{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T04:08:45Z","timestamp":1773288525290,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T00:00:00Z","timestamp":1560902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T00:00:00Z","timestamp":1560902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Out-of-hospital cardiac arrest is a leading cause of death worldwide. Rapid diagnosis and initiation of cardiopulmonary resuscitation (CPR) is the cornerstone of therapy for victims of cardiac arrest. Yet a significant fraction of cardiac arrest victims have no chance of survival because they experience an unwitnessed event, often in the privacy of their own homes. An under-appreciated diagnostic element of cardiac arrest is the presence of agonal breathing, an audible biomarker and brainstem reflex that arises in the setting of severe hypoxia. Here, we demonstrate that a support vector machine (SVM) can classify agonal breathing instances in real-time within a bedroom environment. Using real-world labeled 9-1-1 audio of cardiac arrests, we train the SVM to accurately classify agonal breathing instances. We obtain an area under the curve (AUC) of 0.9993\u2009\u00b1\u20090.0003 and an operating point with an overall sensitivity and specificity of 97.24% (95% CI: 96.86\u201397.61%) and 99.51% (95% CI: 99.35\u201399.67%). We achieve a false positive rate between 0 and 0.14% over 82\u2009h (117,985 audio segments) of polysomnographic sleep lab data that includes snoring, hypopnea, central, and obstructive sleep apnea events. We also evaluate our classifier in home sleep environments: the false positive rate was 0\u20130.22% over 164\u2009h (236,666 audio segments) of sleep data collected across 35 different bedroom environments. We prototype our proof-of-concept contactless system using commodity smart devices (Amazon Echo and Apple iPhone) and demonstrate its effectiveness in identifying cardiac arrest-associated agonal breathing instances played over the air.<\/jats:p>","DOI":"10.1038\/s41746-019-0128-7","type":"journal-article","created":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T12:04:56Z","timestamp":1560945896000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":108,"title":["Contactless cardiac arrest detection using smart devices"],"prefix":"10.1038","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1471-6187","authenticated-orcid":false,"given":"Justin","family":"Chan","sequence":"first","affiliation":[]},{"given":"Thomas","family":"Rea","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9863-3054","authenticated-orcid":false,"given":"Shyamnath","family":"Gollakota","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9133-6922","authenticated-orcid":false,"given":"Jacob E.","family":"Sunshine","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,19]]},"reference":[{"key":"128_CR1","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1016\/S0140-6736(18)30472-0","volume":"391","author":"A Myat","year":"2018","unstructured":"Myat, A., Song, K.-J. & Rea, T. Out-of-hospital cardiac arrest: current concepts. Lancet 391, 970 (2018).","journal-title":"Lancet"},{"key":"128_CR2","first-page":"1","volume":"60","author":"B McNally","year":"2011","unstructured":"McNally, B. et al. Out-of-hospital cardiac arrest surveillance\u2014cardiac arrest registry to enhance survival (cares), United States, October 1, 2005\u2013December 31, 2010. Morb. Mortal. Wkly. Rep.: Surveill. Summ. 60, 1 (2011).","journal-title":"Morb. Mortal. Wkly. Rep.: Surveill. Summ."},{"key":"128_CR3","unstructured":"Schultz, A. M., McCoy, M. A. & Graham, R. Strategies to Improve Cardiac Arrest Survival: a time to act. (National Academies Press, Washington, DC, 2015)."},{"key":"128_CR4","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1097\/01.ccx.0000162095.08148.64","volume":"11","author":"TD Rea","year":"2005","unstructured":"Rea, T. D. Agonal respirations during cardiac arrest. Curr. Opin. Crit. Care 11, 188 (2005).","journal-title":"Curr. Opin. Crit. Care"},{"key":"128_CR5","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1203\/00006450-199903000-00010","volume":"45","author":"CF Poets","year":"1999","unstructured":"Poets, C. F., Meny, R. G., Chobanian, M. R. & Bonofiglo, R. E. Gasping and other cardiorespiratory patterns during sudden infant deaths. Pediatr. Res. 45, 350 (1999).","journal-title":"Pediatr. Res."},{"key":"128_CR6","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1113\/jphysiol.1923.sp002052","volume":"57","author":"T Lumsden","year":"1923","unstructured":"Lumsden, T. Observations on the respiratory centres in the cat. J. Physiol. 57, 153 (1923).","journal-title":"J. Physiol."},{"key":"128_CR7","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1016\/S0196-0644(03)00423-2","volume":"42","author":"SR Hauff","year":"2003","unstructured":"Hauff, S. R. et al. Factors impeding dispatcher-assisted telephone cardiopulmonary resuscitation. Ann. Emerg. Med. 42, 731 (2003).","journal-title":"Ann. Emerg. Med."},{"key":"128_CR8","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.1016\/S0196-0644(05)80062-9","volume":"21","author":"JJ Clark","year":"1992","unstructured":"Clark, J. J., Larsen, M. P., Culley, L. L., Graves, J. R. & Eisenberg, M. S. Incidence of agonal respirations in sudden cardiac arrest. Ann. Emerg. Med. 21, 1464 (1992).","journal-title":"Ann. Emerg. Med."},{"key":"128_CR9","doi-asserted-by":"crossref","unstructured":"$$\\mathop{\\mathrm{B}}\\limits^{\\circ}$$ang, A., Herlitz, J. & Martinell, S. Interaction between emergency medical dispatcher and caller in suspected out-of-hospital cardiac arrest calls with focus on agonal breathing. A review of 100 tape recordings of true cardiac arrest cases. Resuscitation 56, 25 (2003).","DOI":"10.1016\/S0300-9572(02)00278-2"},{"key":"128_CR10","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.117.005716","volume":"6","author":"S van Diepen","year":"2017","unstructured":"van Diepen, S. et al. Multistate 5-year initiative to improve care for out-of-hospital cardiac arrest: Primary results from the HeartRescue Project. J. Am. Heart Assoc. 6, e005716 (2017).","journal-title":"J. Am. Heart Assoc."},{"key":"128_CR11","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/0735-6757(86)90297-4","volume":"4","author":"MS Eisenberg","year":"1986","unstructured":"Eisenberg, M. S. et al. Identification of cardiac arrest by emergency dispatchers. Am. J. Emerg. Med. 4, 299 (1986).","journal-title":"Am. J. Emerg. Med."},{"key":"128_CR12","unstructured":"Gartner says worldwide spending on VPA-enabled wireless speakers will top $2 billion by 2020. https:\/\/www.gartner.com\/en\/newsroom\/press-releases\/2016-10-03-gartner-says-worldwide-spending-on-vpa-enabled-wireless-speakers-will-top-2-billion-by-2020 (2016)."},{"issue":"7","key":"128_CR13","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1016\/j.amjcard.2018.12.038","volume":"123","author":"Kosuke Kiyohara","year":"2019","unstructured":"Kiyohara, K. et al. Out-of-hospital cardiac arrest at home in Japan. Am. J. Cardiol. 123, 1060\u20131068 (2019).","journal-title":"The American Journal of Cardiology"},{"key":"128_CR14","unstructured":"Models for audioset: a large scale dataset of audio events. https:\/\/github.com\/tensorflow\/models\/tree\/master\/research\/audioset (2019)."},{"key":"128_CR15","unstructured":"Muda, L., Begam, M. & Elamvazuthi, I. Voice recognition algorithms using mel frequency cepstral coefficient (mfcc) and dynamic time warping (DTW) techniques. Preprint at https:\/\/arxiv.org\/abs\/1003.4083 (2010)."},{"key":"128_CR16","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1109\/TASLP.2015.2438544","volume":"23","author":"X Cui","year":"2015","unstructured":"Cui, X., Goel, V. & Kingsbury, B. Data augmentation for deep neural network acoustic modeling. IEEE\/ACM Trans. Audio, Speech Lang. Process. (TASLP) 23, 1469 (2015).","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process. (TASLP)"},{"key":"128_CR17","doi-asserted-by":"crossref","unstructured":"Wong, S. C., Gatt, A., Stamatescu, V. & McDonnell, M. D. Understanding data augmentation for classification: when to warp? Preprint at https:\/\/arxiv.org\/abs\/1609.08764 (2016).","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"128_CR18","first-page":"2579","volume":"9","author":"Lvd Maaten","year":"2008","unstructured":"Maaten, Lvd & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"128_CR19","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1016\/j.resuscitation.2009.04.013","volume":"80","author":"LP Roppolo","year":"2009","unstructured":"Roppolo, L. P. et al. Dispatcher assessments for agonal breathing improve detection of cardiac arrest. Resuscitation 80, 769 (2009).","journal-title":"Resuscitation"},{"key":"128_CR20","doi-asserted-by":"crossref","unstructured":"Lewis, M., Stubbs, B. A. & Eisenberg, M. S. Dispatcher-assisted CPR: time to identify cardiac arrest and deliver chest compression instructions. Circulation 128, 1522 (2013).","DOI":"10.1161\/CIRCULATIONAHA.113.002627"},{"key":"128_CR21","doi-asserted-by":"publisher","first-page":"S315","DOI":"10.1161\/CIR.0000000000000252","volume":"132","author":"RW Neumar","year":"2015","unstructured":"Neumar, R. W. et al. Part 1: executive summary: 2015 American Heart Association guidelines update for cardiopulmonary resuscitation and emergency cardiovascular care. Circulation 132, S315 (2015).","journal-title":"Circulation"},{"key":"128_CR22","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.resuscitation.2018.02.004","volume":"125","author":"M Pape","year":"2018","unstructured":"Pape, M. et al. Survival after out-of-hospital cardiac arrest in nursing homes\u2014a nationwide study. Resuscitation 125, 90 (2018).","journal-title":"Resuscitation"},{"key":"128_CR23","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1016\/j.resuscitation.2019.01.015","volume":"138","author":"Stig Nikolaj Blomberg","year":"2019","unstructured":"Blomberg, S. N. et al. Machine learning as a supportive tool to recognize cardiac arrest in emergency calls. Resuscitation 138, 322\u2013329 (2019).","journal-title":"Resuscitation"},{"key":"128_CR24","doi-asserted-by":"crossref","unstructured":"Nandakumar, R., Gollakota, S. & Sunshine, J. E. Opioid overdose detection using smartphones. Sci. Transl. Med. 11, eaau8914 (2019).","DOI":"10.1126\/scitranslmed.aau8914"},{"key":"128_CR25","doi-asserted-by":"publisher","first-page":"2550","DOI":"10.1161\/CIRCULATIONAHA.108.799940","volume":"118","author":"BJ Bobrow","year":"2008","unstructured":"Bobrow, B. J. et al. Gasping during cardiac arrest in humans is frequent and associated with improved survival. Circulation 118, 2550 (2008).","journal-title":"Circulation"},{"key":"128_CR26","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aao3612","volume":"10","author":"SS Gambhir","year":"2018","unstructured":"Gambhir, S. S., Ge, T. J., Vermesh, O. & Spitler, R. Toward achieving precision health. Sci. Transl. Med. 10, eaao3612 (2018).","journal-title":"Sci. Transl. Med."},{"key":"128_CR27","doi-asserted-by":"publisher","first-page":"283rv3","DOI":"10.1126\/scitranslmed.aaa3487","volume":"7","author":"SR Steinhubl","year":"2015","unstructured":"Steinhubl, S. R., Muse, E. D. & Topol, E. J. The emerging field of mobile health. Sci. Transl. Med. 7, 283rv3 (2015).","journal-title":"Sci. Transl. Med."},{"key":"128_CR28","unstructured":"Siwicki, B. Special report: AI voice assistants making an impact in healthcare. http:\/\/provisionnetworks.net\/special-report-ai-voice-assistants-making-an-impact-in-healthcare\/ (2018)."},{"key":"128_CR29","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.1001\/jama.283.14.1829","volume":"283","author":"FJ Nieto","year":"2000","unstructured":"Nieto, F. J. et al. Association of sleep-disordered breathing, sleep apnea, and hypertension in a large community-based study. Jama 283, 1829 (2000).","journal-title":"Jama"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0128-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0128-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0128-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T18:29:11Z","timestamp":1671301751000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0128-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,19]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,12]]}},"alternative-id":["128"],"URL":"https:\/\/doi.org\/10.1038\/s41746-019-0128-7","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,19]]},"assertion":[{"value":"27 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All co-authors are inventors on a US provisional patent, submitted by the University of Washington, which is related to this work. J.C. and S.G. have equity stakes in Edus Health, Inc., which is not related to the technology presented in this manuscript. S.G. is a co-founder of Jeeva Wireless, Inc. and Sound Life Sciences, Inc. J.E.S. is a co-founder of Sound Life Sciences, Inc.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"52"}}