A Metaheuristic Optimization Approach for Parameter Estimation in Arrhythmia Classification from Unbalanced Data

Abstract

The electrocardiogram records the heart’s electrical activity and generates a significant amount of data. The analysis of these data helps us to detect diseases and disorders via heart bio-signal abnormality classification. In unbalanced-data contexts, where the classes are not equally represented, the optimization and configuration of the classification models are highly complex, reflecting on the use of computational resources. Moreover, the performance of electrocardiogram classification depends on the approach and parameter estimation to generate the model with high accuracy, sensitivity, and precision. Previous works have proposed hybrid approaches and only a few implemented parameter optimization. Instead, they generally applied an empirical tuning of parameters at a data level or an algorithm level. Hence, a scheme, including metrics of sensitivity in a higher precision and accuracy scale, deserves special attention. In this article, a metaheuristic optimization approach for parameter estimations in arrhythmia classification from unbalanced data is presented. We selected an unbalanced subset of those databases to classify eight types of arrhythmia. It is important to highlight that we combined undersampling based on the clustering method (data level) and feature selection method (algorithmic level) to tackle the unbalanced class problem. To explore parameter estimation and improve the classification for our model, we compared two metaheuristic approaches based on differential evolution and particle swarm optimization. The final results showed an accuracy of 99.95%, a F1 score of 99.88%, a sensitivity of 99.87%, a precision of 99.89%, and a specificity of 99.99%, which are high, even in the presence of unbalanced data.

RETRACTED ARTICLE: Coronavirus herd immunity optimizer to solve classification problems

“…More comprehensive study of the effect of metaheuristic algorithms on the classification process, Mousavirad et al ( 2020 ) compared the output of 15 metaheuristic algorithms for neural network preparation, including state-of-the-art and some of the most recent algorithms, and evaluated their success on various classification algorithms. In another recent study, Carrillo-Alarcón et al ( 2020 ) addressed the unbalanced class problem, an unbalanced subset of such datasets was chosen to define eight categories of arrhythmia using combined under sampling based on the clustering approach and feature selection method. They compared two metaheuristic methods focused on differential evolution and particle swarm to investigate parameter estimation and boost sample classification.…”

Unsupervised ECG Analysis: A Review

“…However, this technique may lose relevant information that is essential for the classification task. To reduce information loss during under-sampling, Carrillo-Alarcón et al [16] clustered heartbeats in each majority class within the MIT-BIH dataset using self-organizing maps. They under-sampled the heartbeats that are farthest from the center of their clusters to ensure that the most informative heartbeats are used to train the classifier.…”

“…In addition to their application as a part of a broader knowledge discovery system, clustering techniques, in particular deep learning-based unsupervised methods, such as autoencoders [13], [14] and generative adversarial networks [15], have also been employed to overcome some challenges facing ECG supervised learning systems by resolving the imbalanced data problem [16] and low-level automation of patient-specific ECG classifiers [17]- [19]. Moreover, ECG clustering has been utilized in biometric authentication [20]- [23], ECG segmentation [24], [25], and fetal ECG extraction from abdominal ECG [26].…”

IoT based arrhythmia classification using the enhanced hunt optimization‐based deep learning

“…Recently some meta‐heuristics algorithms, such as the monarch butterfly optimization (MBO), slime mould algorithm (SMA), moth search algorithm (MSA), hunger games search (HGS), Runge Kutta method (RUN), colony predation algorithm (CPA), and Harris hawks optimization (HHO) are established and these algorithms provide several advantages whilst tuning the classifier and provide better accuracy, reducing the risk of errors and ensures the faster convergence. Moreover, the algorithms support the global optimal solution, high efficiency and reduce computational complexity associated with the classifiers (Carrillo‐Alarcón et al., 2020; Houssein et al., 2021).…”