Dataset Information

Contactless cardiac arrest detection using smart devices.

ABSTRACT: 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?±?0.0003 and an operating point with an overall sensitivity and specificity of 97.24% (95% CI: 96.86-97.61%) and 99.51% (95% CI: 99.35-99.67%). We achieve a false positive rate between 0 and 0.14% over 82?h (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 0-0.22% over 164?h (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.

SUBMITTER: Chan J

PROVIDER: S-EPMC6584582 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Contactless cardiac arrest detection using smart devices.

Chan Justin J Rea Thomas T Gollakota Shyamnath S Sunshine Jacob E JE

NPJ digital medicine 20190619

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 re ...[more]

PMID: 31304398

Similar Datasets

Project description:Importance:Out-of-hospital cardiac arrest is a common scenario facing prehospital emergency medical services (EMS) professionals and nearly always involves either manual or mechanical cardiopulmonary resuscitation (CPR). Mechanical CPR devices are expensive and prior clinical trials have not provided evidence of benefit for patients when compared with manual CPR. Objectives:To investigate the use of mechanical CPR in the prehospital setting and determine whether patient demographic characteristics or geographical location is associated with its use. Design, Setting, and Participants:A retrospective cross-sectional study was performed using the 2010 through 2016 National Emergency Medical Services Information System data. Participants included all patients identified by EMS professionals as having out-of-hospital cardiac arrest. Main Outcomes and Measures:Use of CPR, categorized as manual or mechanical. Results:From 2010 to 2016, 892?022 patients (38.6% female, 60.4% male, missing for 1%; mean [SD] age, 61.1 [20.5] years) with out-of-hospital cardiac arrest were identified by EMS professionals. Overall, manual CPR was used for 618?171 patients (69.3%) and mechanical CPR was used for 45?493 patients (5.1%). The risk-standardized rate of mechanical CPR use, accounting for patient demographic and geographical characteristics, rose from 1.9% in 2010 to 8.0% in 2016 (P?<?.001). In multivariable analyses, use of mechanical CPR devices was increasingly likely over time among patients identified with out-of-hospital cardiac arrest treated by EMS professionals, increasing from an adjusted odds ratio of 1.58 (95% CI, 1.42-1.77; P?<?.001) when comparing 2011 with 2010, to an adjusted odds ratio of 11.32 (95% CI, 10.22-12.54; P?<?.001) when comparing 2016 with 2010. In addition, several other patient demographic and geographical characteristics were associated with a higher likelihood of receiving mechanical CPR, including being 65 years or older, being male, being Hispanic, as well as receiving treatment in the Northeast Census Region, in a suburban location, or in a zip code with a median annual income greater than $20?000. Conclusions and Relevance:Mechanical CPR device use increased more than 4-fold among patients with out-of-hospital cardiac arrest treated by EMS professionals. Given the high costs of mechanical CPR devices, better evidence is needed to determine whether these devices improve clinically meaningful outcomes for patients treated for out-of-hospital cardiac arrest by prehospital EMS professionals to justify the significant increase in their use.

Project description:BackgroundRecent studies describe an emerging role for percutaneous left ventricular assist devices such as Impella CP® as rescue therapy for refractory cardiac arrest. We hypothesized that the addition of mechanical chest compressions to percutaneous left ventricular assist device assisted CPR would improve hemodynamics by compressing the right ventricle and augmenting pulmonary blood flow and left ventricular filling. We performed a pilot study to test this hypothesis using a swine model of prolonged cardiac arrest.MethodsEight Yorkshire swine were anesthetized, intubated, and instrumented for hemodynamic monitoring. They were subjected to untreated ventricular fibrillation for 5.75 (SD 2.90) minutes followed by mechanical chest compressions for a mean of 20.0 (SD 5.0) minutes before initiation of percutaneous left ventricular assist device. After percutaneous left ventricular assist device initiation, mechanical chest compressions was stopped (n = 4) or continued (n = 4). Defibrillation was attempted 4, 8 and 12 minutes after initiating percutaneous left ventricular assist device circulatory support.ResultsThe percutaneous left ventricular assist device + mechanical chest compressions group had significantly higher percutaneous left ventricular assist device flow prior to return of spontaneous heartbeat at four- and twelve-minutes after percutaneous left ventricular assist device initiation, and significantly higher end tidal CO2 at 4-minutes after percutaneous left ventricular assist device initiation, when compared with the percutaneous left ventricular assist device alone group. Carotid artery flow was not significantly different between the two groups.ConclusionThe addition of mechanical chest compressions to percutaneous left ventricular assist device support during cardiac arrest may generate higher percutaneous left ventricular assist device and carotid artery flow prior to return of spontaneous heartbeat compared to percutaneous left ventricular assist device alone. Further studies are needed to determine if this approach improves other hemodynamic parameters or outcomes after prolonged cardiac arrest.

Dataset Information

Contactless cardiac arrest detection using smart devices.

Publications

Contactless cardiac arrest detection using smart devices.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets