相关实验视频
Updated: May 4, 2026

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
Published on: June 5, 2019
聊天-GPT在分拣:仍然远远超过人类的专业知识 - 一个观察性研究研究
Arian Zaboli1, Francesco Brigo1, Gloria Brigiari2
1Innovation, Research and Teaching Service (SABES-ASDAA), Teaching Hospital of the Paracelsus Medical Private University (PMU), Bolzano, Italy.
在急救部门的人类分类比使用ChatGPT 4.0.0的人工智能 (AI) 更可靠. 人工智能选对高风险患者的敏感性较低,可能导致选不足和结果较差.
科学领域:
- 紧急医疗 紧急医疗
- 医疗保健中的人工智能
- 临床决策支持 临床决策支持
背景情况:
- 紧急部门 (ED) 依靠分拣来优先考虑基于紧急情况的护理.
- 大型语言模型 (LLM) 正在探索用于分类,但它们与人类判断的有效性尚不清楚.
- 这项研究评估了ChatGPT 4.0在ED患者分组中的有效性.
研究的目的:
- 为了比较ChatGPT 4.0选与在ED环境中对人类选的有效性.
- 评估人工智能与人类分拣的一致性和预测准确性.
- 确定LLM是否可以可靠地识别高风险患者.
主要方法:
- 对2658例患者病例的回顾性分析.
- 由人类人员分配的分拣代码和ChatGPT 4.0.0 的比较
- 使用科恩的卡帕统计和ROC曲线的预测准确度评估协议.
主要成果:
- 对于所有结果,人类选显示出比人工智能选更好的预测准确度.
- 人类分组为30天死亡率 (0.88比0.70) 和救命干预 (0.98比0.87) 实现了更高的ROC值.
- 人工智能选显示,各种症状的敏感性和特异性较低,表明选不足的风险.
结论:
- 由于在识别高风险患者时敏感度较低,ChatGPT 4.0对ED分拣具有有限的实用性.
- 人类分类仍然是优先考虑紧急情况下患者护理的更可靠方法.
- 需要进一步的研究来提高人工智能的临床决策支持在重症监护环境.
更多相关视频
06:28E-Patient Counseling Trial E-PACO: Computer Based Education versus Nurse Counseling for Patients to Prepare for Colonoscopy
Published on: August 1, 2019
05:39Author Spotlight: A Non-Intubated Video-Assisted Thoracoscopic Surgery with Multimodal Analgesia and Sevoflurane Inhalation Anesthesia
Published on: May 26, 2023
相关概念视频
Case Studies
Naturalistic Observations
Group Polarization
Higher Mental Functions of the Brain: Language
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Extrasensory Perception
Precognition involves foreseeing future events, such as predicting an accident before it happens. An example of precognition could be someone dreaming about a specific event, like a car crash, which then occurs...