited access to specialized expertise. Future refinements and adaptations to include more comprehensive and medically specific datasets are expected to enhance the precision and utility of LLMs, potentially transforming the landscape of medical diagnostics. Competing Interests: Competing Interests The authors do not have other means of conflict of interest.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu