Key result
Decision tree models using ECG HRV identify impulsive cardiac death risk with ~99% accuracy.
Why the study?
Cardiovascular diseases are causes of unexpected impulsive cardiac death, and risk identification can potentially be obtained from ECG.
Do machine learning and deep learning models using ECG data accurately predict impulsive cardiac death risk?
Do machine learning and deep learning models using ECG data accurately predict impulsive cardiac death risk?
Machine learning and deep learning models utilizing ECG-derived Heart Rate Variability and Wavelet Transform can classify impulsive cardiac death risk with high accuracy.
Requires prospective validation before clinical use; leaves open ECG-ML utility for impulsive cardiac death prediction.
Person suffering from cardiovascular diseases are reasons for unexpected Impulsive cardiac death (ISD). Impulsive cardiac death risk identification can be obtained from Electrocardiogram (ECG).This paper presents machine learning and deep learning approach based intelligent human heart monitoring. Machine learning approach based Heart Rate Variability (HRV) and Wavelet Transform (WT) methods classify obtained data into normal or abnormal subjects. The proposed research can effectively identify risk factors for Impulsive cardiac death. For implementing intelligent learning based cardiovascular diseases risk monitoring system, the proposed method use Naïve Bayes (NB), Decision Tree(DT) and k nearest neighbor (KNN) machine learning classifiers for classification. For this innovative strategy, three classifiers risk identification obtained with highest accuracy of 98.9% (KNN), 98.5(NB) and 99.3 %( DT).The obtained results shows that combined approach HRV and WT are robust and efficient for impulsive cardiac risk identification. CNN-LSTM based deep learning model predicting heart diseases highly accurate when compared to machine learning techniques. Hardware module experiment implemented for testing cardiovascular diseases based on real time ECG signal obtained from patient.
No takes yet. Share an insight, caveat, or question.
Singh et al. (2025) studied Impulsive cardiac death. Machine learning and deep learning models (NB, DT, KNN, CNN-LSTM) was evaluated on Classification accuracy for impulsive cardiac death risk identification. Machine learning classifiers using Heart Rate Variability and Wavelet Transform from ECG achieved high accuracy for impulsive cardiac death risk identification, with Decision Tree reaching 99.3%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: