What question did this study set out to answer?

The study aims to develop a hybrid machine learning approach for classifying heart sounds for early disease detection.

January 10, 2026Diagnostics0 citationsOpen Access

Heart Sound Classification with MFCCs and Wavelet Daubechies Analysis Using Machine Learning Algorithms

SGSebastian Guzmán-AlfaroUniversidad Autónoma de Zacatecas "Francisco García Salinas"KVKaren E. Villagrana-BañuelosUniversidad Autónoma de Zacatecas "Francisco García Salinas"MSManuel A. Soto-MurilloUniversidad Autónoma de Zacatecas "Francisco García Salinas"

Key Result

The support vector machine model using 26 MFCCs and Daubechies-4 wavelet coefficients achieved superior classification performance for heart sounds.

Key Points

The study aims to develop a hybrid machine learning approach for classifying heart sounds for early disease detection.
Implemented machine learning models to classify heart sounds into normal and abnormal categories.
Used the PASCAL dataset for recordings of normal, murmur, and extrasystolic heart sounds.
Extracted features using Mel-Frequency Cepstral Coefficients (MFCCs) and Daubechies wavelet analysis.
Trained four classifiers: support vector machines, logistic regression, random forests, and decision trees.
The support vector machine model with 26 MFCCs and Daubechies-4 wavelet coefficients provided the best classification performance.
All classifiers demonstrated notable results based on various evaluation metrics including accuracy and F1-score.

Structured PICO

Can a hybrid MFCC-Wavelet framework using machine learning algorithms accurately classify normal and abnormal heart sounds?

Population

Heart sound recordings (normal, murmur, and extrasystolic) from the PASCAL dataset

Intervention

Machine learning models (support vector machines, logistic regression, random forests, and decision trees) using a hybrid feature extraction approach (Mel-Frequency Cepstral Coefficients and Daubechies wavelet analysis)

Comparator

Comparison among different machine learning classifiers

Outcome

Model performance assessed by accuracy, precision, recall, specificity, F1-score, and area under curve

A hybrid MFCC-Wavelet framework using support vector machines provides a lightweight, interpretable, and computationally efficient solution for automated heart sound classification and early cardiovascular screening.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Background/Objectives: Cardiovascular diseases are the leading cause of mortality worldwide according to the World Health Organization (WHO), highlighting the need for accessible tools for early detection. Automated classification systems based on signal processing and machine learning offer a non-invasive alternative to support clinical diagnosis. Methods: This study implements and evaluates machine learning models for distinguishing normal and abnormal heart sounds using a hybrid feature extraction approach. Recordings labeled as normal, murmur, and extrasystolic were obtained from the PASCAL dataset and subsequently binarized into two classes. Multiple numerical datasets were generated through statistical features derived from Mel-Frequency Cepstral Coefficients (MFCCs) and Daubechies wavelet analysis. Each dataset was standardized and used to train four classifiers: support vector machines, logistic regression, random forests, and decision trees. Results: Model performance was assessed using accuracy, precision, recall, specificity, F1-score, and area under curve. All classifiers achieved notable results; however, the support vector machine model trained with 26 MFCCs and Daubechies-4 wavelet coefficients obtained the best performance. Conclusions: These findings demonstrate that the proposed hybrid MFCC–Wavelet framework provides competitive diagnostic accuracy and represents a lightweight, interpretable, and computationally efficient solution for computer-aided auscultation and early cardiovascular screening.

Ask AI

Helpful

Bookmark

View Full Paper