Large Language Models in Radiology Reporting—A Systematic Review of Performance, Limitations, and Clinical Implications

作者
Yaara Artsi,Eyal Klang,Jeremy D. Collins,Benjamin Scott Glicksberg,Panagiotis D. Korfiatis,Girish N. Nadkarni,Vera Sorin
出处
期刊:medRxiv 被引量:12
标识
DOI:10.1101/2025.03.18.25324193
摘要

Abstract Background Large language models (LLMs) have emerged as potential tools for automated radiology reporting. However, concerns regarding their fidelity, reliability, and clinical applicability remain. This systematic review examines the current literature on LLM-generated radiology reports. Methods We conducted a systematic search of MEDLINE, Google Scholar, Scopus, and Web of Science to identify studies published between January 2015 and February 2025. Studies evaluating LLM-generated radiology reports were included. The study follows PRISMA guidelines. Risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Results Nine studies met the inclusion criteria. Of these, six evaluated full radiology reports, while three focused on impression generation. Six studies assessed base LLMs, and three evaluated fine-tuned models. Fine-tuned models demonstrated better alignment with expert evaluations and achieved higher performance on natural language processing metrics compared to base models. All LLMs showed hallucinations, misdiagnoses, and inconsistencies. Conclusion LLMs show promise in radiology reporting. However, limitations in diagnostic accuracy and hallucinations necessitate human oversight. Future research should focus on improving evaluation frameworks, incorporating diverse datasets, and prospectively validating AI-generated reports in clinical workflows.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Wei发布了新的文献求助10
刚刚
My_magnum_opus的应助被溧谦采纳,获得30
刚刚
刚刚
1秒前
搜集达人的应助被lalalall采纳,获得10
1秒前
xiaoXu发布了新的文献求助10
2秒前
Eana发布了新的文献求助10
2秒前
2秒前
酷酷的冷安完成签到,获得积分10
2秒前
kk子的应助被星星采纳,获得10
2秒前
CodeCraft的应助被FiiisH采纳,获得10
3秒前
mlw完成签到,获得积分10
3秒前
FashionBoy的应助被小方采纳,获得10
4秒前
妮妮发布了新的文献求助10
4秒前
无奈冬瓜完成签到,获得积分10
5秒前
6秒前
郑瑞欣完成签到 ,获得积分10
6秒前
一只眠羊发布了新的文献求助10
6秒前
科研通AI6.3的应助被笑笑采纳,获得10
6秒前
wkw发布了新的文献求助10
7秒前
bkagyin的应助被不想看文献采纳,获得10
8秒前
归途完成签到,获得积分10
11秒前
NexusExplorer的应助被zhangxinyi采纳,获得10
11秒前
周周发布了新的文献求助10
11秒前
科研通AI65的应助被ad采纳,获得10
11秒前
13秒前
Mickey完成签到 ,获得积分10
13秒前
abcd_1067完成签到,获得积分10
13秒前
不安的恶天完成签到,获得积分10
13秒前
顾矜的应助被小y同学采纳,获得10
13秒前
13秒前
minmin完成签到 ,获得积分10
14秒前
在水一方的应助被Eana采纳,获得10
15秒前
15秒前
15秒前
妮妮完成签到,获得积分10
15秒前
16秒前
大个的应助被科研通管家采纳,获得10
16秒前
Cr的应助被科研通管家采纳,获得10
16秒前
科研通AI2S的应助被临平吴彦祖采纳,获得10
16秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183601
求助须知:如何正确求助?哪些是违规求助? 9572875
关于积分的说明 21827816
捐赠科研通 7780716
什么是DOI,文献DOI怎么找? 3434031
关于科研通互助平台的介绍 2558197
邀请新用户注册赠送积分活动 2480485