Prediction of Left Ventricular Ejection Fraction from Lead-II ECG monitoring waveforms (EMW) Using Deep Learning Algorithms

Prediction of Left Ventricular Ejection Fraction from Lead-II ECG monitoring waveforms (EMW) Using Deep Learning Algorithms | 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 Article Prediction of Left Ventricular Ejection Fraction from Lead-II ECG monitoring waveforms (EMW) Using Deep Learning Algorithms Doudou Wang, XianCong Wang, Jian Sun, Yueguo Wang, Jie Wang, Xin Wang, and 7 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8264590/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Background： Left ventricular ejection fraction (EF) is a key marker of cardiac systolic function and plays a central role in hemodynamic management of critically ill patients. Although echocardiography remains the standard for EF assessment, its routine use in intensive care units (ICUs) is limited by equipment availability, operator dependency, and lack of capability for continuous monitoring. This study aimed to develop and validate a deep learning model using lead-II electrocardiogram (ECG) monitoring waveforms (EMW) to estimate EF continuously and non-invasively, providing a practical alternative for real-time cardiac function monitoring in the ICU. Methods This prospective, single-center observational study was conducted in the Emergency Intensive Care Unit (EICU) of the First Affiliated Hospital of the University of Science and Technology of China between September 2024 and March 2025. Patients underwent 120-second lead-II EMW recordings at 500 Hz, synchronized with M-mode echocardiography. EF was quantified using the Teichholz method and verified by three experienced echocardiographers. EMW signals were processed using wavelet-based denoising, R-peak detection, and heartbeat segmentation. Two datasets were developed: the Single-beat EF Dataset (SEF), with beat-level EF labels, and the Averaged EF Dataset (AveEF), with patient-level average EF labels. A convolutional neural network combined with a long short-term memory architecture (CNN-LSTM) was trained for continuous EF regression. Performance was evaluated using mean squared error (MSE) and mean absolute error (MAE), as illustrated in Figure 1. Results： A total of 42 patients were enrolled, generating 6,948 EMW-EF paired samples. In the SEF Dataset, the CNN-LSTM model achieved a mean MAE<4 and worst MAE 95% of samples presenting MAE<4. Subgroup analysis stratified by EF levels showed the highest predictive accuracy among patients with EF <40%, 93.1% of predictions had MAE <4. Prospective validation in three new patients confirmed generalizability, with all samples showing MAE <10. Conclusions: A CNN-LSTM model using short-duration lead-II EMW enables accurate, continuous, and non-invasive EF estimation. These findings support future development of waveform-based monitoring and wearable technologies for dynamic cardiac assessment in critical care. Ejection Fraction Lead-II ECG CNN-LSTM Deep Learning Cardiac Function Intensive Care Non-Invasive Monitoring Artificial intelligence Full Text Additional Declarations No competing interests reported. Supplementary Files DevelopmentBaseline.xlsx ProspectiveBaseline.xlsx SupplementaryMaterials.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 14 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviews received at journal 08 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 02 Apr, 2026 Reviewers invited by journal 01 Apr, 2026 Editor invited by journal 17 Mar, 2026 Editor assigned by journal 04 Dec, 2025 Submission checks completed at journal 04 Dec, 2025 First submitted to journal 02 Dec, 2025 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-8264590","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":616510438,"identity":"17419418-5fe2-4aea-9af7-154621eb7905","order_by":0,"name":"Doudou Wang","email":"","orcid":"","institution":"School of Mathematical Sciences, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Doudou","middleName":"","lastName":"Wang","suffix":""},{"id":616510439,"identity":"87e9c9fd-d380-4bd3-88df-490dff659988","order_by":1,"name":"XianCong Wang","email":"","orcid":"","institution":"Department of Emergency Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"XianCong","middleName":"","lastName":"Wang","suffix":""},{"id":616510440,"identity":"0861b335-9e84-4b01-a9a2-9041505fd819","order_by":2,"name":"Jian Sun","email":"","orcid":"","institution":"Department of Emergency Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Sun","suffix":""},{"id":616510441,"identity":"7b4e80ce-8d2a-422e-9671-efb29cfd2b10","order_by":3,"name":"Yueguo Wang","email":"","orcid":"","institution":"Department of Emergency Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Yueguo","middleName":"","lastName":"Wang","suffix":""},{"id":616510442,"identity":"5b3fdafb-17da-4adc-88e6-dda13c4bc777","order_by":4,"name":"Jie Wang","email":"","orcid":"","institution":"Department of Emergency Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Jie","middleName":"","lastName":"Wang","suffix":""},{"id":616510443,"identity":"0f43ff21-f15d-4dc9-bd94-1d3c2663e7dd","order_by":5,"name":"Xin Wang","email":"","orcid":"","institution":"Department of Emergency Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Wang","suffix":""},{"id":616510444,"identity":"af951bef-33ed-47e5-b6f7-0bb114e245ed","order_by":6,"name":"Quan Tang","email":"","orcid":"","institution":"School of Mathematical Sciences, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Quan","middleName":"","lastName":"Tang","suffix":""},{"id":616510445,"identity":"cf2ff949-37fa-463d-81c8-ed88f5413e2f","order_by":7,"name":"ShuSheng Zhou","email":"","orcid":"","institution":"Department of Emergency Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"ShuSheng","middleName":"","lastName":"Zhou","suffix":""},{"id":616510446,"identity":"1381e70e-6d71-4b1c-a0a6-001760711b53","order_by":8,"name":"Jie Ren","email":"","orcid":"","institution":"Department of Ultrasound Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Jie","middleName":"","lastName":"Ren","suffix":""},{"id":616510447,"identity":"3f00c934-141e-4372-bb4e-ee304470f4d3","order_by":9,"name":"Tao Xiong","email":"","orcid":"","institution":"School of Mathematical Sciences, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Xiong","suffix":""},{"id":616510448,"identity":"b8a87838-263c-47a3-a06a-80ec2a47946d","order_by":10,"name":"Yinglei Lai","email":"","orcid":"","institution":"School of Mathematical Sciences, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Yinglei","middleName":"","lastName":"Lai","suffix":""},{"id":616510449,"identity":"3e2ad3ee-c3ca-401a-8bae-683ba5901194","order_by":11,"name":"Mengping Zhang","email":"","orcid":"","institution":"School of Mathematical Sciences, University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Mengping","middleName":"","lastName":"Zhang","suffix":""},{"id":616510450,"identity":"c6cef960-81d2-422d-ae9c-29238e4f0782","order_by":12,"name":"Kui Jin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYBACCQbGBoMEBhsol414LWlQ1cRpAYPDJGiRnJHcUPBwx/nE+fObHzB8KDvMwD+7Ab8WaYnEBoPEM7cTNxxjM2Ccce4wg8SdA/i1yIG1tAG1sPEwMPO2HWYwkEggSsu5xPltQC1/idECcVjbgcSGY0AtjMRokex5CNKSbLzhWJrBwZ5z6TwSNwhokTie/szwZ5ud7Pzmww8f/CizluOfQUALELAZwFgHgJiHoHogYH5AjKpRMApGwSgYwQAA1ahCUrot/DcAAAAASUVORK5CYII=","orcid":"","institution":"Department of Emergency Medicine,The First Affiliated Hospital of USTC,Division of Life Sciences and Medicine, University of Science and Technology of China","correspondingAuthor":true,"prefix":"","firstName":"Kui","middleName":"","lastName":"Jin","suffix":""}],"badges":[],"createdAt":"2025-12-03 00:23:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8264590/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8264590/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106406131,"identity":"e9ff1f16-97e4-4916-be29-a709683dba92","added_by":"auto","created_at":"2026-04-08 09:29:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5375452,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8264590/v1_covered_a6865bd7-a49a-4c50-b160-53e74f554a3e.pdf"},{"id":106362732,"identity":"2cdaeec5-9856-443b-a98a-c6ef1603861b","added_by":"auto","created_at":"2026-04-07 21:20:31","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":15686,"visible":true,"origin":"","legend":"","description":"","filename":"DevelopmentBaseline.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8264590/v1/4e83e02c1c76866dcccd86d8.xlsx"},{"id":106362733,"identity":"7818c91c-c583-49df-a567-c5cb37bcaf00","added_by":"auto","created_at":"2026-04-07 21:20:31","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":10758,"visible":true,"origin":"","legend":"","description":"","filename":"ProspectiveBaseline.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-8264590/v1/fdbcc61ab62c299716bc907a.xlsx"},{"id":106404167,"identity":"e4d075f3-b91f-4163-8068-d7ed81db9606","added_by":"auto","created_at":"2026-04-08 09:15:34","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":2466683,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterials.docx","url":"https://assets-eu.researchsquare.com/files/rs-8264590/v1/294145500b1d02cff3d5aa26.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction of Left Ventricular Ejection Fraction from Lead-II ECG monitoring waveforms (EMW) Using Deep Learning Algorithms","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Ejection Fraction, Lead-II ECG, CNN-LSTM, Deep Learning, Cardiac Function, Intensive Care, Non-Invasive Monitoring, Artificial intelligence","lastPublishedDoi":"10.21203/rs.3.rs-8264590/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8264590/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground：\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eLeft ventricular ejection fraction (EF) is a key marker of cardiac systolic function and plays a central role in hemodynamic management of critically ill patients. Although echocardiography remains the standard for EF assessment, its routine use in intensive care units (ICUs) is limited by equipment availability, operator dependency, and lack of capability for continuous monitoring. This study aimed to develop and validate a deep learning model using lead-II electrocardiogram (ECG) monitoring waveforms (EMW) to estimate EF continuously and non-invasively, providing a practical alternative for real-time cardiac function monitoring in the ICU.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis prospective, single-center observational study was conducted in the Emergency Intensive Care Unit (EICU) of the First Affiliated Hospital of the University of Science and Technology of China between September 2024 and March 2025. Patients underwent 120-second lead-II EMW recordings at 500 Hz, synchronized with M-mode echocardiography. EF was quantified using the Teichholz method and verified by three experienced echocardiographers.\u003c/p\u003e\n\u003cp\u003eEMW signals were processed using wavelet-based denoising, R-peak detection, and heartbeat segmentation. Two datasets were developed: the Single-beat EF Dataset (SEF), with beat-level EF labels, and the Averaged EF Dataset (AveEF), with patient-level average EF labels. A convolutional neural network combined with a long short-term memory architecture (CNN-LSTM) was trained for continuous EF regression. Performance was evaluated using mean squared error (MSE) and mean absolute error (MAE), as illustrated in Figure 1.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults：\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 42 patients were enrolled, generating 6,948 EMW-EF paired samples. In the SEF Dataset, the CNN-LSTM model achieved a mean MAE\u0026lt;4 and worst MAE\u0026lt;10, outperforming models including CNN, LSTM, and Transformer architectures (R²= 0.9521). In the AveEF Dataset, the model achieved improved stability (R² =0.9596), with \u0026gt; 95% of samples presenting MAE\u0026lt;4. Subgroup analysis stratified by EF levels showed the highest predictive accuracy among patients with EF \u0026lt;40%, 93.1% of predictions had MAE \u0026lt;4. Prospective validation in three new patients confirmed generalizability, with all samples showing MAE \u0026lt;10.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA CNN-LSTM model using short-duration lead-II EMW enables accurate, continuous, and non-invasive EF estimation. These findings support future development of waveform-based monitoring and wearable technologies for dynamic cardiac assessment in critical care.\u003c/p\u003e","manuscriptTitle":"Prediction of Left Ventricular Ejection Fraction from Lead-II ECG monitoring waveforms (EMW) Using Deep Learning Algorithms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-07 21:20:27","doi":"10.21203/rs.3.rs-8264590/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-14T04:44:35+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T05:59:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-08T08:43:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"223280908666910433665993995688693389605","date":"2026-04-08T04:46:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"150547442043808969106364295140829238886","date":"2026-04-02T09:54:22+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-02T03:54:03+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-17T12:24:42+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-04T12:52:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-04T12:52:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2025-12-03T00:13:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cc8d3cbd-2b2b-4865-a465-5f5cd324340f","owner":[],"postedDate":"April 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-10T05:38:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-07 21:20:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8264590","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8264590","identity":"rs-8264590","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}