What question did this study set out to answer?

The central aim is to develop a method for autonomously detecting cardiac ailments using ECG signals.

January 10, 2026International Journal of Basic and Applied Sciences0 citationsOpen Access

Autonomous Detection of Cardiac Ailments Using ECG Signals and Random Forest Classifier

GLGunturu Naga LakshmiAcharya Nagarjuna University SBS. Nagakishore BhavanamRani Durgavati University VMVasujadevi Midasala

Key Result

The Random Forest classifier achieved the highest accuracy of 91.94% for the multi-class classification of cardiac ailments among various evaluated algorithms.

Key Points

The central aim is to develop a method for autonomously detecting cardiac ailments using ECG signals.
Employs a Butterworth third-order band-pass filter for signal pre-processing.
Utilizes four-level maximal overlap discrete wavelet packet transform for feature extraction.
Applies five supervised machine learning algorithms for classification: SVM, KNN, NB, DT, and RF.
The Random Forest classifier achieved the highest accuracy of 91.94%.
Overall classification accuracies for SVM, KNN, NB, DT, and RF are 90.83%, 90.56%, 90.28%, 91.39%, and 91.94% respectively.

Structured PICO

Does a Random Forest classifier using MODWPT feature extraction accurately detect and classify cardiac ailments from ECG signals compared to other machine learning algorithms?

Population

1,200 ECG signals (300 signals each for Arrhythmia, Congestive Heart Failure, Atrial Fibrillation, and Normal Sinus Rhythm) sourced from the MIT-BIH and BIDMC databases on PhysioNet.

Intervention

Random Forest (RF) classifier utilizing a four-level maximal overlap discrete wavelet packet transform (MODWPT) technique with symlet wavelet for feature extraction from ECG signals.

Comparator

Other supervised machine learning algorithms: Support Vector Machine (SVM), K-nearest Neighbour (KNN), Naive Bayes (NB), and Decision Tree (DT).

Outcome

Overall classification accuracy of cardiac ailments.surrogate

A Random Forest machine learning model utilizing MODWPT feature extraction can autonomously classify ECG signals into normal sinus rhythm, arrhythmia, atrial fibrillation, and congestive heart failure with high accuracy.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

The ECG signal is a vital resource in diagnosing various cardiac ailments, providing crucial information for accurate decision-making re-‎garding different types of heart diseases. To achieve autonomous detection of cardiac ailments, several strategies have been proposed to ‎extract critical features from the ECG signal with utmost precision. In this study, a state-of-the-art methodology is introduced for the auto-‎matic detection of cardiac ailments. The proposed methodology encompasses three main steps: pre-processing, feature extraction, and classi-‎fication. In the pre-processing step, a Butterworth third-order band-pass filter is utilized to refine the ECG signal. For feature extraction, a ‎four-level maximal overlap discrete wavelet packet transform (MODWPT) technique is employed, utilizing the symlet wavelet as the mother ‎wavelet. In the final stage of classification, five supervised machine learning algor2 ns are applied to classify the considered three cardiac ‎ailments from the MIT-BIH database: Arrhythmia, Congestive Heart Failure, Atrial Fibrillation, and Normal Sinus Rhythm. The algorithms ‎used include Support Vector Machine (SVM), K-nearest Neighbour (KNN). Naive Bayes (NB), Decision Tree (DT), and Random Forest ‎‎(RF). These classifiers yield overall accuracies of 90.83%, 90.56%, 90.28%, 91.39%, and 91.94% respectively. Based on the results, it is ‎evident that the Random Forest classifier exhibits superior accuracy among the proposed methodology's classifiers for the multiclass classi-‎fication of cardiac ailments‎.

Ask AI

Helpful

Bookmark

View Full Paper