{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:02:49Z","timestamp":1785434569509,"version":"3.56.0"},"reference-count":42,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Cardio"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Continuous vital sign monitoring ensures early detection, prevents intensive care unit (ICU) admissions, and improves patient outcomes. Continuous heart rate (HR) monitoring methods often require direct skin contact, which can lead to patient discomfort. The rising popularity of ballistocardiography (BCG) offers a promising, noncontact solution for continuous vital sign monitoring with improved patient comfort.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop and validate a novel HR measurement algorithm leveraging convolutional neural networks (CNNs) and BCG signals for accurate, noncontact, and continuous HR monitoring. By integrating time-domain peak detection with short-time Fourier transform and CNN models, the proposed approach seeks to enhance HR measurement accuracy across diverse health care settings. The study follows the Food and Drug Administration (FDA)\u2019s Good Machine Learning Practice guidelines and evaluates the algorithm\u2019s robustness, generalizability, and clinical applicability through extensive testing on a diverse dataset, ensuring improved patient comfort and early detection of clinical deterioration.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n The proposed algorithm combines time-domain peak detection with short-time Fourier transform and CNNs to enhance HR measurement from BCG signals. The CNN model developed was trained on 129,976 data points from 373 participants (HR range: 36\u2010230 bpm), including ICU patients, and was tuned on 75,970 data points from 192 participants (HR range: 46\u2010169 bpm), with HR obtained from clinical-grade electrocardiography devices to improve generalizability. The algorithm was tested on 70,211 data points from 205 participants, including ICU patients, across 5 independent studies to demonstrate robust performance against diverse settings, demographics, and comorbidities. The methodology is in compliance with the FDA\u2019s\n Good Machine Learning Practice for Medical Device Development: Guiding Principles<\/jats:italic>\n .\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The algorithm achieved a mean absolute error of under 3 bpm and a detection rate exceeding 80%, underscoring its robustness. The Bland-Altman analysis indicates high accuracy with a minimal bias of 0.25 and limits of agreement within 8.59 bpm. Additionally, the Pearson correlation coefficient of 0.97 from the Deming regression further demonstrates strong alignment with reference HR measurements, reinforcing its precision and reliability for clinical applications.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This CNN-based algorithm presents a robust solution for contactless HR monitoring, addressing the limitations of prior methods in noise management and adaptability. Its demonstrated accuracy, particularly in real-world, noisy clinical environments, highlights its potential for broad application in patient monitoring and improved comfort.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/71224","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T04:15:06Z","timestamp":1775448906000},"page":"e71224-e71224","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Convolutional Neural Network\u2013Based Algorithm for Heart Rate Measurement From Ballistocardiography Signals in Diverse Clinical Settings: Observational Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2813-7741","authenticated-orcid":false,"given":"Kumar","family":"Chokalingam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muthukumarasamy","family":"Saravanan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7788-1490","authenticated-orcid":false,"given":"Ashish","family":"Kaushal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0620-4947","authenticated-orcid":false,"given":"Srishti","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9041-8567","authenticated-orcid":false,"given":"Inam","family":"Ur Rahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6983-923X","authenticated-orcid":false,"given":"Ashwathi","family":"Nambiar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7394-5417","authenticated-orcid":false,"given":"Mudit","family":"Dandwate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3520-8141","authenticated-orcid":false,"given":"Ravi","family":"Mahajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9148-1249","authenticated-orcid":false,"given":"Kunal","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8401-9355","authenticated-orcid":false,"given":"Gaurav","family":"Parchani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"issue":"5","key":"R1","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1016\/j.bja.2022.01.036","article-title":"Effect of continuous wireless vital sign monitoring on unplanned ICU admissions and rapid response team calls: a before-and-after study","volume":"128","author":"Eddahchouri","journal-title":"Br J Anaesth"},{"issue":"4","key":"R2","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1097\/01.NAJ.0000742504.44428.c9","article-title":"Continuous physiological monitoring improves patient outcomes","volume":"121","author":"Stellpflug","journal-title":"Am J Nurs"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.3389\/fmedt.2024.1436034","article-title":"Early detection of deteriorating patients in general wards through continuous contactless vital signs monitoring","volume":"6","author":"Yadav","journal-title":"Front Med Technol"},{"issue":"5","key":"R4","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1097\/EJA.0000000000000798","article-title":"Improving detection of patient deterioration in the general hospital ward environment","volume":"35","author":"Vincent","journal-title":"Eur J Anaesthesiol"},{"issue":"6","key":"R5","doi-asserted-by":"publisher","DOI":"10.3390\/s20061796","article-title":"ECG monitoring systems: review, architecture, processes, and key challenges","volume":"20","author":"Serhani","journal-title":"Sensors (Basel)"},{"issue":"16","key":"R6","doi-asserted-by":"publisher","first-page":"6560","DOI":"10.1109\/JSEN.2019.2914166","article-title":"Heart rate estimation from wrist-worn photoplethysmography: a review","volume":"19","author":"Biswas","journal-title":"IEEE Sensors J"},{"issue":"2","key":"R7","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1007\/s11831-021-09597-4","article-title":"A review on computation methods used in photoplethysmography signal analysis for heart rate estimation","volume":"29","author":"Kumar","journal-title":"Arch Computat Methods Eng"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.1111\/j.1742-481X.2011.00915.x","article-title":"Skin irritation because of electrocardiograph lead in patients in intensive care unit","volume":"10","author":"Rafiei","journal-title":"Int Wound J"},{"key":"R9","unstructured":"Torp KD Modi P Pollard EJ Simon LV . Pulse oximetry. In: StatPearls. StatPearls Publishing; 2024. URL: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK470348\/ [Accessed 15-04-2026]"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","first-page":"201","DOI":"10.2174\/1874120701004010201","article-title":"Theory and developments in an unobtrusive cardiovascular system representation: ballistocardiography","volume":"4","author":"Pinheiro","journal-title":"Open Biomed Eng J"},{"issue":"2","key":"R11","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1161\/01.cir.7.2.268","article-title":"Ballistocardiography; an appraisal of technic, physiologic principles, and clinical value","volume":"7","author":"Gubner","journal-title":"Circulation"},{"issue":"6","key":"R12","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1111\/j.1475-097X.2012.01150.x","article-title":"Using ballistocardiography to measure cardiac performance: a brief review of its history and future significance","volume":"32","author":"Vogt","journal-title":"Clin Physiol Funct Imaging"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2023.1222898","article-title":"Heart rate estimation from ballistocardiogram signals processing via low-cost telemedicine architectures: a comparative performance evaluation","volume":"5","author":"Tramontano","journal-title":"Front Digit Health"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Ahmed N Srivyshnav KS Chokalingam K et al. Classification of sleep-wake state in ballistocardiogram system based on deep learning. Presented at: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); Jul 11-15, 2022; Glasgow, Scotland, United Kingdom. [doi: 10.1109\/EMBC48229.2022.9871831]","DOI":"10.1109\/EMBC48229.2022.9871831"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Saran V Kumar G Parchani G . Unsupervised extraction of respiration cycles through ballistocardiography. Presented at: Third International Conference on Advanced Informatics for Computing Research, ICAICR 2019; Jun 15-16, 2019; Shimla, India. [doi: 10.1007\/978-981-15-0108-1_14]","DOI":"10.1007\/978-981-15-0108-1_14"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1177\/09727531211063426","article-title":"Efficacy of non-contact ballistocardiographysystem to determine heart rate variability","volume":"29","author":"Parchani","journal-title":"Ann Neurosci"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Saran V Kumar G Dhawan U Parchani G . Unsupervised identification of cardiac contraction through ballistocardiography. Presented at: 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES); Dec 3-6, 2018; Sarawak, Malaysia. [doi: 10.1109\/IECBES.2018.8626652]","DOI":"10.1109\/IECBES.2018.8626652"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871007","article-title":"Validation of Dozee, a ballistocardiography-based device, for contactless and continuous heart rate and respiratory rate measurement","volume":"2022","author":"Saran","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Kedia S Ur Rahman I Kaushal A et al. Clinical validation of an indigenous micro-vibration vital parameter monitor Dozee VS. Presented at: 2023 15th International Conference on COMmunication Systems & NETworkS (COMSNETS); Jan 3-8, 2023; Bangalore, India. [doi: 10.1109\/COMSNETS56262.2023.10041343]","DOI":"10.1109\/COMSNETS56262.2023.10041343"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912650","article-title":"Performance comparison for ballistocardiogram peak detection methods","volume":"7","author":"Suliman","journal-title":"IEEE Access"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2021.3069815","article-title":"A wearable tele-health system towards monitoring COVID-19 and chronic diseases","volume":"15","author":"Jiang","journal-title":"IEEE Rev Biomed Eng"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1177\/20552076241277746","article-title":"Solving variability: accurately extracting feature components from ballistocardiograms","volume":"10","author":"Yang","journal-title":"Digit Health"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Javaid AQ Toreyin H Inan OT . Quantifying the effects of blood pressure changes on ballistocardiogram signals. Presented at: 2017 25th Signal Processing and Communications Applications Conference (SIU); May 15-18, 2017; Antalya, Turkey. [doi: 10.1109\/SIU.2017.7960423]","DOI":"10.1109\/SIU.2017.7960423"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-019-0071-7","article-title":"Ballistocardiogram signal processing: a review","volume":"7","author":"Sadek","journal-title":"Health Inf Sci Syst"},{"issue":"8","key":"R25","doi-asserted-by":"publisher","first-page":"3720","DOI":"10.1109\/JBHI.2022.3162396","article-title":"Non-contact heartbeat detection based on ballistocardiogram using UNet and bidirectional long short-term memory","volume":"26","author":"Mai","journal-title":"IEEE J Biomed Health Inform"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9630255","article-title":"Efficient J peak detection from ballistocardiogram using lightweight convolutional neural network","volume":"2021","author":"Huang","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"R27","unstructured":"Good machine learning practice for medical device development: guiding principles. U.S. Food and Drug Administration (FDA); 2025. URL: https:\/\/www.fda.gov\/medical-devices\/software-medical-device-samd\/good-machine-learning-practice-medical-device-development-guiding-principles [Accessed 18-05-2026]"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","DOI":"10.2196\/16620","article-title":"A contact-free, ballistocardiography-based monitoring system (Emfit QS) for measuring nocturnal heart rate and heart rate variability: validation study","volume":"5","author":"Vesterinen","journal-title":"JMIR Biomed Eng"},{"key":"R29","doi-asserted-by":"crossref","unstructured":"Clemente J Valero M Li F Wang C Song W . Helena: real-time contact-free monitoring of sleep activities and events around the bed. Presented at: 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom); Mar 23-27, 2020; Austin, TX, USA. [doi: 10.1109\/PerCom45495.2020.9127369]","DOI":"10.1109\/PerCom45495.2020.9127369"},{"issue":"7","key":"R30","doi-asserted-by":"publisher","first-page":"075005","DOI":"10.1088\/1361-6579\/ac10aa","article-title":"Heart rate estimation from ballistocardiographic signals using deep learning","volume":"42","author":"Pr\u00f6ll","journal-title":"Physiol Meas"},{"issue":"9","key":"R31","doi-asserted-by":"publisher","first-page":"3373","DOI":"10.1109\/JBHI.2021.3066885","article-title":"Accurate ballistocardiogram based heart rate estimation using an array of load cells in a hospital bed","volume":"25","author":"Jung","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"R32","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1097\/ALN.0000000000003029","article-title":"Vital signs monitoring with wearable sensors in high-risk surgical patients: a clinical validation study","volume":"132","author":"Breteler","journal-title":"Anesthesiology"},{"issue":"4","key":"R33","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.5664\/jcsm.9754","article-title":"A validation study of a ballistocardiograph sleep tracker against polysomnography","volume":"18","author":"Kholghi","journal-title":"J Clin Sleep Med"},{"issue":"5","key":"R34","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e27369","article-title":"Heart rate detection method based on ballistocardiogram signal of wearable device: algorithm development and validation","volume":"10","author":"Geng","journal-title":"Heliyon"},{"issue":"7","key":"R35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0272072","article-title":"Contactless continuous heart rate monitoring system using ballistocardiography","volume":"17","author":"Sumali","journal-title":"PLoS ONE"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1201722","article-title":"Non-invasive monitoring of cardiac function through ballistocardiogram: an algorithm integrating short-time Fourier transform and ensemble empirical mode decomposition","volume":"14","author":"Feng","journal-title":"Front Physiol"},{"key":"R37","doi-asserted-by":"crossref","unstructured":"Pino EJ Chavez JAP Aqueveque P . BCG algorithm for unobtrusive heart rate monitoring. Presented at: 2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT); Nov 6-8, 2017; Bethesda, MD, USA. [doi: 10.1109\/HIC.2017.8227614]","DOI":"10.1109\/HIC.2017.8227614"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Moukadem A Finnaoui A Gassara HE Adolphe D Schacher L Dieterlen A . Time-frequency domain for BCG analysis. Presented at: 2018 International Conference on Computer and Applications (ICCA); Aug 25-26, 2018; Beirut, Lebanon. [doi: 10.1109\/COMAPP.2018.8460408]","DOI":"10.1109\/COMAPP.2018.8460408"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.3389\/fnetp.2024.1425871","article-title":"Surrogate modelling of heartbeat events for improved J-peak detection in BCG using deep learning","volume":"4","author":"Schranz","journal-title":"Front Netw Physiol"},{"key":"R40","volume":"28","author":"Choe","journal-title":"Biomed Res (Tokyo)"},{"key":"R41","doi-asserted-by":"crossref","unstructured":"Ghosh A Anand N Kaushik P Bagrodia V Pal PK Yadav R . IOT based sensor system for 24\u00d77 monitoring movement disorder symptoms using machine learning. Presented at: 2023 15th International Conference on COMmunication Systems & NETworkS (COMSNETS); Jan 3-8, 2023; Bangalore, India. [doi: 10.1109\/COMSNETS56262.2023.10041330]","DOI":"10.1109\/COMSNETS56262.2023.10041330"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.2196\/56463","article-title":"Effectiveness of remote patient monitoring equipped with an early warning system in tertiary care hospital wards: retrospective cohort study","volume":"27","author":"Lakshman","journal-title":"J Med Internet Res"}],"container-title":["JMIR Cardio"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:02:41Z","timestamp":1785430961000},"score":1,"resource":{"primary":{"URL":"https:\/\/cardio.jmir.org\/2026\/1\/e71224"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.2196\/71224","relation":{},"ISSN":["2561-1011"],"issn-type":[{"value":"2561-1011","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]},"article-number":"v10i5e71224"}}