人工智能模型和医生在治疗静脉栓栓塞的患者教育中的比较:双盲随机对照试验
Ozgur Genc1, Omer Naci Tabakci2
1Department of Radiology, Istanbul Aydin University, VM Medical Park Florya Hospital, Istanbul, Türkiye.
Frontiers in radiology
|October 30, 2025
概括
人工智能 (AI) 模型,比如双子座,在教育患者关于静脉栓栓塞方面的表现优于医生,显示出卓越的学术准确性和同情心. 这表明,人工智能可以增强患者在干预放射学方面的教育.
科学领域:
- 医学成像和干预性放射学
- 医疗保健中的人工智能
- 患者教育和沟通
背景情况:
- 很少有研究将大型语言模型 (LLM) 与临床医生在患者信息传递方面进行比较.
- 评估人工智能性能对于开发混合信息系统至关重要.
- 静脉栓患者教育需要严格的评估.
研究的目的:
- 为了比较人工智能模型和临床专家在告知患者关于静脉栓塞的情况.
- 建立人工智能辅助患者教育的证据基础.
- 评估AI的学术准确性和同情的沟通.
主要方法:
- 预期的,双盲的,随机对照试验.
- 3个AI模型和1名干预放射科医生回答了关于静脉栓塞的25个常见问题.
- 两位独立的放射科医生对学术准确性和同理心的反应进行了评估,使用5分利克尔特尺度.
主要成果:
- 双子AI在学术准确度 (4.09) 和同理心 (3.54) 中获得了最高分.
- 包括Copilot和ChatGPT在内的AI模型在准确性和同情心方面通常比比较医生得分更高.
- 在学术准确性和同理心方面,在各组之间发现了统计学上显著的差异.
结论:
- 人工智能模型,特别是双子座,在学术准确性和同情性沟通方面表现出优异的表现,与医生相比.
- 人工智能具有显著的潜力,可以增强干预放射学的患者教育系统.
- 这些发现支持开发混合AI-临床医生患者教育模型.
相关概念视频
01:26Varicose Veins II: Diagnostic Studies and Interprofessional Care
178
Varicose veins, or varicosities, develop when the valves in the veins, which control blood flow, weaken or damage. It causes blood to pool and the veins to enlarge. Understanding the clinical manifestations, diagnostic approaches, and management options for varicose veins is crucial for effective treatment and relief.Clinical manifestationsClinical manifestations of varicose veins include a heavy, achy feeling or pain after prolonged standing or sitting. This discomfort can often be relieved by...
178
01:11Blinding
3.8K
Blinding is a commonly used method of not telling participants which treatment a subject is receiving. Blinding is a critical part of a randomized control trial or RCT. It reduces the bias that affects the results. In an RCT, blinding is used in the form of a placebo. A placebo effect occurs when untreated subjects falsely believe they have received the treatment and report improved symptoms. A placebo or a dummy treatment is administered to subjects to negate the bias caused by such an effect.
3.8K