MobileNetv2 achieved 99.90% accuracy on the original dataset and 99.00% on the balanced dataset for identifying premature ventricular contractions without feature extraction.
Does a machine learning approach without feature extraction accurately detect Premature Ventricular Contractions in ECG recordings?
Deep learning models, particularly MobileNetv2, can detect premature ventricular contractions from raw ECG data with extremely high accuracy without requiring manual feature extraction.
Tasa de eventos absoluta: 99.9% vs 99%
Detection of Premature Ventricular Contractions (PVC) is of crucial importance in the cardiology field, not only to improve the health system but also to reduce the workload of experts who analyze electrocardiograms (ECG) manually. PVC is a non-harmful common occurrence represented by extra heartbeats, whose diagnosis is not always easily identifiable, especially when done by long-term manual ECG analysis. In some cases, it may lead to disastrous consequences when associated with other pathologies. This work introduces an approach to identify PVCs using machine learning techniques without feature extraction and cross-validation techniques. In particular, a group of six classifiers has been used: Decision Tree, Random Forest, Long-Short Term Memory (LSTM), Bidirectional LSTM, ResNet-18, MobileNetv2, and ShuffleNet. Two types of experiments have been performed on data extracted from the MIT-BIH Arrhythmia database: (i) the original dataset and (ii) the balanced dataset. MobileNetv2 came in first in both experiments with high performance and promising results for PVCs’ final diagnosis. The final results showed 99.90% of accuracy in the first experiment and 99.00% in the second one, despite no feature detection techniques were used. The approach we used, which was focused on classification without using feature extraction and cross-validation techniques, allowed us to provide excellent performance and obtain better results. Finally, this research defines as first step toward understanding the explanations for deep learning models’ incorrect classifications.
Marco et al. (Thu,) conducted a other in Premature Ventricular Contractions (PVC). Machine learning classifiers (MobileNetv2) vs. Other classifiers (Decision Tree, Random Forest, LSTM, Bidirectional LSTM, ResNet-18, ShuffleNet) was evaluated on Accuracy of PVC detection. MobileNetv2 achieved 99.90% accuracy on the original dataset and 99.00% on the balanced dataset for identifying premature ventricular contractions without feature extraction.