Error Detection and Correction in Chinese Radiology Reports Using Large Language Models: Real-World Clinical Validation Study

医学 医学物理学 病历 模式 集合(抽象数据类型) 考试(生物学) 数据集 医学影像学 放射科 模态(人机交互) 梅德林 计算机科学 人工智能 回顾性队列研究 医疗保健 试验装置 错误检测和纠正 标准化 病人护理 阅读(过程) 临床实习 数据挖掘
作者
Jiafeng Zhou,YuXin Wei,Qian Cai,Bin Chen,Eugene Edzeafene-Mensah,Yunjun Yang,Zhifang Pan
出处
期刊:Journal of Medical Internet Research [JMIR Publications]
卷期号:28: e94689-e94689
标识
DOI:10.2196/94689
摘要

Abstract Background Large language models (LLMs) show promise in automatically detecting errors in radiology reports, but their performance remains insufficiently validated in large-scale, real-world clinical datasets. Objective This study aimed to systematically evaluate the performance of LLMs in detecting and correcting errors in Chinese radiology reports derived from authentic clinical data. Methods A large-scale dataset of 4480 Chinese radiology reports with modification records containing real clinical practice-generated errors was retrospectively collected between January 2023 and June 2024 at a single institution. After exclusions, 1363 reports containing 1551 errors were included. The dataset covers various anatomical parts of the body from different imaging modalities and was randomly divided into a test set (n=1263) and an internal validation set (n=100). Additionally, 100 error-free reports were added to the internal validation set. An additional 200 English-language reports from the Medical Information Mart for Intensive Care (MIMIC-III) were used for external validation. Eight human readers and 8 widely adopted LLMs, enhanced by prompt engineering, were tasked with error detection. Overall and subgroup detection performance and reading time were evaluated. Correction suggestions from the 2 best-performing LLMs were reviewed by a senior radiologist. Results On the test set, DeepSeek-R1 achieved the highest overall detection rate at 89% (95% CI 87%-90%), significantly better than the other 7 models ( P =.001-.007). On the internal validation set, DeepSeek-R1 and Claude-3.5-Sonnet achieved detection rates of 83% (100/120; 95% CI 76%-89%) and 80% (96/120; 95% CI 72%-86%), respectively. DeepSeek-R1 showed performance comparable to radiologists (83%, 95% CI 76%-89% vs 80%, 95% CI 72%-86% for junior radiologists and 78%, 95% CI 70%-85% for senior radiologists; P =.39 and P =.19, respectively) and significantly better performance than that of nonradiologists and nonphysicians (83%, 95% CI 76%-89% vs 66%, 95% CI 57%-74% and 38%, 95% CI 30%-47%; P <.001, respectively). DeepSeek-R1 showed a false-positive rate comparable to radiologists (DeepSeek-R1 vs senior radiologists and junior radiologists, 3% vs 0% and 1%; P =.25 and P =.61, respectively) and a significantly lower rate than nonradiologists and nonphysicians (3% vs 13% and 17%; P =.02 and P =.002, respectively). On the external validation set, DeepSeek-R1 and Claude-3.5-Sonnet achieved detection rates of 94% (95% CI 89%-97%) and 93% (95% CI 88%-97%), respectively. The correction accuracy of DeepSeek-R1 and Claude-3.5-Sonnet was 95% and 91%, respectively. Conclusions Enhanced LLMs, particularly DeepSeek-R1, demonstrated robust performance in error detection and correction within real-world Chinese radiology reports, supporting their clinical use for automated quality assurance and integration into workflows to improve reporting accuracy and efficiency.
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
科研通AI65的应助被ad采纳,获得10
刚刚
2秒前
Mickey完成签到 ,获得积分10
2秒前
abcd_1067完成签到,获得积分10
2秒前
不安的恶天完成签到,获得积分10
2秒前
顾矜的应助被小y同学采纳,获得10
2秒前
2秒前
minmin完成签到 ,获得积分10
3秒前
在水一方的应助被Eana采纳,获得10
4秒前
4秒前
4秒前
妮妮完成签到,获得积分10
4秒前
5秒前
大个的应助被科研通管家采纳,获得10
5秒前
Cr的应助被科研通管家采纳,获得10
5秒前
科研通AI2S的应助被临平吴彦祖采纳,获得10
5秒前
CipherSage的应助被科研通管家采纳,获得10
5秒前
sendou的应助被科研通管家采纳,获得30
5秒前
Jasper的应助被科研通管家采纳,获得10
5秒前
6秒前
yn107发布了新的文献求助10
6秒前
顾矜的应助被科研通管家采纳,获得10
6秒前
科研菜菜的应助被科研通管家采纳,获得30
6秒前
Eric完成签到,获得积分10
6秒前
6秒前
wanci的应助被科研通管家采纳,获得10
6秒前
英俊的铭的应助被科研通管家采纳,获得10
6秒前
上官若男的应助被科研通管家采纳,获得10
6秒前
脑洞疼的应助被科研通管家采纳,获得10
7秒前
Akim的应助被科研通管家采纳,获得10
7秒前
所所的应助被科研通管家采纳,获得10
7秒前
7秒前
Jasper的应助被科研通管家采纳,获得10
7秒前
Cr的应助被科研通管家采纳,获得10
7秒前
思源的应助被科研通管家采纳,获得10
7秒前
Orange的应助被xyt采纳,获得10
7秒前
Cr的应助被科研通管家采纳,获得10
7秒前
无奈醉柳完成签到,获得积分10
8秒前
qian完成签到,获得积分10
8秒前
9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