Sudden cardiac deathSudden Cardiac Death (SCD) is a prominent cause of death around the world. SCD leads to unconsciousness and death within a few minutes. The effectiveness of available SCD predictionPrediction algorithms is minimal due to their limitations. Therefore, developing an accurate and precise methodology is essential for accurate early-stage SCD predictionPrediction, which will save many lives worldwide. In order to identify the risk of SCD in patients with congestive heart failure (CHF), atrial fibrillation (AF), coronary artery disease (CAD), ventricular tachyarrhythmia (VT), and normal sinus rhythm (NSR) subjects using heart rate variabilityHeart Rate Variability (HRV) analysis, this study proposes a new methodology for detecting SCD 8 min before its onset. A total of 124 HRV signals of six classes acquired from the PhysioBank were used to extract 35 features for each subject in the time-domain, frequency, domain, and nonlinearNonlinear methods. A mutual information-based feature selectionMutual Information-Based Feature Selection algorithm is used to select the optimal number of features for better performance. We detected SCD 8 min before its onset using the Light gradient boosting (LightGBMLightGBM) classifier, with accuracy, sensitivity, specificity, and precision of 95.52%, 94.96%, 99.08%, and 95.87%, respectively. These results indicate that the performance of the proposed method is superior to that of existing ones in terms of the number of classes, predictionPrediction time, and accuracy. The experimental results acquired by evaluating the HRV signal showed substantial results for 8 min before SCD onset, which will be helpful in automatic diagnostic systems and intensive care units (ICUs) detecting those at risk of developing SCD. Clinicians may have enough time to respond to treatment using this methodology. As a result, the proposed technique can be a valuable tool for increasing survival rates.
Early Prediction of Sudden Cardiac Death Using Optimal Heart Rate Variability Features Based on Mutual Information
Lect. Notes Electrical Eng.
International Conference on Robotics, Control, Automation and Artificial Intelligence ; 2022 November 24, 2022 - November 26, 2022
2023-11-18
13 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Early warning and first aid interconnection system for sudden death of heart disease
Europäisches Patentamt | 2023
|Europäisches Patentamt | 2023
|Sudden Natural Death While Driving
British Library Conference Proceedings | 1997
|Sudden death from tourniquet shock
Elsevier | 1993
|