Large language models for error detection in radiology reports: a comparative analysis between closed-source and privacy-compliant open-source models

开源 神经组阅片室 介入放射学 医学 放射科 超声波 医学物理学 计算机科学 程序设计语言 软件 神经学 精神科
作者
Babak Salam,Claire Stüwe,Sebastian Nowak,Alois Martin Sprinkart,Maike Theis,Dmitrij Kravchenko,Narine Mesropyan,Tatjana Dell,Christoph Endler,Claus Christian Pieper,Daniel L. R. Kuetting,Julian Alexander Luetkens,Alexander Isaak
出处
期刊:European Radiology [Springer Science+Business Media]
卷期号:35 (8): 4549-4557 被引量:45
标识
DOI:10.1007/s00330-025-11438-y
摘要

PURPOSE: Large language models (LLMs) like Generative Pre-trained Transformer 4 (GPT-4) can assist in detecting errors in radiology reports, but privacy concerns limit their clinical applicability. This study compares closed-source and privacy-compliant open-source LLMs for detecting common errors in radiology reports. MATERIALS AND METHODS: A total of 120 radiology reports were compiled (30 each from X-ray, ultrasound, CT, and MRI). Subsequently, 397 errors from five categories (typographical, numerical, findings-impression discrepancies, omission/insertion, interpretation) were inserted into 100 of these reports; 20 reports were left unchanged. Two open-source models (Llama 3-70b, Mixtral 8x22b) and two commercial closed-source (GPT-4, GPT-4o) were tasked with error detection using identical prompts. The Kruskall-Wallis test and paired t-test were used for statistical analysis. RESULTS: Open-source LLMs required less processing time per radiology report than closed-source LLMs (6 ± 2 s vs. 13 ± 4 s; p < 0.001). Closed-source LLMs achieved higher error detection rates than open-source LLMs (GPT-4o: 88% [348/397; 95% CI: 86, 92], GPT-4: 83% [328/397; 95% CI: 80, 87], Llama 3-70b: 79% [311/397; 95% CI: 76, 83], Mixtral 8x22b: 73% [288/397; 95% CI: 68, 77]; p < 0.001). Numerical errors (88% [67/76; 95% CI: 82, 93]) were detected significantly more often than typographical errors (75% [65/86; 95% CI: 68, 82]; p = 0.02), discrepancies between findings and impression (73% [73/101; 95% CI: 67, 80]; p < 0.01), and interpretation errors (70% [50/71; 95% CI: 62, 78]; p = 0.001). CONCLUSION: Open-source LLMs demonstrated effective error detection, albeit with comparatively lower accuracy than commercial closed-source models, and have potential for clinical applications when deployed via privacy-compliant local hosting solutions. KEY POINTS: Question Can privacy-compliant open-source large language models (LLMs) match the error-detection performance of commercial non-privacy-compliant closed-source models in radiology reports? Findings Closed-source LLMs achieved slightly higher accuracy in detecting radiology report errors than open-source models, with Llama 3-70b yielding the best results among the open-source models. Clinical relevance Open-source LLMs offer a privacy-compliant alternative for automated error detection in radiology reports, improving clinical workflow efficiency while ensuring patient data confidentiality. Further refinement could enhance their accuracy, contributing to better diagnosis and patient care.
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
在水一方的应助被Eana采纳,获得10
1秒前
1秒前
1秒前
妮妮完成签到,获得积分10
1秒前
2秒前
大个的应助被科研通管家采纳,获得10
2秒前
Cr的应助被科研通管家采纳,获得10
2秒前
科研通AI2S的应助被临平吴彦祖采纳,获得10
2秒前
CipherSage的应助被科研通管家采纳,获得10
2秒前
sendou的应助被科研通管家采纳,获得30
2秒前
Jasper的应助被科研通管家采纳,获得10
2秒前
3秒前
yn107发布了新的文献求助10
3秒前
顾矜的应助被科研通管家采纳,获得10
3秒前
科研菜菜的应助被科研通管家采纳,获得30
3秒前
Eric完成签到,获得积分10
3秒前
3秒前
wanci的应助被科研通管家采纳,获得10
3秒前
英俊的铭的应助被科研通管家采纳,获得10
3秒前
上官若男的应助被科研通管家采纳,获得10
3秒前
脑洞疼的应助被科研通管家采纳,获得10
4秒前
Akim的应助被科研通管家采纳,获得10
4秒前
所所的应助被科研通管家采纳,获得10
4秒前
4秒前
Jasper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
思源的应助被科研通管家采纳,获得10
4秒前
Orange的应助被xyt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
无奈醉柳完成签到,获得积分10
5秒前
qian完成签到,获得积分10
5秒前
6秒前
小方发布了新的文献求助10
6秒前
水弘的应助被暮晓见采纳,获得10
7秒前
8秒前
wiliiam完成签到,获得积分10
8秒前
9秒前
9秒前
10秒前
Jonathan发布了新的文献求助10
11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