Comparative performance of large language models for patient-initiated ophthalmology consultations

作者
Mingxue Huang,Xiaoyan Wang,Shiqi Zhou,Xinyu Cui,Zilin Zhang,Yanwu Xu,Weihua Yang,Wei Chi
出处
期刊:Frontiers in Public Health [Frontiers Media]
卷期号:13: 1673045-1673045 被引量:13
标识
DOI:10.3389/fpubh.2025.1673045
摘要

Background: Large language models (LLMs) are increasingly accessed by lay users for medical advice. This study aims to conduct a comprehensive evaluation of the responses generated by five large language models. Methods: We identified 31 ophthalmology-related questions most frequently raised by patients during routine consultations and subsequently elicited responses from five large language models: ChatGPT-4o, DeepSeek-V3, Doubao, Wenxin Yiyan 4.0 Turbo, and Qwen. A five-point likert scale was employed to assess each model across five domains: accuracy, logical consistency, coherence, safety, and content accessibility. Additionally, textual characteristics, including character, word, and sentence counts, were quantitatively analyzed. Results: < 0.05). Existing safety evaluations indicate that both Doubao and Wenxin Yiyan 4.0 Turbo exhibit significant security deficiencies. Conversely, Qwen generated significantly longer outputs, as evidenced by greater character, word, and sentence counts. Conclusion: ChatGPT-4o and DeepSeek-V3 demonstrated the highest overall performance and are best suited for laypersons seeking ophthalmic information. Doubao and Qwen, with their richer clinical terminology, better serve users with medical training, whereas Wenxin Yiyan 4.0 Turbo most effectively supports patients' pre-procedural understanding of diagnostic procedures. Prospective randomized controlled trials are required to determine whether integrating the top-performing model into pre-consultation triage improves patient comprehension.

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
小王子完成签到,获得积分10
1秒前
huangsiting完成签到 ,获得积分10
1秒前
鸥羡完成签到,获得积分10
1秒前
Oxinxin发布了新的文献求助10
1秒前
zisezhaoyan完成签到,获得积分10
1秒前
峯回路转完成签到,获得积分10
2秒前
在水一方的应助被Verna采纳,获得10
2秒前
2秒前
王玲完成签到 ,获得积分10
2秒前
taka完成签到,获得积分10
2秒前
ai0217邮箱amyvx完成签到,获得积分20
3秒前
无情听南完成签到,获得积分10
3秒前
mm完成签到 ,获得积分10
5秒前
小橙好运完成签到 ,获得积分10
5秒前
youyyuy完成签到,获得积分10
5秒前
滕祥发布了新的文献求助200
5秒前
寒冷尔柳完成签到 ,获得积分10
6秒前
6秒前
kiana完成签到,获得积分10
7秒前
tengfei完成签到,获得积分10
7秒前
7秒前
bodhi完成签到,获得积分10
7秒前
寒酥完成签到 ,获得积分10
7秒前
mobei完成签到,获得积分10
7秒前
宗佳茹发布了新的文献求助10
8秒前
科研大佬的路上完成签到 ,获得积分10
8秒前
wanci的应助被LKX采纳,获得10
8秒前
高挑的葵阴完成签到,获得积分10
8秒前
xh完成签到 ,获得积分10
8秒前
ljy0825完成签到 ,获得积分10
8秒前
Orange的应助被quhayley采纳,获得10
8秒前
无声瀑布完成签到,获得积分10
9秒前
稀饭完成签到,获得积分10
9秒前
9秒前
null的应助被科研通管家采纳,获得10
9秒前
9秒前
邓力的应助被科研通管家采纳,获得10
9秒前
树池完成签到,获得积分10
9秒前
邓力的应助被科研通管家采纳,获得10
9秒前
情怀的应助被科研通管家采纳,获得30
10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 1500
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
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
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 8159288
求助须知:如何正确求助?哪些是违规求助? 9554702
关于积分的说明 21720900
捐赠科研通 7748911
什么是DOI,文献DOI怎么找? 3427184
关于科研通互助平台的介绍 2552111
邀请新用户注册赠送积分活动 2471479