Harnessing Large Language Models for Radiology Report Simplification and Improving Patient Comprehension: A Narrative Review.
Authors
Affiliations (5)
Affiliations (5)
- Division of Interventional Radiology and Image-Guided Medicine, Department of Radiology and Imaging Science, Emory University School of Medicine, Atlanta, Georgia (S.U.N., H.L., J.T.M., E.P., Z.L.B., J.N., J.W.G.); Division of Vascular and Interventional Radiology, Department of Radiology, University of Florida College of Medicine, Gainesville, FL (S.U.N.).
- Division of Interventional Radiology and Image-Guided Medicine, Department of Radiology and Imaging Science, Emory University School of Medicine, Atlanta, Georgia (S.U.N., H.L., J.T.M., E.P., Z.L.B., J.N., J.W.G.). Electronic address: [email protected].
- Division of Interventional Radiology and Image-Guided Medicine, Department of Radiology and Imaging Science, Emory University School of Medicine, Atlanta, Georgia (S.U.N., H.L., J.T.M., E.P., Z.L.B., J.N., J.W.G.).
- Emory College of Arts & Sciences, Emory University, Atlanta, Georgia (R.K.).
- Division of Emergency and Trauma Imaging, Emory University School of Medicine, Atlanta, Georgia (H.T.).
Abstract
Radiological reports are essential clinical documents often written in highly technical language that is challenging for patients to comprehend. Despite advancements in digital imaging and reporting technologies, the inherent complexity of radiology reports creates significant barriers to effective patient understanding. Recently, large language models (LLMs) have emerged as a promising solution to simplify radiological reports. Therefore, this narrative review aims to provide a comprehensive overview of LLMs for simplifying patient-centered radiology reports. We examined 19 studies evaluating various LLMs including GPT-3.5, GPT-4, Claude, Gemini, and others across multiple imaging modalities. All studies reported descriptive/consistent improvements in readability metrics, with simplified reports typically achieving 5th-8th grade reading levels compared to the original 10th-14th grade levels. However, many studies identified accuracy concerns, with reports containing a range of omissions, commissions, and distortions depending on modality and model. Building upon these findings, we discuss medicolegal considerations, workflow integration challenges, and strategies for effective LLM implementation. We also explore potential impacts on radiologist workflow, including the impact of LLM biases and liability for simplified reports. Despite promising results, significant challenges remain in ensuring accurate simplification across diverse patient populations while maintaining clinical precision. In conclusion, this review underscores the transformative potential of LLMs in enhancing patient understanding of radiological findings while highlighting the need for careful implementation with appropriate oversight mechanisms.