从不断变化的临床特征出发,深入持续地进行多任务严重性评估

Pablo Ferri, Carlos Sáez, Antonio Félix-De Castro, Purificación Sánchez-Cuesta, Juan M García-Gómez
{"title":"从不断变化的临床特征出发,深入持续地进行多任务严重性评估","authors":"Pablo Ferri, Carlos Sáez, Antonio Félix-De Castro, Purificación Sánchez-Cuesta, Juan M García-Gómez","doi":"10.1101/2024.02.20.24303094","DOIUrl":null,"url":null,"abstract":"When developing Machine Learning models to support emergency medical triage, it is important to consider how changes over time in the data distribution can negatively affect the models' performance. The objective of this study was to assess the effectiveness of various Continual Learning pipelines in keeping model performance stable when input features are subject to change over time, including the emergence of new features and the disappearance of existing ones. The model is designed to identify life-threatening situations, calculate its admissible response delay, and determine its institution jurisdiction. We analyzed a total of 1 414 575 events spanning from 2009 to 2019. Our findings demonstrate important performance improvements, up to 7.8% in life-threatening and 14.8% in response delay, in terms of F1-score, when employing deep continual approaches. We noticed that combining fine-tuning and dynamic feature domain updating strategies offers a practical and effective solution for addressing these distributional drifts in medical emergency data.","PeriodicalId":501290,"journal":{"name":"medRxiv - Emergency Medicine","volume":"124 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep continual multitask severity assessment from changing clinical features\",\"authors\":\"Pablo Ferri, Carlos Sáez, Antonio Félix-De Castro, Purificación Sánchez-Cuesta, Juan M García-Gómez\",\"doi\":\"10.1101/2024.02.20.24303094\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"When developing Machine Learning models to support emergency medical triage, it is important to consider how changes over time in the data distribution can negatively affect the models' performance. The objective of this study was to assess the effectiveness of various Continual Learning pipelines in keeping model performance stable when input features are subject to change over time, including the emergence of new features and the disappearance of existing ones. The model is designed to identify life-threatening situations, calculate its admissible response delay, and determine its institution jurisdiction. We analyzed a total of 1 414 575 events spanning from 2009 to 2019. Our findings demonstrate important performance improvements, up to 7.8% in life-threatening and 14.8% in response delay, in terms of F1-score, when employing deep continual approaches. We noticed that combining fine-tuning and dynamic feature domain updating strategies offers a practical and effective solution for addressing these distributional drifts in medical emergency data.\",\"PeriodicalId\":501290,\"journal\":{\"name\":\"medRxiv - Emergency Medicine\",\"volume\":\"124 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"medRxiv - Emergency Medicine\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1101/2024.02.20.24303094\",\"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 - Emergency Medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2024.02.20.24303094","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

在开发支持紧急医疗分诊的机器学习模型时,必须考虑数据分布随时间的变化会对模型性能产生怎样的负面影响。本研究的目的是评估各种持续学习管道在输入特征随时间变化(包括新特征的出现和现有特征的消失)时保持模型性能稳定的有效性。该模型旨在识别危及生命的情况,计算其可接受的响应延迟,并确定其机构管辖范围。我们分析了从 2009 年到 2019 年共 1 414 575 起事件。我们的研究结果表明,在采用深度持续方法时,性能有了显著提高,在生命威胁方面提高了 7.8%,在响应延迟方面提高了 14.8%(以 F1 分数计算)。我们注意到,结合微调和动态特征域更新策略为解决医疗急救数据中的分布漂移问题提供了一种实用而有效的解决方案。
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
Deep continual multitask severity assessment from changing clinical features
When developing Machine Learning models to support emergency medical triage, it is important to consider how changes over time in the data distribution can negatively affect the models' performance. The objective of this study was to assess the effectiveness of various Continual Learning pipelines in keeping model performance stable when input features are subject to change over time, including the emergence of new features and the disappearance of existing ones. The model is designed to identify life-threatening situations, calculate its admissible response delay, and determine its institution jurisdiction. We analyzed a total of 1 414 575 events spanning from 2009 to 2019. Our findings demonstrate important performance improvements, up to 7.8% in life-threatening and 14.8% in response delay, in terms of F1-score, when employing deep continual approaches. We noticed that combining fine-tuning and dynamic feature domain updating strategies offers a practical and effective solution for addressing these distributional drifts in medical emergency 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
自引率
0.00%
发文量
0
期刊最新文献
In-hospital stay of anemic patients (70-90 g.L-1) in the ED with/without transfusion: a single-center propensity-matched study. Accuracy of the National Early Warning Score version 2 (NEWS2) in predicting need for time-critical treatment: Retrospective observational cohort study What strategies are used to select patients for direct admission under acute medicine services? A systematic review of the literature. Feasibility of mixed-reality telecollaboration to enhance pre-medical student shadowing education Evaluating the Impact of NHS Strikes on Patient Flow through Emergency Departments
×
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