This study illustrates a novel application of machine learning: the prediction of sudden cardiac arrest (SCA) using HRV features. SCA is a life-threatening condition that calls for rapid medical intervention. Patients with SCA who get an early diagnosis have a far better prognosis. HRV known as Heart Rate Variability analysis is used in this study to diagnose cardiac abnormalities and assess autonomic nervous system dysfunction. Prediction models built with machine learning algorithms might aid clinicians in identifying people at risk for cardiac arrest. The strategy involves gathering and preparing data, extracting and choosing features, and training and evaluating models. The experimental prediction performance of the proposed model may be seen using a variety of performance metrics including accuracy, sensitivity, and specificity. The clinical significance of the proposed machine learning approach to SCA prediction is addressed, along with its limitations and recommended future lines of inquiry.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Heart Rate Variability-Based Machine Learning Approach for Sudden Cardiac Arrest Prediction


    Contributors:


    Publication date :

    2023-11-22


    Size :

    315504 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Method and system for notifying driver of cardiac arrest using heart rate sensor

    KIM YONG YOON | European Patent Office | 2023

    Free access


    Sudden cardiac arrest during flight in a military helicopter pilot with mitral annular disjunction

    Dean, John-Henry L. / Tunzi, Matthew A. / Kelly, Faith R. et al. | Elsevier | 2025

    Free access

    Short-term Exposure to Microgravity and the Associated Risk of Sudden Cardiac Arrest: Implications for Commercial Spaceflight

    Laing, K.J.C. / Russamano, T. / European Space Agency | British Library Conference Proceedings | 2013