从术语到清晰:通过人工智能大语言模型提高脚放射学报告的可读性
James J Butler1, Michael C Harrington2, Yixuan Tong1
1Foot and Ankle Division, Department of Orthopaedic Surgery, NYU Langone Health, 171 Delancey St, 2nd floor, New York City, USA.
概括
人工智能大语言模型 (AI-LLM) 显著提高了脚放射学报告的可读性. 由AI-LLM生成的X射线报告显示出优异的得分,提高了患者的理解能力.
科学领域:
- 放射学和医学成像学 医学成像学
- 医疗保健中的人工智能
- 医疗信息学 医疗信息学
背景情况:
- 放射学报告经常使用复杂的医学术语,阻碍了患者的理解.
- 改善放射学发现的可访问性对于患者参与和遵守治疗计划至关重要.
研究的目的:
- 评估人工智能大语言模型 (AI-LLM) 在提高脚骨科放射学报告的可读性方面的有效性.
- 为了比较不同成像方式的可读性改进:X射线,CT和MRI.
主要方法:
- 分析了300份放射学报告 (100张X射线,100张CT,100张MRI) 的数据集.
- 一个AI-LLM被要求用客户的术语为患者重新表述报告.
- 评估的关键指标包括报告长度,弗莱什阅读易度得分 (FRES),弗莱什-金凯德阅读水平 (FKRL),信息准确性 (利克特尺度) 和AI"幻觉".
主要成果:
- 在所有模式中,AI-LLM显著改善了FRES,并减少了FKRL (p < 0.001).
- 与CT和MRI报告相比,AI-LLM生成的X射线报告获得了优异的FRES和Likert分数.
- AI-LLM报告显示高准确度,幻觉率为4% (X射线),7% (CT) 和6% (MRI).
结论:
- AI-LLM是改善足放射学报告可读性的有效工具.
- 人工智能生成的X射线报告提供了最高的可读性和准确性,表明了以患者为中心的沟通的潜力.
- 这项技术代表了一种有前途的方法,可以提高患者对诊断成像结果的理解.
相关概念视频
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...