在现实世界中部署和评估PEri-operativeAI CHatbot (PEACH):一个大型语言模型聊天机器人用于外科手术期间的医学
Yu He Ke1,2,3, Liyuan Jin4, Kabilan Elangovan4
1Department of Anaesthesiology, Singapore General Hospital, Singapore.
Anaesthesia
|September 19, 2025
概括
经手术前人工智能聊天机器人 (PEACH) 在经手术前决策中表现出高度准确性和可用性. 这种人工智能工具提高了临床的一致性和效率,在现实数据中观察到的偏差和幻觉最小.
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
- 大型语言模型
背景情况:
- 大型语言模型 (LLM) 对复杂的医疗保健任务有希望.
- 该PEri-operative AI CHatbot (PEACH) 是通过将35个外科手术协议集成到一个安全的LLM中来开发的.
- 代的快速工程和内部测试确保了临床相关性和准确性.
研究的目的:
- 开发和评估Peri-operative AI CHatbot (PEACH),用于外科手术期间的决策.
- 评估PEACH系统的准确性,安全性和可用性.
- 将PEACH的表现与机构指南和专家共识进行比较.
主要方法:
- 通过使用真实世界的临床数据进行静音部署来测试PEACH.
- 通过将PEACH响应与机构指南和专家共识进行比较来衡量准确性.
- 使用戴维斯技术接受模型收集用户反,并根据潜在的危害对偏差/幻觉进行分类.
主要成果:
- 更新的PEACH达到97.9%的准确性,明显优于95%的零假设 (p=0.018).
- 幻觉 (1/240) 和偏差 (2/240) 是最小的,表明高安全性.
- 临床医生报告说,PEACH在95%的病例中加速了决策,证明了高可用性和效率.
结论:
- PEACH是一个准确且可适应的AI工具,用于提高外科手术期间决策的一致性和效率.
- 人工智能聊天机器人展示了高的互评级可靠性,与经验丰富的医生相美.
- 未来的研究应侧重于跨医学专业的可扩展性和对临床结果的影响.
相关概念视频
Issues And Trends In Healthcare Delivery System
6.1K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
6.1K
Current Trends in Nursing II
3.3K
Trends in nursing are multifactorial and associated with changes in society, within the nursing profession, and in other professions. Notably, telehealth and remote nursing contribute to successful healthcare delivery for numerous patients and help reduce stress for nurses due to nursing shortages. Nurses can reach patients, monitor their conditions, and interact with them using computers, audio, visual accessories, and telephones—for example, remote patient monitoring systems. Likewise,...
3.3K


