及时的工程策略提高了神经放射学病例中 GPT-4 Turbo 的诊断准确性

medRxiv - Radiology and Imaging Pub Date : 2024-05-01 DOI:10.1101/2024.04.29.24306583

Akihiko Wada, Toshiaki Akashi, George Shih, Akifumi Hagiwara, Mitsuo Nishizawa, Yayoi Hayakawa, Junko Kikuta, Keigo Shimoji, Katsuhiro Sano, Koji Kamagata, Atsushi Nakanishi, Shigeki Aoki

{"title":"及时的工程策略提高了神经放射学病例中 GPT-4 Turbo 的诊断准确性","authors":"Akihiko Wada, Toshiaki Akashi, George Shih, Akifumi Hagiwara, Mitsuo Nishizawa, Yayoi Hayakawa, Junko Kikuta, Keigo Shimoji, Katsuhiro Sano, Koji Kamagata, Atsushi Nakanishi, Shigeki Aoki","doi":"10.1101/2024.04.29.24306583","DOIUrl":null,"url":null,"abstract":"<strong>Background</strong> Large language models (LLMs) like GPT-4 demonstrate promising capabilities in medical image analysis, but their practical utility is hindered by substantial misdiagnosis rates ranging from 30-50%.","PeriodicalId":501358,"journal":{"name":"medRxiv - Radiology and Imaging","volume":"27 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Prompt Engineering Strategies Improve the Diagnostic Accuracy of GPT-4 Turbo in Neuroradiology Cases\",\"authors\":\"Akihiko Wada, Toshiaki Akashi, George Shih, Akifumi Hagiwara, Mitsuo Nishizawa, Yayoi Hayakawa, Junko Kikuta, Keigo Shimoji, Katsuhiro Sano, Koji Kamagata, Atsushi Nakanishi, Shigeki Aoki\",\"doi\":\"10.1101/2024.04.29.24306583\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<strong>Background</strong> Large language models (LLMs) like GPT-4 demonstrate promising capabilities in medical image analysis, but their practical utility is hindered by substantial misdiagnosis rates ranging from 30-50%.\",\"PeriodicalId\":501358,\"journal\":{\"name\":\"medRxiv - Radiology and Imaging\",\"volume\":\"27 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"medRxiv - Radiology and Imaging\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1101/2024.04.29.24306583\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"medRxiv - Radiology and Imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2024.04.29.24306583","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

背景 GPT-4 等大型语言模型（LLMs）在医学图像分析中表现出了良好的能力，但 30-50% 的高误诊率阻碍了它们的实际应用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Prompt Engineering Strategies Improve the Diagnostic Accuracy of GPT-4 Turbo in Neuroradiology Cases

Background Large language models (LLMs) like GPT-4 demonstrate promising capabilities in medical image analysis, but their practical utility is hindered by substantial misdiagnosis rates ranging from 30-50%.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

medRxiv - Radiology and Imaging

自引率

0.00%

发文量