RadCoT: a Radiological Chain-of-Thought framework for enhanced error detection in radiology reports

作者
Jia Li,Zichun Zhou,Yantao Niu,Pengfei Zhao,Yan Xu,Xinghao Wang,Lihua Wang,Lining Dong,Wei Wei,Xuan Wei,Zhenchang Wang,Han Lv
出处
期刊:European Radiology Experimental [Springer Science+Business Media]
卷期号:10 (1)
标识
DOI:10.1186/s41747-026-00804-0
摘要

BACKGROUND: Errors in radiology reports are a major patient-safety concern and are difficult to detect with manual quality assurance (QA). Large language models (LLMs) can assist, but generic prompting does not reflect radiologists' structured, section-based workflows. OBJECTIVE: To develop and evaluate RadCoT (Radiological Chain-of-Thought), a domain-specific prompting framework aligning LLM reasoning with radiological review workflows, and to assess whether it enables open-source models to approach commercial benchmarks for error detection. MATERIALS AND METHODS: In this retrospective study, 1,170 clinician-validated errors were extracted from a departmental QA repository (January 2021-December 2024), corresponding to 900 error-containing reports. An additional 300 error-free reports served as controls, yielding 1,200 reports balanced across radiography, ultrasound, CT, and MRI. Errors were categorized into five types by experienced radiologists. Seven LLMs were evaluated using standard prompting and the six-step RadCoT framework. Micro-averaged precision, recall, and F1 were computed at the error-instance level. Error type, modality-specific performance, and inference time were analyzed. RESULTS: RadCoT significantly improved the mean micro-averaged F1 across all models from 0.77 ± 0.06 (standard) to 0.85 ± 0.06 (RadCoT; p = 0.003). GPT-4o with RadCoT achieved the highest F1 (0.93). Llama-3.3-70B with RadCoT (F1 = 0.89) narrowed the gap with GPT-4o under standard prompting (F1 = 0.88; paired t-test, Holm-adjusted p = 0.28). Interpretation errors showed the largest gain, with F1 improving from 0.57 to 0.75. CONCLUSION: RadCoT consistently enhances LLM-based error detection, particularly for complex logic and consistency errors, closing the gap between open-source and commercial models and offering a pathway for privacy-preserving, on-premises QA. KEY POINTS: Question Manual review misses radiology report errors and remains difficult to scale. Findings Structured prompting improves detection of interpretation and section-consistency errors across seven models. Relevance statement Open-source models approach commercial performance for privacy-preserving on-premises radiology quality assurance.

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
1秒前
Mickey完成签到 ,获得积分10
1秒前
abcd_1067完成签到,获得积分10
1秒前
不安的恶天完成签到,获得积分10
1秒前
顾矜的应助被小y同学采纳,获得10
1秒前
1秒前
minmin完成签到 ,获得积分10
2秒前
在水一方的应助被Eana采纳,获得10
3秒前
3秒前
3秒前
妮妮完成签到,获得积分10
3秒前
4秒前
大个的应助被科研通管家采纳,获得10
4秒前
Cr的应助被科研通管家采纳,获得10
4秒前
科研通AI2S的应助被临平吴彦祖采纳,获得10
4秒前
CipherSage的应助被科研通管家采纳,获得10
4秒前
sendou的应助被科研通管家采纳,获得30
4秒前
Jasper的应助被科研通管家采纳,获得10
4秒前
5秒前
yn107发布了新的文献求助10
5秒前
顾矜的应助被科研通管家采纳,获得10
5秒前
科研菜菜的应助被科研通管家采纳,获得30
5秒前
Eric完成签到,获得积分10
5秒前
5秒前
wanci的应助被科研通管家采纳,获得10
5秒前
英俊的铭的应助被科研通管家采纳,获得10
5秒前
上官若男的应助被科研通管家采纳,获得10
5秒前
脑洞疼的应助被科研通管家采纳,获得10
6秒前
Akim的应助被科研通管家采纳,获得10
6秒前
所所的应助被科研通管家采纳,获得10
6秒前
6秒前
Jasper的应助被科研通管家采纳,获得10
6秒前
Cr的应助被科研通管家采纳,获得10
6秒前
思源的应助被科研通管家采纳,获得10
6秒前
Orange的应助被xyt采纳,获得10
6秒前
Cr的应助被科研通管家采纳,获得10
6秒前
无奈醉柳完成签到,获得积分10
7秒前
qian完成签到,获得积分10
7秒前
8秒前
小方发布了新的文献求助10
8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 8183508
求助须知:如何正确求助?哪些是违规求助? 9572862
关于积分的说明 21827639
捐赠科研通 7780681
什么是DOI,文献DOI怎么找? 3434016
关于科研通互助平台的介绍 2558189
邀请新用户注册赠送积分活动 2480405