ICU False Alarm Identification Based on Convolution Neural Network

ICU False Alarm Identification Based on Convolution Neural Network | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research ICU False Alarm Identification Based on Convolution Neural Network Qiang Yu, Cheng Wang, Jing Xi, Ying Chen, Weifeng Li, Yun Ge, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-130985/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background: In intensive care unit(ICU), excessive false alarms burden medical staff greatly, and cause medical resource waste as well. In order to alleviate false alarms in ICU, we constructed models for classification using convolutional neural networks, which can deal directly with time series and avoid extracting features manually. Results: Combining with grouping strategy, we tried two basic network structures, i.e. DGCN and EDGCN. After that, based on EDGCN, which was proved better, ensembling networks were also constructed to elevate the performance further. Considering of the limited sample size, different data expansions were also experimented. Finally, we tested our model in the online sandbox, and got a score of 78.14. Conclusions: Although the performance is slightly lower than the best scores that have been reported, our models are end-to-end, through which the original time series can be automatically mapped into a binary output, without manually feature extraction. In addition, our method innovatively uses grouped convolution to make full use of the information in multi-channel signals. In the end, we also discussed the potential solutions to further elevate performances. Biomedical Engineering ICU DGCN EDGCN grouped convolution multi-channel physiological signals Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Full Text Due to technical limitations, full-text HTML conversion of this manuscript could not be completed. However, the latest manuscript can be downloaded and accessed as a PDF. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-130985","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research","associatedPublications":[],"authors":[{"id":6686980,"identity":"21372775-bc30-4e88-bc19-48b9917bd7f5","order_by":0,"name":"Qiang Yu","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Qiang","middleName":"","lastName":"Yu","suffix":""},{"id":6686981,"identity":"d37f380f-5021-48c9-9b0d-ebb8a0fbb9aa","order_by":1,"name":"Cheng Wang","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Cheng","middleName":"","lastName":"Wang","suffix":""},{"id":6686982,"identity":"23587d88-27e2-482b-a4e8-b88b57d6ec63","order_by":2,"name":"Jing Xi","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Xi","suffix":""},{"id":6686983,"identity":"e4db2e3f-77fe-47a9-bca1-126973891b02","order_by":3,"name":"Ying Chen","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Chen","suffix":""},{"id":6686984,"identity":"a94d0016-b3b5-4e80-850b-39f2cb3ada26","order_by":4,"name":"Weifeng Li","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Weifeng","middleName":"","lastName":"Li","suffix":""},{"id":6686985,"identity":"6e010be1-41b1-4b12-a5cc-4bd4227bc7b9","order_by":5,"name":"Yun Ge","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yun","middleName":"","lastName":"Ge","suffix":""},{"id":6686986,"identity":"f1b798c7-eb9e-4df0-84f3-ab016ec6d591","order_by":6,"name":"Xiaolin Huang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYDACdh4wJcfAcABIsRGjhRmixZh0LYkNYIoYLQaHeY9J/NxRm76d8YwBw4eywwz8sxvwa5Fs5kuT7D1zPHdnwxkDxhnnDjNI3DmAXws/M4+ZBG/bsdwNB84YMPO2HWYwkEjAr4UNqEXyb9uxdAOQlr/EaAHZIs3bVpMA1sJIjBbJZh5ja9m2A4YbDhwrONhzLp1H4gYBLQbHewxvvm2rkze4cXjjgx9l1nL8MwhogYLDDAwSB8CRyUOUeiCoA/qqgVjFo2AUjIJRMNIAAMbuQfE5sIRcAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-3382-5346","institution":"Nanjing University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Xiaolin","middleName":"","lastName":"Huang","suffix":""}],"badges":[],"createdAt":"2020-12-17 19:37:55","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-130985/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-130985/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":4429431,"identity":"0e6dc5e2-0459-44fd-bf2e-9fab1da05321","added_by":"auto","created_at":"2020-12-21 23:08:29","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":399298,"visible":true,"origin":"","legend":" Illustration of DGCN Model.\n","description":"","filename":"dgcn.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/02c94af1365c2654a4a2c5c1.png"},{"id":4429503,"identity":"bfcaf0b1-36b1-4dd3-8a4d-33d46635362f","added_by":"auto","created_at":"2020-12-21 23:11:30","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":234926,"visible":true,"origin":"","legend":" Illustration of receptive field and date length after layer processing.\n","description":"","filename":"receptive.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/a504d3b1a523443e72de7b2b.png"},{"id":4429389,"identity":"717e6069-2c43-4b33-9c00-379cbfcaf9a8","added_by":"auto","created_at":"2020-12-21 23:05:30","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":132486,"visible":true,"origin":"","legend":"Illustration of EDGCN Model.","description":"","filename":"edgcn.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/961757742cce83fa34b5a8f0.png"},{"id":4429436,"identity":"7f79d684-d62b-4333-a357-7eb9273d1e82","added_by":"auto","created_at":"2020-12-21 23:08:30","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":674835,"visible":true,"origin":"","legend":"Schematic diagram of slicing process.\n","description":"","filename":"slice.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/85687db2bbae0123937e7b15.png"},{"id":4429502,"identity":"b502bf12-6b0c-49b0-ad5f-fdf33770497f","added_by":"auto","created_at":"2020-12-21 23:11:29","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":168797,"visible":true,"origin":"","legend":"Illustrations of noise addition.","description":"","filename":"noise.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/13ccbf63dfdca7f2967c4324.png"},{"id":4429504,"identity":"ba7641ff-656b-4c50-90af-c544645b1b9f","added_by":"auto","created_at":"2020-12-21 23:11:30","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":207638,"visible":true,"origin":"","legend":"Schematic diagram of the combined model.\n","description":"","filename":"combined.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/6ab34b992d4ac4f45a43b407.png"},{"id":4429392,"identity":"cc1d3b9b-7356-4288-9ef8-8449410c7c04","added_by":"auto","created_at":"2020-12-21 23:05:30","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":274625,"visible":true,"origin":"","legend":" Framework diagram of overall processing flow.","description":"","filename":"flow.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/8baa048f58e95d581613780e.png"},{"id":4429390,"identity":"4fb411d7-5372-4bec-8a5e-b36ff7d2e025","added_by":"auto","created_at":"2020-12-21 23:05:30","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":605982,"visible":true,"origin":"","legend":"The first 200 epochs performances of different models on the open dataset.","description":"","filename":"results.png","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/adb49092d1f66860436dabcc.png"},{"id":13638887,"identity":"72f1fd05-bc60-4d24-9b6a-18ae007630eb","added_by":"auto","created_at":"2021-09-17 08:52:48","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2165469,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-130985/v1/42d6381a-e84e-4fcd-81db-3fe68e2b8273.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eICU False Alarm Identification Based on Convolution Neural Network\u003c/p\u003e","fulltext":[{"header":"Full Text","content":"Due to technical limitations, full-text HTML conversion of this manuscript could not be completed. However, the latest manuscript can be downloaded and \u003ca href='/article/rs-130985/latest.pdf' target='_blank'\u003e accessed as a PDF.\u003c/a\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"ICU, DGCN, EDGCN, grouped convolution, multi-channel physiological signals","lastPublishedDoi":"10.21203/rs.3.rs-130985/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-130985/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground:\u003c/strong\u003e In intensive care unit(ICU), excessive false alarms burden medical staff greatly, and cause medical resource waste as well. In order to alleviate false alarms in ICU, we constructed models for classification using convolutional neural networks, which can deal directly with time series and avoid extracting features manually. \u003c/p\u003e\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e Combining with grouping strategy, we tried two basic network structures, i.e. DGCN and EDGCN. After that, based on EDGCN, which was proved better, ensembling networks were also constructed to elevate the performance further. Considering of the limited sample size, different data expansions were also experimented. Finally, we tested our model in the online sandbox, and got a score of 78.14. \u003c/p\u003e\u003cp\u003e\u003cstrong\u003eConclusions:\u003c/strong\u003e Although the performance is slightly lower than the best scores that have been reported, our models are end-to-end, through which the original time series can be automatically mapped into a binary output, without manually feature extraction. In addition, our method innovatively uses grouped convolution to make full use of the information in multi-channel signals. In the end, we also discussed the potential solutions to further elevate performances.\u003c/p\u003e","manuscriptTitle":"ICU False Alarm Identification Based on Convolution Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2020-12-21 23:05:27","doi":"10.21203/rs.3.rs-130985/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3345a2cd-f7be-4db8-ae08-ec4b501db8ed","owner":[],"postedDate":"December 21st, 2020","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":1554819,"name":"Biomedical Engineering"}],"tags":[],"updatedAt":"2020-12-21T23:05:29+00:00","versionOfRecord":[],"versionCreatedAt":"2020-12-21 23:05:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-130985","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-130985","identity":"rs-130985","version":["v1"]},"buildId":"FbvkV6FR0MCFSLy54lSbu","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}