使用机器学习算法预测急诊科入院:回顾性研究的概念证明。

IF 2.3 3区 医学 Q1 EMERGENCY MEDICINE BMC Emergency Medicine Pub Date : 2025-01-06 DOI:10.1186/s12873-024-01141-4
Cyrielle Brossard, Christophe Goetz, Pierre Catoire, Lauriane Cipolat, Christophe Guyeux, Cédric Gil Jardine, Mahuna Akplogan, Laure Abensur Vuillaume
{"title":"使用机器学习算法预测急诊科入院:回顾性研究的概念证明。","authors":"Cyrielle Brossard, Christophe Goetz, Pierre Catoire, Lauriane Cipolat, Christophe Guyeux, Cédric Gil Jardine, Mahuna Akplogan, Laure Abensur Vuillaume","doi":"10.1186/s12873-024-01141-4","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Overcrowding in emergency departments (ED) is a major public health issue, leading to increased workload and exhaustion for the teams, resulting poor outcomes. It seems interesting to be able to predict the admissions of patients in the ED.</p><p><strong>Aim: </strong>The main objective of this study was to build and test a prediction tool for ED admissions using artificial intelligence.</p><p><strong>Methods: </strong>We performed a retrospective multicenter study in two French ED from January 1st, 2010 to December 31st, 2019.We tested several machine learning algorithms and compared the results.</p><p><strong>Results: </strong>The arrival and departure times from the ED of 2 hospitals were collected from all consultations during the study period, then grouped into 87 600 one-hour slots. Through the development of two models (one for each location), we found that the XGBoost method with hyperparameter adaptations was the best, suggesting that the studied data could be predicted (mean absolute error) at 2.63 for Hospital 1 and 2.64 for Hospital 2).</p><p><strong>Conclusions: </strong>This study ran the construction and validation of a powerful tool for predicting ED admissions in 2 French ED. This type of tool should be integrated into the overall organization of an ED, to optimize the resources of healthcare professionals.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":"25 1","pages":"3"},"PeriodicalIF":2.3000,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11706136/pdf/","citationCount":"0","resultStr":"{\"title\":\"Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study.\",\"authors\":\"Cyrielle Brossard, Christophe Goetz, Pierre Catoire, Lauriane Cipolat, Christophe Guyeux, Cédric Gil Jardine, Mahuna Akplogan, Laure Abensur Vuillaume\",\"doi\":\"10.1186/s12873-024-01141-4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Overcrowding in emergency departments (ED) is a major public health issue, leading to increased workload and exhaustion for the teams, resulting poor outcomes. It seems interesting to be able to predict the admissions of patients in the ED.</p><p><strong>Aim: </strong>The main objective of this study was to build and test a prediction tool for ED admissions using artificial intelligence.</p><p><strong>Methods: </strong>We performed a retrospective multicenter study in two French ED from January 1st, 2010 to December 31st, 2019.We tested several machine learning algorithms and compared the results.</p><p><strong>Results: </strong>The arrival and departure times from the ED of 2 hospitals were collected from all consultations during the study period, then grouped into 87 600 one-hour slots. Through the development of two models (one for each location), we found that the XGBoost method with hyperparameter adaptations was the best, suggesting that the studied data could be predicted (mean absolute error) at 2.63 for Hospital 1 and 2.64 for Hospital 2).</p><p><strong>Conclusions: </strong>This study ran the construction and validation of a powerful tool for predicting ED admissions in 2 French ED. This type of tool should be integrated into the overall organization of an ED, to optimize the resources of healthcare professionals.</p>\",\"PeriodicalId\":9002,\"journal\":{\"name\":\"BMC Emergency Medicine\",\"volume\":\"25 1\",\"pages\":\"3\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2025-01-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11706136/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Emergency Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12873-024-01141-4\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"EMERGENCY MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Emergency Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12873-024-01141-4","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EMERGENCY MEDICINE","Score":null,"Total":0}
引用次数: 0

摘要

简介:急诊科(ED)人满为患是一个主要的公共卫生问题,导致工作量增加和团队疲惫,结果不佳。能够预测急诊科患者的入院情况似乎很有趣。目的:本研究的主要目的是利用人工智能建立和测试急诊科入院情况的预测工具。方法:2010年1月1日至2019年12月31日,我们对两名法国急诊科患者进行了回顾性多中心研究。我们测试了几种机器学习算法并比较了结果。结果:收集两家医院在研究期间的所有会诊中到达和离开急诊科的时间,然后将其分组为87,600个1小时时段。通过开发两个模型(每个位置一个模型),我们发现具有超参数自适应的XGBoost方法是最好的,这表明所研究的数据可以预测(平均绝对误差)为2.63医院1和2.64医院2)。本研究构建并验证了一种预测2个法国急诊科住院情况的强大工具。这种类型的工具应整合到急诊科的整体组织中,以优化医疗保健专业人员的资源。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Predicting emergency department admissions using a machine-learning algorithm: a proof of concept with retrospective study.

Introduction: Overcrowding in emergency departments (ED) is a major public health issue, leading to increased workload and exhaustion for the teams, resulting poor outcomes. It seems interesting to be able to predict the admissions of patients in the ED.

Aim: The main objective of this study was to build and test a prediction tool for ED admissions using artificial intelligence.

Methods: We performed a retrospective multicenter study in two French ED from January 1st, 2010 to December 31st, 2019.We tested several machine learning algorithms and compared the results.

Results: The arrival and departure times from the ED of 2 hospitals were collected from all consultations during the study period, then grouped into 87 600 one-hour slots. Through the development of two models (one for each location), we found that the XGBoost method with hyperparameter adaptations was the best, suggesting that the studied data could be predicted (mean absolute error) at 2.63 for Hospital 1 and 2.64 for Hospital 2).

Conclusions: This study ran the construction and validation of a powerful tool for predicting ED admissions in 2 French ED. This type of tool should be integrated into the overall organization of an ED, to optimize the resources of healthcare professionals.

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
BMC Emergency Medicine
BMC Emergency Medicine Medicine-Emergency Medicine
CiteScore
3.50
自引率
8.00%
发文量
178
审稿时长
29 weeks
期刊介绍: BMC Emergency Medicine is an open access, peer-reviewed journal that considers articles on all urgent and emergency aspects of medicine, in both practice and basic research. In addition, the journal covers aspects of disaster medicine and medicine in special locations, such as conflict areas and military medicine, together with articles concerning healthcare services in the emergency departments.
期刊最新文献
Construction and evaluation of a triage assessment model for patients with acute non-traumatic chest pain: mixed retrospective and prospective observational study. Design and psychometric testing of a moral intelligence instrument for pre-hospital emergency medical services personnel: a sequential-exploratory mixed-method study. Empowerment of volunteer nursing service providers during disasters: A qualitative study. Enhancing trauma triage in low-resource settings using machine learning: a performance comparison with the Kampala Trauma Score. Incidence and outcomes of dysnatremia in crush injury patients admitted to Türkiye's largest hospital following the Kahramanmaraş earthquake.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1