PDF(Pubmed)
Abstract：
BACKGROUND: ChatGPT (Chat Generative Pre-trained Transformer), developed by OpenAI (San Francisco, CA, USA), has gained attention in the medical field. It has the potential to enhance and simplify tasks, such as preoperative planning in orthopedic surgery. We aimed to test ChatGPT\'s accuracy in measuring the angle of correction for high tibial osteotomy for cases planned and performed at a tertiary teaching hospital in Singapore.
METHODS: Peri-operative angular parameters from 114 consecutive patients who underwent medial opening wedge high tibial osteotomy (MOWHTO) were used to query ChatGPT 3.0. First ChatGPT 3.0 was queried on what information it required to plan a MOWHTO. Based on its response, pre-operative medial proximal tibial angle (MPTA) and joint line congruence angle (JLCA) were provided. ChatGPT 3.0 then responded with its recommended angle of correction. This was compared against the manually planned surgical correction by our fellowship-trained surgeon. A root mean square analysis was then performed to compare ChatGPT 3.0 and manual planning.
RESULTS: The root mean square error (RMSE) of ChatGPT 3.0 in predicting correction angle in MWHTO was 2.96, suggesting a very poor model fit.
CONCLUSIONS: Although ChatGPT 3.0 represents a significant breakthrough in large language models with extensive capabilities, it is not currently optimized to effectively perform complex pre-operative planning in orthopedic surgery, specifically in the context of MOWHTO. Further refinement and consideration of specific factors are necessary to enhance its accuracy and suitability for such applications.
METHODS: Peri-operative angular parameters from 114 consecutive patients who underwent medial opening wedge high tibial osteotomy (MOWHTO) were used to query ChatGPT 3.0. First ChatGPT 3.0 was queried on what information it required to plan a MOWHTO. Based on its response, pre-operative medial proximal tibial angle (MPTA) and joint line congruence angle (JLCA) were provided. ChatGPT 3.0 then responded with its recommended angle of correction. This was compared against the manually planned surgical correction by our fellowship-trained surgeon. A root mean square analysis was then performed to compare ChatGPT 3.0 and manual planning.
RESULTS: The root mean square error (RMSE) of ChatGPT 3.0 in predicting correction angle in MWHTO was 2.96, suggesting a very poor model fit.
CONCLUSIONS: Although ChatGPT 3.0 represents a significant breakthrough in large language models with extensive capabilities, it is not currently optimized to effectively perform complex pre-operative planning in orthopedic surgery, specifically in the context of MOWHTO. Further refinement and consideration of specific factors are necessary to enhance its accuracy and suitability for such applications.
摘要：
背景：ChatGPT（聊天生成预训练转换器），由OpenAI(旧金山，CA,美国),在医学领域受到关注。它有可能增强和简化任务，如骨科手术的术前规划。我们旨在测试ChatGPT测量在新加坡三级教学医院计划和实施的胫骨高位截骨术矫正角度的准确性。
方法：对114例接受胫骨内侧开口楔形高位截骨术（MOWHTO）的连续患者进行围手术期角度参数查询ChatGPT3.0。首先询问了ChatGPT3.0计划MOWTO所需的信息。根据它的反应，提供术前胫骨近端内侧角（MPTA）和关节线全等角（JLCA）。ChatGPT3.0随后以其推荐的校正角度做出了回应。将其与我们受过研究金训练的外科医生手动计划的手术矫正进行了比较。然后进行均方根分析以比较ChatGPT3.0和手动计划。
结果：ChatGPT3.0在预测MWHTO中的校正角时的均方根误差（RMSE）为2.96，表明模型拟合非常差。
结论：尽管ChatGPT3.0代表了具有广泛功能的大型语言模型的重大突破，目前还没有优化，可以有效地在骨科手术中执行复杂的术前计划，特别是在MOWHTO的背景下。需要进一步完善和考虑特定因素，以提高其准确性和对此类应用的适用性。
方法：对114例接受胫骨内侧开口楔形高位截骨术（MOWHTO）的连续患者进行围手术期角度参数查询ChatGPT3.0。首先询问了ChatGPT3.0计划MOWTO所需的信息。根据它的反应，提供术前胫骨近端内侧角（MPTA）和关节线全等角（JLCA）。ChatGPT3.0随后以其推荐的校正角度做出了回应。将其与我们受过研究金训练的外科医生手动计划的手术矫正进行了比较。然后进行均方根分析以比较ChatGPT3.0和手动计划。
结果：ChatGPT3.0在预测MWHTO中的校正角时的均方根误差（RMSE）为2.96，表明模型拟合非常差。
结论：尽管ChatGPT3.0代表了具有广泛功能的大型语言模型的重大突破，目前还没有优化，可以有效地在骨科手术中执行复杂的术前计划，特别是在MOWHTO的背景下。需要进一步完善和考虑特定因素，以提高其准确性和对此类应用的适用性。
