使用真实临床笔记识别中心静脉相关血流感染 (CLABSI) 的大型语言模型的性能。

IF 3 4区医学 Q2 INFECTIOUS DISEASES

Infection Control and Hospital Epidemiology Pub Date : 2024-10-30 DOI:10.1017/ice.2024.164

Guillermo Rodriguez-Nava, Goar Egoryan, Katherine E Goodman, Daniel J Morgan, Jorge L Salinas

{"title":"使用真实临床笔记识别中心静脉相关血流感染 (CLABSI) 的大型语言模型的性能。","authors":"Guillermo Rodriguez-Nava, Goar Egoryan, Katherine E Goodman, Daniel J Morgan, Jorge L Salinas","doi":"10.1017/ice.2024.164","DOIUrl":null,"url":null,"abstract":"We evaluated one of the first secure large language models approved for protected health information, for identifying central line-associated bloodstream infections (CLABSIs) using real clinical notes. Despite no pretraining, the model demonstrated rapid assessment and high sensitivity for CLABSI identification. Performance would improve with access to more patient data.","PeriodicalId":13663,"journal":{"name":"Infection Control and Hospital Epidemiology","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Performance of a large language model for identifying central line-associated bloodstream infections (CLABSI) using real clinical notes.\",\"authors\":\"Guillermo Rodriguez-Nava, Goar Egoryan, Katherine E Goodman, Daniel J Morgan, Jorge L Salinas\",\"doi\":\"10.1017/ice.2024.164\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We evaluated one of the first secure large language models approved for protected health information, for identifying central line-associated bloodstream infections (CLABSIs) using real clinical notes. Despite no pretraining, the model demonstrated rapid assessment and high sensitivity for CLABSI identification. Performance would improve with access to more patient data.\",\"PeriodicalId\":13663,\"journal\":{\"name\":\"Infection Control and Hospital Epidemiology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-10-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Infection Control and Hospital Epidemiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1017/ice.2024.164\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"INFECTIOUS DISEASES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Infection Control and Hospital Epidemiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1017/ice.2024.164","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"INFECTIOUS DISEASES","Score":null,"Total":0}

引用次数: 0

摘要

我们对首批获准用于受保护健康信息的安全大型语言模型之一进行了评估，以利用真实的临床记录识别中心静脉相关性血流感染（CLABSI）。尽管没有预先训练，但该模型在 CLABSI 识别方面表现出了快速评估和高灵敏度。在获得更多患者数据后，性能将得到改善。

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

Performance of a large language model for identifying central line-associated bloodstream infections (CLABSI) using real clinical notes.

We evaluated one of the first secure large language models approved for protected health information, for identifying central line-associated bloodstream infections (CLABSIs) using real clinical notes. Despite no pretraining, the model demonstrated rapid assessment and high sensitivity for CLABSI identification. Performance would improve with access to more patient data.

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

Infection Control and Hospital Epidemiology 医学-传染病学

CiteScore

6.40

自引率

6.70%

发文量

289

审稿时长

3-8 weeks

期刊介绍： Infection Control and Hospital Epidemiology provides original, peer-reviewed scientific articles for anyone involved with an infection control or epidemiology program in a hospital or healthcare facility. Written by infection control practitioners and epidemiologists and guided by an editorial board composed of the nation''s leaders in the field, ICHE provides a critical forum for this vital information.