Yao Michael S, Chae Allison, Saraiya Piya, Kahn Charles E, Witschey Walter R, Gee James C, Sagreiya Hersh, Bastani Osbert
Department of Bioengineering, University of Pennsylvania, Philadelphia, PA, USA.
Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
Commun Med (Lond). 2025 Aug 4;5(1):332. doi: 10.1038/s43856-025-01061-9.
Diagnostic imaging studies are increasingly important in the management of acutely presenting patients. However, ordering appropriate imaging studies in the emergency department is a challenging task with a high degree of variability among healthcare providers. To address this issue, recent work has investigated whether generative AI and large language models can be leveraged to recommend diagnostic imaging studies in accordance with evidence-based medical guidelines. However, it remains challenging to ensure that these tools can provide recommendations that correctly align with medical guidelines, especially given the limited diagnostic information available in acute care settings.
In this study, we introduce a framework to intelligently leverage language models by recommending imaging studies for patient cases that align with the American College of Radiology's Appropriateness Criteria, a set of evidence-based guidelines. To power our experiments, we introduce RadCases, a dataset of over 1500 annotated case summaries reflecting common patient presentations, and apply our framework to enable state-of-the-art language models to reason about appropriate imaging choices.
Using our framework, state-of-the-art language models achieve accuracy comparable to clinicians in ordering imaging studies. Furthermore, we demonstrate that our language model-based pipeline can be used as an intelligent assistant by clinicians to support image ordering workflows and improve the accuracy of acute image ordering according to the American College of Radiology's Appropriateness Criteria.
Our work demonstrates and validates a strategy to leverage AI-based software to improve trustworthy clinical decision-making in alignment with expert evidence-based guidelines.
诊断成像研究在急性病患者的管理中日益重要。然而，在急诊科安排合适的成像检查是一项具有挑战性的任务，医疗服务提供者之间的差异很大。为解决这一问题，最近的研究探讨了是否可以利用生成式人工智能和大语言模型，根据循证医学指南推荐诊断成像检查。然而，要确保这些工具能够提供与医学指南正确相符的建议仍然具有挑战性，尤其是考虑到急性护理环境中可用的诊断信息有限。
在本研究中，我们引入了一个框架，通过为符合美国放射学会适用性标准（一套循证指南）的患者病例推荐成像检查，来智能利用语言模型。为支持我们的实验，我们引入了RadCases，这是一个包含1500多个带注释病例摘要的数据集，反映了常见的患者表现，并应用我们的框架使先进的语言模型能够推断出合适的成像选择。
使用我们的框架，先进的语言模型在安排成像检查方面达到了与临床医生相当的准确率。此外，我们证明基于语言模型的流程可以被临床医生用作智能助手，以支持图像安排工作流程，并根据美国放射学会的适用性标准提高急性图像安排的准确性。
我们的工作展示并验证了一种策略，即利用基于人工智能的软件，根据专家循证指南改进可靠的临床决策。
