Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 25, 2023Expert SystemsOpen Access

An automated energy-based signal reconstruction method using Fine-KNN achieved 99.3% accuracy in classifying five classes of heart sounds from PCG signals.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Timely and accurate detection and diagnosis of heart disorders is a significant problem as mortality rates rise, and non-invasive PCG signals can be used for automatic classification.

Does an automated energy-based signal reconstruction and Fine-KNN classification improve the accuracy of detecting heart disorders from PCG signals?

Population

Publicly available dataset of heart sounds across five diagnostic classes

Comparison

Several classification methods including Fine-KNN, SVM, Trees, and Neural Networks

Design

Machine learning algorithm development and validation study

Key result

An automated energy-based signal reconstruction method using Fine-KNN achieved 99.3% accuracy in classifying five classes of heart sounds from PCG signals.

Authors

MTMuhammad TalalSASumair AzizMKMuhammad Umar Khan

Discussion

Loading...

Member takes

Overview

May aid noninvasive PCG-based detection of heart disorders; leaves open prospective clinical validation.

Structured PICO

Does an automated energy-based signal reconstruction and Fine-KNN classification improve the accuracy of detecting heart disorders from PCG signals?

P
Population
Publicly available dataset of heart sounds (PCG signals) representing five classes: healthy, aortic stenosis, mitral stenosis, mitral regurgitation, and mitral valve prolapse.
I
Intervention
Automated energy-based signal reconstruction through Empirical Mode Decomposition (EMD) and Mel Frequency Cepstral Coefficients (MFCC) feature extraction, classified using Fine K-Nearest Neighbours (Fine-KNN).
C
Comparator
Other classification methods (Fine Tree, Quadratic Discriminant, Kernel Naive Bayes, SVM, Ensemble Bagged Trees, Neural Network) and existing state-of-the-art methods.
O
Outcome
Classification accuracy of heart disorders from PCG signals.

An automated machine learning pipeline using EMD and Fine-KNN can classify heart sounds into five categories with 99.3% accuracy, offering a potential non-invasive diagnostic tool.

Cite This Study

Talal et al. (2023) studied Heart disorders (aortic stenosis, mitral stenosis, mitral regurgitation, mitral valve prolapse). Automated energy-based signal reconstruction and Fine-KNN classification vs. Existing state-of-the-art methods was evaluated on Classification accuracy. An automated energy-based signal reconstruction method using Fine-KNN achieved 99.3% accuracy in classifying five classes of heart sounds from PCG signals.

synapsesocial.com/papers/6a7dbf01c2b228f3e18c9dd4https://doi.org/10.1111/exsy.13411
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1PCG Signal Acquisition and Classification for Heart Failure Detection: Recent Advances and Implementation of Memory-Efficient Classifiers for Edge Computing-Based Wearable Devices2024 · 3 citations
  2. 2Phonocardiogram classification Based on Machine learning and Deep learning using hybrid features extraction techniques2026
  3. 3Classification of Heart Sound Recordings (PCG) via Recurrence Plot-Derived Features and Machine Learning Techniques2026 · 4 citations
  4. 4Heart Sound Classification based on Discrete Wavelet Transform and Group-based Sparse Features of PCG Signal2023 · 1 citations
  5. 5Integrated fusion approach for multi-class heart disease classification through ECG and PCG signals with deep hybrid neural networks2025 · 29 citations