Assessment of Differential Diagnoses for Oculoplastics Cases Produced by Large Language Models.

IF 1.3 4区 医学 Q3 OPHTHALMOLOGY
Jeffrey C Peterson, Sruti S Rachapudi, Sasha Hubschman, Kevin Heinze, Thomas Oetting, Sean M Rodriguez, Pete Setabutr, Ann Q Tran
{"title":"Assessment of Differential Diagnoses for Oculoplastics Cases Produced by Large Language Models.","authors":"Jeffrey C Peterson, Sruti S Rachapudi, Sasha Hubschman, Kevin Heinze, Thomas Oetting, Sean M Rodriguez, Pete Setabutr, Ann Q Tran","doi":"10.1097/IOP.0000000000002984","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to evaluate the accuracy of different large language models (LLMs) in generating differential diagnoses for oculoplastic cases.</p><p><strong>Methods: </strong>Differential diagnoses were generated for 20 oculoplastic cases sourced from University of Iowa EyeRounds.org using 6 LLMs: Chat Generative Pre-Trained Transformer (ChatGPT) 3.5, ChatGPT 4.0, OcuSmart/EyeGPT, Google Gemini 1.5, Claude 3.5, and Microsoft CoPilot. Outputs were compared against the EyeRounds expert-curated differentials examining (1) top diagnosis match rate (2) inclusion of the correct diagnosis within the generated list, as well as (3) recall and (4) precision, calculated to assess the overlap and conciseness of LLM outputs.</p><p><strong>Results: </strong>OcuSmart/EyeGPT achieved the highest top diagnosis match rate (85 ± 36%), while Claude 3.5 demonstrated the highest rate of inclusion of correct diagnosis in differential, as well as recall rate (100 ± 0% and 55 ± 27%, respectively). Google Gemini produced the most precise differentials at 43 ± 24%. Claude 3.5 generated the largest but least concise lists. LLM performance varied by case; for example, idiopathic orbital inflammation cases yielded highest recall and top diagnosis match across all models, while floppy eyelid syndrome cases demonstrated lowest performance.</p><p><strong>Conclusions: </strong>LLMs show promising potential in diagnosing oculoplastic cases, with OcuSmart/EyeGPT and Claude 3.5 performing best for determining the case diagnosis and recall, and ChatGPT 3.5, OcuSmart/EyeGPT, and Gemini generating concise and relevant differentials. However, further research and development are necessary to validate LLMs' capabilities and integrate them into the clinical workflow.</p>","PeriodicalId":19588,"journal":{"name":"Ophthalmic Plastic and Reconstructive Surgery","volume":" ","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ophthalmic Plastic and Reconstructive Surgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/IOP.0000000000002984","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: This study aimed to evaluate the accuracy of different large language models (LLMs) in generating differential diagnoses for oculoplastic cases.

Methods: Differential diagnoses were generated for 20 oculoplastic cases sourced from University of Iowa EyeRounds.org using 6 LLMs: Chat Generative Pre-Trained Transformer (ChatGPT) 3.5, ChatGPT 4.0, OcuSmart/EyeGPT, Google Gemini 1.5, Claude 3.5, and Microsoft CoPilot. Outputs were compared against the EyeRounds expert-curated differentials examining (1) top diagnosis match rate (2) inclusion of the correct diagnosis within the generated list, as well as (3) recall and (4) precision, calculated to assess the overlap and conciseness of LLM outputs.

Results: OcuSmart/EyeGPT achieved the highest top diagnosis match rate (85 ± 36%), while Claude 3.5 demonstrated the highest rate of inclusion of correct diagnosis in differential, as well as recall rate (100 ± 0% and 55 ± 27%, respectively). Google Gemini produced the most precise differentials at 43 ± 24%. Claude 3.5 generated the largest but least concise lists. LLM performance varied by case; for example, idiopathic orbital inflammation cases yielded highest recall and top diagnosis match across all models, while floppy eyelid syndrome cases demonstrated lowest performance.

Conclusions: LLMs show promising potential in diagnosing oculoplastic cases, with OcuSmart/EyeGPT and Claude 3.5 performing best for determining the case diagnosis and recall, and ChatGPT 3.5, OcuSmart/EyeGPT, and Gemini generating concise and relevant differentials. However, further research and development are necessary to validate LLMs' capabilities and integrate them into the clinical workflow.

基于大语言模型的眼整形病例鉴别诊断评估。
目的:本研究旨在评估不同的大语言模型(llm)在眼部增生病例鉴别诊断中的准确性。方法:采用聊天生成预训练变形(ChatGPT) 3.5、聊天生成预训练变形(ChatGPT) 4.0、OcuSmart/EyeGPT、谷歌Gemini 1.5、Claude 3.5和Microsoft CoPilot 6个LLMs对20例眼部整形病例进行鉴别诊断。输出与EyeRounds专家策划的差异进行比较,检查(1)最高诊断匹配率(2)在生成的列表中包含正确诊断,以及(3)召回率和(4)精度,计算以评估LLM输出的重叠和简明性。结果:OcuSmart/EyeGPT的最高诊断匹配率为85±36%,而Claude 3.5的鉴别诊断正确纳入率和召回率最高(分别为100±0%和55±27%)。谷歌双子座产生了最精确的差值,为43±24%。Claude 3.5生成了最大但最不简洁的列表。法学硕士的表现因案例而异;例如,在所有模型中,特发性眼窝炎症病例的召回率和最高诊断匹配率最高,而眼睑松弛综合征病例的表现最低。结论:llm在诊断眼部整形病例方面显示出良好的潜力,OcuSmart/EyeGPT和Claude 3.5在确定病例诊断和回忆方面表现最好,ChatGPT 3.5、OcuSmart/EyeGPT和Gemini能够产生简洁和相关的鉴别。然而,需要进一步的研究和开发来验证llm的能力并将其整合到临床工作流程中。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
2.50
自引率
10.00%
发文量
322
审稿时长
3-8 weeks
期刊介绍: Ophthalmic Plastic and Reconstructive Surgery features original articles and reviews on topics such as ptosis, eyelid reconstruction, orbital diagnosis and surgery, lacrimal problems, and eyelid malposition. Update reports on diagnostic techniques, surgical equipment and instrumentation, and medical therapies are included, as well as detailed analyses of recent research findings and their clinical applications.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信