Lee Jungwook, Xu Xuanang, Kim Daeseung, Deng Hannah H, Kuang Tianshu, Lampen Nathan, Fang Xi, Gateno Jaime, Yan Pingkun
Department of Biomedical Engineering and Center for Biotechnology and Interdisciplinary Studies, Rensselaer Polytechnic Institute, Troy, NY 12180, USA.
Department of Oral and Maxillofacial Surgery, Houston Methodist Research Institute, Houston, TX, 77030, USA.
medRxiv. 2024 Jul 11:2024.07.11.24310274. doi: 10.1101/2024.07.11.24310274.
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.
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.
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.
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.
本研究探讨大语言模型（LLMs）在诊断颌骨畸形中的应用，旨在通过利用大语言模型的先进能力来克服各种诊断方法的局限性，以加强数据解读。目标是提供简化复杂数据分析的工具，使临床医生的诊断过程更易于操作且直观。
对患有颌骨畸形的患者进行了一项实验，将头影测量值（SNB角、面部角、下颌单位长度）转换为文本以供大语言模型分析。使用平衡准确率和F1分数，针对包括LLAMA-2变体、GPT模型和Gemini-Pro模型在内的多个大语言模型，与各种方法（基于阈值的方法、机器学习模型）进行了评估。
我们的研究表明，更大的大语言模型能够有效地适应诊断任务，在极少的训练示例下就能迅速达到性能饱和，并减少模糊分类，这突出了它们强大的上下文学习能力。将复杂的头影测量值转换为直观的文本格式，不仅拓宽了信息的可获取性，还增强了可解释性，为临床医生提供了清晰且可操作的见解。
将大语言模型整合到颌骨畸形诊断中标志着在使诊断过程更易于操作和减少对专业培训的依赖方面取得了重大进展。这些模型是有价值的辅助工具，提供清晰、易懂的输出，便于临床医生，特别是经验较少或在获取专业知识有限的环境中的临床医生做出更轻松的决策。预计未来通过改进和调整以纳入更全面和医学特定的数据集将提高大语言模型的精度和实用性，可能会改变医学诊断的格局。
