聊天GPT和双子座的建议是否与手和上肢手术的既定指南相一致?
Yibin B Zhang1, Fielding S Fischer1, Matthew V Abola2
1Harvard Medical School, Boston, MA, USA.
概括
像ChatGPT和Gemini这样的大型语言模型 (LLM) 显示了骨科指南的中等临床准确性. 这两种LLM在透明度和一致性方面都有局限性,在临床广泛采用之前需要进一步评估.
科学领域:
- 人工智能在医学中的应用
- 临床决策支持系统 临床决策支持系统
- 医疗保健信息学 医疗保健信息学
背景情况:
- 大型语言模型 (LLM) 在医疗保健中越来越多地用于管理任务和患者沟通.
- 人们对医学实践中LLM建议的临床准确性和可靠性存在担忧.
- 本研究调查了LLM输出对已建立的临床实践指南 (CPG) 的遵守情况.
研究的目的:
- 评估ChatGPT和Gemini的建议与美国骨科外科医生学会 (AAOS) 临床实践指南 (CPG) 的一致性.
- 为了比较ChatGPT和Gemini在不同骨科条件的准确性和引用透明度方面的表现.
主要方法:
- 聊天GPT (版本 4o) 和双子座 (版本 1.5 闪光) 被提示与AAOS CPGs对齐的文字,用于手腕道综合征,远端半径骨折和关节关节骨关节炎.
- 盲目审查员评估了LLM输出与CPG的一致性.
- 模型,主题和指南优势之间的一致率进行了比较,并评估了引用透明度.
主要成果:
- 在174个建议中观察到62.1%的总体一致率.
- 在ChatGPT (66.7%) 和Gemini (57.5%) (P = .131) 之间没有发现统计学上显著的一致差异.
- 两种模型都表现出较低的引用透明度,Gemini提供来源的频率 (39.1%) 比ChatGPT (3.5%) (P < .0001) 更多.
结论:
- 目前的LLM与AAOS CPG相对适度一致,这表明临床整合存在重大局限性.
- 跨主题和指南优势表现的变化,加上引用透明度差,需要进一步改进.
- 在采用手术和其他临床专业的LLM之前,彻底评估和改进至关重要.
更多相关视频
09:14Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction
Published on: September 28, 2019
12.1K
07:59Therapy Interventions for Upper Limb Amputees Undergoing Selective Nerve Transfers
Published on: October 29, 2021
4.1K
相关概念视频
Pre-Procedural Guidelines for Assessing Blood Pressure
817
Accurate blood pressure assessment is crucial for diagnosing and managing various health conditions. To ensure the reliability of these measurements, healthcare professionals must adhere to standardized pre-procedural guidelines. These guidelines enhance patient safety and improve the overall quality of healthcare. The following steps are essential for obtaining accurate and consistent blood pressure readings, from using the appropriate tools to ensuring effective communication with the...
817
Peripheral Artery Disease V: Postoperative Nursing Management
378
During the postoperative period, it is crucial to focus on maintaining circulation, identifying and managing potential complications, and planning for discharge.Nursing AssessmentVital signs monitoring: Regularly monitor vital signs, including blood pressure, heart rate, respiratory rate, and temperature, to detect early signs of complications such as bleeding and infection.Circulation assessment: Monitor pulses, perform Doppler assessments, and check capillary refill, color, temperature, and...
378
