尺寸并不重要:在医疗环境中评估大型语言模型的可靠性:专注于外周信息检索
Marina Del Barrio1, Kazim Laos2, María José Vilchez Lara3
1Hospital de Henares, Av. de Marie Curie, 0, Coslada, Madrid, 28822, Spain; Universidad Rey Juan Carlos, Av. de Atenas s/n, Alcorcon, Madrid, 28922, Spain.
Artificial intelligence in medicine
|February 19, 2026
概括
大型语言模型 (LLM) 显示出提供关于外周止痛的信息的潜力,但准确性各不相同. 医学协会必须合作,以确保可信的人工智能产生的健康内容.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 产科和妇科 产科和妇科
背景情况:
- 大型语言模型 (LLM) 提供了可访问的信息,但可以影响关键的健康决策,如外周止痛使用.
- 对专家的访问有限,知识缺口可能会导致个人使用不可靠的来源,包括人工智能.
- 确保人工智能生成的医疗信息的准确性对于防止错误信息至关重要.
研究的目的:
- 评估LLM产生的关于外周止痛的信息的可靠性和可信性.
- 为了比较各种LLM在提供准确的医疗信息方面的表现.
主要方法:
- 12名LLM被询问了10个关于外周止痛的标准化问题,每一个都被翻译成西班牙语和英语 (共2400个答案).
- 两位独立麻醉师使用扩展的SERVQUAL框架评估了反应.
- 性能指标包括准确性,可靠性和响应一致性.
主要成果:
- 聊天GPT表现最高,其次是双子座2.
- 像Phi-3这样的中型型号的表现优于较大的型号 (例如Llama-2),这表明尺寸并不总是表明质量.
- 英语回应通常比西班牙语更可靠,在一些西班牙语输出中出现了显著的不一致.
结论:
- 虽然LLM很有前途,但在医学应用方面存在局限性.
- 开发标准化,基于证据的资源对于培养LLM和提高人工智能生成的健康信息可信度至关重要.
- 建议医疗协会之间进行合作,以提高医疗保健中的AI可靠性.
相关概念视频
Local Anesthetics: Clinical Application as Epidural Anesthesia
817
Epidural anesthetics are administered in the fat-filled epidural space, the outermost part of the spinal canal. This technique is commonly employed for pain management and anesthesia during lower abdomen and pelvis surgeries or labor and delivery.
Since epidural anesthetics can be infused through an epidural catheter, all types of drugs, including short-acting ones, can be administered. Chloroprocaine and lidocaine are examples of short and long-duration anesthetics, respectively. Bupivacaine...
Since epidural anesthetics can be infused through an epidural catheter, all types of drugs, including short-acting ones, can be administered. Chloroprocaine and lidocaine are examples of short and long-duration anesthetics, respectively. Bupivacaine...
817
Local Anesthetics: Clinical Application as Spinal Anesthesia
1.6K
Spinal anesthetics are given during lower abdomen and limb surgeries to block sensory and motor neurons. They are administered in the mid to low lumbar regions, primarily acting on the cauda equina's nerve roots. The blockade level depends on the local anesthetic (LA) concentration. Usually, low LA concentrations are sufficient to block sensory fibers, while only high LA concentrations block motor fibers. Other factors like injection volume and speed, the patient's posture, and the drug...
1.6K

