探索多语言大语言模型以增强肺癌分期中放射学报告的TNM分类
Exploring Multilingual Large Language Models for Enhanced TNM classification of Radiology Report in lung cancer staging
AI总结：
本研究探究GPT3.5-turbo基于放射学报告进行肺癌TNM分类的准确性及多语言效用，发现提供完整TNM定义可显著提升准确率，英语报告表现优于日语，验证了大语言模型在放射学场景的应用潜力。
摘要：
研究背景：由于结构化工作耗时费力且报告多为叙述式风格，结构化放射学报告的发展仍较为滞后。深度学习，尤其是GPT-3.5这类大语言模型（LLM），为自然语言放射学报告的自动化结构化提供了可行前景。然而，尽管已有研究指出LLM在非英语语言中的效果较差，但其在放射学领域的表现尚未得到广泛研究。研究目的：本研究旨在探究基于放射学报告使用GPT3.5-turbo（GPT3.5）进行TNM分类的准确性，以及多语言LLM在日语和英语中的应用效用。材料与方法：我们利用GPT3.5开发了一套系统，可从肺癌胸部CT报告中自动生成TNM分类并评估其性能。我们使用广义线性混合模型，统计分析了在两种语言下提供完整或部分TNM定义带来的影响。研究结果：当提供完整TNM定义且放射学报告为英语时，模型达到最高准确率（M分期=94%，N分期=80%，T分期=47%，全部分类准确率=36%）。为T、N、M各分期因子提供定义均能统计显著地提升对应分期的准确率（T分期：比值比（OR）=2.35，p<0.001；N分期：OR=1.94，p<0.01；M分期：OR=2.50，p<0.001）。日语报告的N分期和M分期准确率有所下降（N分期准确率：OR=0.74，M分期准确率：OR=0.21）。研究结论：本研究凸显了多语言LLM用于放射学报告自动TNM分类的潜力。即便无需额外模型训练，提供TNM定义即可明显提升性能，表明LLM在放射学场景中具有应用价值。
英文摘要：
Background: Structured radiology reports remains underdeveloped due to labor-intensive structuring and narrative-style reporting. Deep learning, particularly large language models (LLMs) like GPT-3.5, offers promise in automating the structuring of radiology reports in natural languages. However, although it has been reported that LLMs are less effective in languages other than English, their radiological performance has not been extensively studied. Purpose: This study aimed to investigate the accuracy of TNM classification based on radiology reports using GPT3.5-turbo (GPT3.5) and the utility of multilingual LLMs in both Japanese and English. Material and Methods: Utilizing GPT3.5, we developed a system to automatically generate TNM classifications from chest CT reports for lung cancer and evaluate its performance. We statistically analyzed the impact of providing full or partial TNM definitions in both languages using a Generalized Linear Mixed Model. Results: Highest accuracy was attained with full TNM definitions and radiology reports in English (M = 94%, N = 80%, T = 47%, and ALL = 36%). Providing definitions for each of the T, N, and M factors statistically improved their respective accuracies (T: odds ratio (OR) = 2.35, p < 0.001; N: OR = 1.94, p < 0.01; M: OR = 2.50, p < 0.001). Japanese reports exhibited decreased N and M accuracies (N accuracy: OR = 0.74 and M accuracy: OR = 0.21). Conclusion: This study underscores the potential of multilingual LLMs for automatic TNM classification in radiology reports. Even without additional model training, performance improvements were evident with the provided TNM definitions, indicating LLMs' relevance in radiology contexts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
