预测医院供水管网军团菌污染风险的机器学习与回归模型。

IF 1.5 Q3 HEALTH CARE SCIENCES & SERVICES Annali di igiene : medicina preventiva e di comunita Pub Date : 2025-01-01 Epub Date: 2024-07-11 DOI:10.7416/ai.2024.2644
Osvalda De Giglio, Fabrizio Fasano, Giusy Diella, Valentina Spagnuolo, Francesco Triggiano, Marco Lopuzzo, Francesca Apollonio, Carla Maria Leone, Maria Teresa Montagna
{"title":"预测医院供水管网军团菌污染风险的机器学习与回归模型。","authors":"Osvalda De Giglio, Fabrizio Fasano, Giusy Diella, Valentina Spagnuolo, Francesco Triggiano, Marco Lopuzzo, Francesca Apollonio, Carla Maria Leone, Maria Teresa Montagna","doi":"10.7416/ai.2024.2644","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>The periodic monitoring of Legionella in hospital water networks allows preventive measures to be taken to avoid the risk of legionellosis to patients and healthcare workers.</p><p><strong>Study design: </strong>The aim of the study is to standardize a method for predicting the risk of Legionella contamination in the water supply of a hospital facility, by comparing Machine Learning, conventional and combined models.</p><p><strong>Methods: </strong>During the period July 2021- October 2022, water sampling for Legionella detection was performed in the rooms of an Italian hospital pavilion (89.9% of the total number of rooms). Fifty-eight parameters regarding the structural and environmental characteristics of the water network were collected. Models were built on 70% of the dataset and tested on the remaining 30% to evaluate accuracy, sensitivity, and specificity.</p><p><strong>Results: </strong>A total of 1,053 water samples were analyzed and 57 (5.4%) were positive for Legionella. Of the Machine Learning models tested, the most efficient had an input layer (56 neurons), hidden layer (30 neurons), and output layer (two neurons). Accuracy was 93.4%, sensitivity was 43.8%, and specificity was 96%. The regression model had an accuracy of 82.9%, sensitivity of 20.3%, and specificity of 97.3%. The combination of the models achieved an accuracy of 82.3%, sensitivity of 22.4%, and specificity of 98.4%. The most important parameters that influenced the model results were the type of water network (hot/cold), the replacement of filter valves, and atmospheric temperature. Among the models tested, Machine Learning obtained the best results in terms of accuracy and sensitivity.</p><p><strong>Conclusions: </strong>Future studies are required to improve these predictive models by expanding the dataset using other parameters and other pavilions of the same hospital.</p>","PeriodicalId":7999,"journal":{"name":"Annali di igiene : medicina preventiva e di comunita","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning vs. regression models to predict the risk of Legionella contamination in a hospital water network.\",\"authors\":\"Osvalda De Giglio, Fabrizio Fasano, Giusy Diella, Valentina Spagnuolo, Francesco Triggiano, Marco Lopuzzo, Francesca Apollonio, Carla Maria Leone, Maria Teresa Montagna\",\"doi\":\"10.7416/ai.2024.2644\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>The periodic monitoring of Legionella in hospital water networks allows preventive measures to be taken to avoid the risk of legionellosis to patients and healthcare workers.</p><p><strong>Study design: </strong>The aim of the study is to standardize a method for predicting the risk of Legionella contamination in the water supply of a hospital facility, by comparing Machine Learning, conventional and combined models.</p><p><strong>Methods: </strong>During the period July 2021- October 2022, water sampling for Legionella detection was performed in the rooms of an Italian hospital pavilion (89.9% of the total number of rooms). Fifty-eight parameters regarding the structural and environmental characteristics of the water network were collected. Models were built on 70% of the dataset and tested on the remaining 30% to evaluate accuracy, sensitivity, and specificity.</p><p><strong>Results: </strong>A total of 1,053 water samples were analyzed and 57 (5.4%) were positive for Legionella. Of the Machine Learning models tested, the most efficient had an input layer (56 neurons), hidden layer (30 neurons), and output layer (two neurons). Accuracy was 93.4%, sensitivity was 43.8%, and specificity was 96%. The regression model had an accuracy of 82.9%, sensitivity of 20.3%, and specificity of 97.3%. The combination of the models achieved an accuracy of 82.3%, sensitivity of 22.4%, and specificity of 98.4%. The most important parameters that influenced the model results were the type of water network (hot/cold), the replacement of filter valves, and atmospheric temperature. Among the models tested, Machine Learning obtained the best results in terms of accuracy and sensitivity.</p><p><strong>Conclusions: </strong>Future studies are required to improve these predictive models by expanding the dataset using other parameters and other pavilions of the same hospital.</p>\",\"PeriodicalId\":7999,\"journal\":{\"name\":\"Annali di igiene : medicina preventiva e di comunita\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2025-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annali di igiene : medicina preventiva e di comunita\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.7416/ai.2024.2644\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/7/11 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annali di igiene : medicina preventiva e di comunita","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.7416/ai.2024.2644","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/11 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
引用次数: 0

摘要

简介:定期监测医院供水管网中的军团菌可采取预防措施,避免患者和医护人员感染军团菌病:通过定期监测医院供水管网中的军团菌,可以采取预防措施,避免患者和医护人员感染军团菌病的风险:研究目的:本研究旨在通过比较机器学习模型、传统模型和组合模型,对预测医院供水中军团菌污染风险的方法进行标准化:方法:在 2021 年 7 月至 2022 年 10 月期间,对意大利一家医院的病房(占病房总数的 89.9%)进行了水样采集,以检测军团菌。收集了有关水网结构和环境特征的 58 个参数。在 70% 的数据集上建立了模型,并在其余 30% 的数据集上进行了测试,以评估准确性、灵敏度和特异性:共分析了 1,053 份水样,其中 57 份(5.4%)对军团菌呈阳性反应。在测试的机器学习模型中,最有效的模型有输入层(56 个神经元)、隐藏层(30 个神经元)和输出层(2 个神经元)。准确率为 93.4%,灵敏度为 43.8%,特异性为 96%。回归模型的准确率为 82.9%,灵敏度为 20.3%,特异性为 97.3%。组合模型的准确率为 82.3%,灵敏度为 22.4%,特异性为 98.4%。影响模型结果的最重要参数是水网类型(热/冷)、过滤器阀门的更换和大气温度。在测试的模型中,机器学习在准确性和灵敏度方面取得了最佳结果:今后的研究需要通过使用其他参数和同一医院的其他病房来扩大数据集,从而改进这些预测模型。
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
Machine learning vs. regression models to predict the risk of Legionella contamination in a hospital water network.

Introduction: The periodic monitoring of Legionella in hospital water networks allows preventive measures to be taken to avoid the risk of legionellosis to patients and healthcare workers.

Study design: The aim of the study is to standardize a method for predicting the risk of Legionella contamination in the water supply of a hospital facility, by comparing Machine Learning, conventional and combined models.

Methods: During the period July 2021- October 2022, water sampling for Legionella detection was performed in the rooms of an Italian hospital pavilion (89.9% of the total number of rooms). Fifty-eight parameters regarding the structural and environmental characteristics of the water network were collected. Models were built on 70% of the dataset and tested on the remaining 30% to evaluate accuracy, sensitivity, and specificity.

Results: A total of 1,053 water samples were analyzed and 57 (5.4%) were positive for Legionella. Of the Machine Learning models tested, the most efficient had an input layer (56 neurons), hidden layer (30 neurons), and output layer (two neurons). Accuracy was 93.4%, sensitivity was 43.8%, and specificity was 96%. The regression model had an accuracy of 82.9%, sensitivity of 20.3%, and specificity of 97.3%. The combination of the models achieved an accuracy of 82.3%, sensitivity of 22.4%, and specificity of 98.4%. The most important parameters that influenced the model results were the type of water network (hot/cold), the replacement of filter valves, and atmospheric temperature. Among the models tested, Machine Learning obtained the best results in terms of accuracy and sensitivity.

Conclusions: Future studies are required to improve these predictive models by expanding the dataset using other parameters and other pavilions of the same hospital.

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
Annali di igiene : medicina preventiva e di comunita
Annali di igiene : medicina preventiva e di comunita HEALTH CARE SCIENCES & SERVICES-
CiteScore
3.40
自引率
0.00%
发文量
69
期刊最新文献
Intentions to move abroad among medical students: a cross-sectional study to investigate determinants and opinions. Prevalence and predictors of hand hygiene compliance in clinical, surgical and intensive care unit wards: results of a second cross-sectional study at the Umberto I teaching hospital of Rome. The prevention of medication errors in the home care setting: a scoping review. Training in infection prevention and control: survey on the volume and on the learning demands of healthcare-associated infections control figures in the Emilia-Romagna Region (Northern Italy). Machine learning vs. regression models to predict the risk of Legionella contamination in a hospital water network.
×
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