Objective: Exploit accelerometry data for an automatic, reliable, and prompt detection of spontaneous circulation during cardiac arrest, as this is both vital for patient survival and practically challenging.

Methods: We developed a machine learning algorithm to automatically predict the circulatory state during cardiopulmonary resuscitation from 4-second-long snippets of accelerometry and electrocardiogram (ECG) data from pauses of chest compressions of real-world defibrillator records. The algorithm was trained based on 422 cases from the German Resuscitation Registry, for which ground truth labels were created by a manual annotation of physicians. It uses a kernelized Support Vector Machine classifier based on 49 features, which partially reflect the correlation between accelerometry and electrocardiogram data.

Results: Evaluating 50 different test-training data splits, the proposed algorithm exhibits a balanced accuracy of 81.2%, a sensitivity of 80.6%, and a specificity of 81.8%, whereas using only ECG leads to a balanced accuracy of 76.5%, a sensitivity of 80.2%, and a specificity of 72.8%.

Conclusion: The first method employing accelerometry for pulse/no-pulse decision yields a significant increase in performance compared to single ECG-signal usage.

Significance: This shows that accelerometry provides relevant information for pulse/no-pulse decisions. In application, such an algorithm may be used to simplify retrospective annotation for quality management and, moreover, to support clinicians to assess circulatory state during cardiac arrest treatment.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TBME.2023.3242717DOI Listing

Publication Analysis

Top Keywords

cardiac arrest
12
circulatory state
8
accelerometry electrocardiogram
8
balanced accuracy
8
accelerometry
5
accelerometry-based classification
4
classification circulatory
4
circulatory states
4
states out-of-hospital
4
out-of-hospital cardiac
4

Similar Publications

When encountering severe hypoxemia that does not respond to oxygen supplementation, it is essential to consider underlying right-to-left shunting. Among various diagnostic approaches, the microbubble test via transthoracic echocardiography (TTE) is a simple, noninvasive method for detecting pulmonary arteriovenous shunts, particularly in hepatopulmonary syndrome (HPS). Although microbubbles are usually administered peripherally, using a Swan-Ganz (SG) catheter to inject microbubbles directly into the pulmonary artery may provide even more definitive diagnostic information.

View Article and Find Full Text PDF

The number of women with congenital heart disease (CHD) surviving to childbearing age is continuously growing. Although most pregnancies in this patient-population are well tolerated, there is a significant risk of potentially fatal complications. We describe a case of a previously completely asymptomatic patient who was diagnosed late during pregnancy with an inferior sinus venosus type atrial septal defect (ISV-ASD) and anomalous connection of all right pulmonary veins (PAPVC) who presented a cardiac arrest with ventricular fibrillation the day after delivery.

View Article and Find Full Text PDF

Background: Flecainide and other class-Ic antiarrhythmic drugs (AADs) are widely used in Andersen-Tawil syndrome type 1 (ATS1) patients. However, class-Ic drugs might be proarrhythmic in some cases. We investigated the molecular mechanisms of class-I AADs proarrhythmia and whether they might increase the risk of death in ATS1 patients with structurally normal hearts.

View Article and Find Full Text PDF

Objective: To evaluate the impact of cardiac arrest time (CAT) in brain-dead donors on graft and recipient outcomes following liver transplantation.

Background: The outcome of livers from brain-dead donors with a history of cardiac arrest (CA) remains controversial, and the duration of the CAT has never been evaluated.

Methods: A retrospective review of data from the Scientific Registry of Transplant Recipients between 2003 and 2022 was conducted.

View Article and Find Full Text PDF

We describe a case of profound bradyarrhythmia after sugammadex administration during ambulatory anesthesia. The patient was a 21-year-old man with autism spectrum disorder undergoing planned general anesthesia for dental treatment. After treatment completion, sugammadex was administered upon awakening, and sudden bradyarrhythmia appeared immediately.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!