Improving Radiology Report Error Detection Using a Multipass Large Language Model: Framework Development and Validation

计算机科学 医学物理学 数据挖掘 放射科 医学影像学 医学 人工智能 软件 梅德林 人为错误 钥匙(锁) 专家系统 自动化方法 计算机断层摄影术
作者
Songsoo Kim,Seungtae Lee,See Young Lee,Joon-Ho Kim,Keechan Kan,Hyunji Lee,Dukyong Yoon
出处
期刊:JMIR medical informatics [JMIR Publications]
卷期号:14: e87368-e87368 被引量:2
标识
DOI:10.2196/87368
摘要

Background: Large language model (LLM) proofreaders for radiology reports generate many false positives (FPs) due to the low prevalence of errors. Objective: This study aimed to determine whether an optimized LLM framework could improve both precision and cost-efficiency without compromising error detection capability. Methods: In this retrospective study, 1000 radiology reports (radiography, ultrasonography, computed tomography, and magnetic resonance imaging; 250 each) were sampled from the Medical Information Mart for Intensive Care III database. Two public chest radiography corpora (CheXpert and Open-i) served as external test sets. Three LLM frameworks were evaluated: single-prompt detector (framework 1); report extractor plus single-prompt detector (framework 2); and extractor, detector, and FP verifier (framework 3). Precision for each framework was assessed using positive predictive value (PPV) and detected errors per 1000 reports. Overall efficiency was estimated using model inference costs and reviewer labor costs. Results: PPV increased from 0.063 (95% CI 0.036-0.101) in framework 1 to 0.079 (95% CI 0.049-0.118) in framework 2 and 0.159 (95% CI 0.090-0.252) in framework 3 (P<.001). Despite improved PPV, detected errors remained stable (detected errors per 1000 reports: 12-14). Human review burden decreased from 192 to 88 reports. Framework 3 also reduced model inference costs to US $5.57 per 1000 reports (vs US $9.72 and US $6.85 for frameworks 1 and 2; 42.6% and 18.5% reductions, respectively). External validation confirmed similar improvements. Qualitative analysis revealed that remaining FPs in framework 3 were largely confined to cases requiring deep clinical context (clinically equivalent rephrasing: 53%; unsupported discrepancy assertions: 43%). By eliminating structural FPs (eg, section mismatches and lexical errors: 0%), the framework effectively shifted the quality assurance burden to a smaller set of ambiguous cases, enabling a targeted human-in-the-loop workflow. Conclusions: The multipass LLM improved the precision and cost-efficiency of radiology report error detection in real-world, low-error prevalence settings. The framework demonstrates the feasibility of synergistic artificial intelligence-radiologist collaboration and provides a cost-effective and scalable approach to artificial intelligence-assisted quality assurance in both radiological practice and research.
最长约 10秒,即可获得该文献文件

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
852的应助被李仟亿采纳,获得10
刚刚
1秒前
小y同学发布了新的文献求助10
1秒前
1秒前
小劳完成签到,获得积分10
1秒前
我是谁的应助被master采纳,获得30
2秒前
Wei发布了新的文献求助10
2秒前
My_magnum_opus的应助被溧谦采纳,获得30
2秒前
2秒前
3秒前
搜集达人的应助被lalalall采纳,获得10
3秒前
xiaoXu发布了新的文献求助10
4秒前
Eana发布了新的文献求助10
4秒前
4秒前
酷酷的冷安完成签到,获得积分10
4秒前
kk子的应助被星星采纳,获得10
4秒前
CodeCraft的应助被FiiisH采纳,获得10
5秒前
mlw完成签到,获得积分10
5秒前
FashionBoy的应助被小方采纳,获得10
6秒前
妮妮发布了新的文献求助10
6秒前
无奈冬瓜完成签到,获得积分10
7秒前
8秒前
郑瑞欣完成签到 ,获得积分10
8秒前
一只眠羊发布了新的文献求助10
8秒前
科研通AI6.3的应助被笑笑采纳,获得10
8秒前
wkw发布了新的文献求助10
9秒前
bkagyin的应助被不想看文献采纳,获得10
10秒前
归途完成签到,获得积分10
13秒前
NexusExplorer的应助被zhangxinyi采纳,获得10
13秒前
周周发布了新的文献求助10
13秒前
科研通AI65的应助被ad采纳,获得10
13秒前
15秒前
Mickey完成签到 ,获得积分10
15秒前
abcd_1067完成签到,获得积分10
15秒前
不安的恶天完成签到,获得积分10
15秒前
顾矜的应助被小y同学采纳,获得10
15秒前
15秒前
minmin完成签到 ,获得积分10
16秒前
在水一方的应助被Eana采纳,获得10
17秒前
17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