Classification of QRS complexes to detect Premature Ventricular Contraction using machine learning techniques

Abstract

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.

Refactoring and performance analysis of the main CNN architectures: using false negative rate minimization to solve the clinical images melanoma detection problem

“…Finally, our results support what has already been discovered, which is that networks perform better when using the original images without any pre-processing [ 19 , 42 ]. Additional research on this aspect might aid in understanding the motivation behind this behavior.…”

“…With the development of artificial intelligence (AI) methods such as machine learning (ML) and deep learning (DL), it is now feasible to assist clinicians with a wide range of activities. In order to extract relevant data for digital health, these cutting-edge technologies are increasingly applied to biomedical challenges [ 14 , 15 ], such as proteomics [ 16 , 17 ], genetics and image and signal data classification [ 18 , 19 ], and visualization [ 20 ]. Additionally, the Internet of Medical Things (IoMT), a subset of the Internet of Things (IoT) dedicated to the connectivity of all medical equipment, expands as more medical devices are connected [ 21 ].…”

Refactoring and performance analysis of the main CNN architectures: using false negative rate minimization to solve the Clinical Images Melanoma Detection Problem

“…Finally, our results support what has already been discovered, which is that networks perform better when using the original images without any pre-processing [41,19]. Additional research on this aspect might aid in understanding the motivation behind this behavior.…”

“…With the development of artificial intelligence methods such as machine learning and deep learning, it is now feasible to assist clinicians with a wide range of activities. In order to extract relevant data for digital health, these cutting-edge technologies are increasingly applied to biomedical challenges [14,15], such as proteomics [16,17], genetics and image and signal data classification [18,19], and visualization [20]. Additionally, the Internet of Medical Things (IoMT), a subset of the Internet of Things (IoT) dedicated to the connectivity of all medical equipment, expands as more medical devices are connected [21].…”

Ensemble learning based transmission line fault classification using phasor measurement unit (PMU) data with explainable AI (XAI)

“…Therefore, power system reliability and consistency depend on the early and precise detection and categorization [20][21][22][23] of power system faults. The PMU data has widespread usage in power system fault classification [24][25][26] engaging machine learning techniques. The objective of this literature review is to give an overview of recent work on fault classification employing machine learning methods.…”