Objectives: To evaluate the performance of a real-time feedback algorithm for chest compression (CC) during cardiopulmonary resuscitation (CPR), which provides accurate estimation of the CC depth based on dual accelerometer signal processing, without assuming full CDC. Also, to explore the influence of incomplete chest decompression (CDC) on the CC depth estimation performance.
Methods: The performance of a real-time feedback algorithm for CC during CPR was evaluated by comparison with an offline algorithm using adult CPR manikin CC data obtained under various conditions.
Results: The real-time algorithm, using non-causal baselining, delivered comparable CC depth estimation accuracy to the offline algorithm on both soft and hard back support surfaces. In addition, for both algorithms incomplete CDC led to underestimation of the CC depth.
Conclusions: CPR feedback systems which utilize an assumption of full CDC may be unreliable especially in long duration CPR events where rescuer fatigue can strongly influence CC quality. In addition, these systems may increase the risk of thoracic and abdominal injury during CPR since rescuers may apply excessive compression forces due to underestimation of the CC depth when incomplete CDC occurs. Hence, there is a strong need for CPR feedback systems to accurately measure CDC in order to improve their clinical effectiveness.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.resuscitation.2014.03.003 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
AI-Driven Radiology Report Generation for Traumatic Brain Injuries.
J Imaging Inform Med
January 2025
Charles Nicolle Hospital, Tunis El Manar University, Tunis, Tunisia.
Traumatic brain injuries present significant diagnostic challenges in emergency medicine, where the timely interpretation of medical images is crucial for patient outcomes. In this paper, we propose a novel AI-based approach for automatic radiology report generation tailored to cranial trauma cases. Our model integrates an AC-BiFPN with a Transformer architecture to capture and process complex medical imaging data such as CT and MRI scans.
View Article and Find Full Text PDFLong-term engagement in smoking cessation campaign: A mixed methods randomized trial.
PLoS One
January 2025
Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada.
Introduction: A long-term engagement (LTE) intervention was embedded in a social marketing campaign aimed at motivating quit attempts among Canadian adult commercial tobacco users 35 to 64 years of age. The purpose of this study was to examine the effectiveness and appeal of LTE within a marketing campaign.
Methods: 3,199 Canadians who smoked cigarettes aged 35-64 recruited using Facebook and Instagram advertisements were randomized into Intervention and Control groups.
Public and patient involvement (PPI) in the design, execution and dissemination of a trial: the BISTRO trial.
Health Technol Assess
January 2025
School of Medicine, Keele University, Keele, Staffordshire, UK.
Background: For people receiving haemodialysis, a balance has to be struck between removing sufficient but not too much fluid during a treatment session and maintaining any remaining kidney function they might have. In the BISTRO trial, this study sought to establish if getting the balance right might be improved by the additional use of bioimpedance, a device that measures body fluid composition to help decide how much fluid to remove during dialysis. Designing and executing this trial, which incorporated complex and repeated trial procedures that would be dependent on participant engagement, presented challenges that demanded effective public and patient involvement.
View Article and Find Full Text PDFComparison of different surfaces in resuscitation quality using a real-time feedback device: A manikin study.
Turk J Emerg Med
January 2025
Department of Emergency, University of Health Sciences, Sultan 2. Abdülhamid Han Research and Training Hospital, Istanbul, Türkiye.
Objectives: Delivering chest compressions (CCs) at the targeted depth and rate is a crucial aspect of maintaining the quality of cardiopulmonary resuscitation (CPR). Although administering CCs on a firm surface is recommended, it may not always be feasible. This study aimed to determine whether the underlying surface affects CC depth and rate using a real-time feedback device.
View Article and Find Full Text PDFEvaluation of machine learning techniques for real-time prediction of implanted lower limb mechanics.
Front Bioeng Biotechnol
January 2025
Center for Orthopaedic Biomechanics, University of Denver, Denver, CO, United States.
Introduction: Accurate prediction of knee biomechanics during total knee replacement (TKR) surgery is crucial for optimal outcomes. This study investigates the application of machine learning (ML) techniques for real-time prediction of knee joint mechanics.
Methods: A validated finite element (FE) model of the lower limb was used to generate a dataset of knee joint kinematics, kinetics, and contact mechanics.
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!