What is the clinical evidence from this study?

Study design: Other. Population: Cardiovascular diseases. Intervention: XGBoost with engineered acoustic features vs. Hybrid CNN + LSTM and Wav2Vec embeddings. Primary outcome: Multi-class classification accuracy of five heart sound categories.

What does this research mean for the field?

XGBoost achieved an accuracy of 99% in heart sound classification, outperforming the hybrid CNN + LSTM model at 98%, underscoring the value of feature engineering. Novelty: ClaimNovelty.CONFIRMATORY. Consensus alignment: ConsensusAlignment.SUPPORTS_CONSENSUS.

What question did this study set out to answer?

The aim is to improve the early detection of cardiovascular diseases using heart sound classification and advanced machine learning models.

January 21, 2026Sensors0 citationsOpen Access

Heart Sound Classification for Early Detection of Cardiovascular Diseases Using XGBoost and Engineered Acoustic Features

PKP. P. Satya KarthikeyaAmrita Vishwa Vidyapeetham PRP. RohithAmrita Vishwa Vidyapeetham BKB. KarthikeyaAmrita Vishwa Vidyapeetham

Key Result

XGBoost trained on engineered acoustic features achieved 99% accuracy in classifying heart sounds, outperforming a hybrid CNN+LSTM model (98%) and Wav2Vec-based models.

Key Points

The aim is to improve the early detection of cardiovascular diseases using heart sound classification and advanced machine learning models.
Combined traditional acoustic features and Wav2Vec embeddings for classification.
Extracted ten engineered acoustic features from heart sounds.
Evaluated four model configurations: CNN + LSTM and XGBoost with both feature sets.
Assessed models with hyperparameter tuning and cross-validation on a held-out test set.
XGBoost achieved the highest accuracy of 99% for heart sound classification.
Models using regular features consistently outperformed those using Wav2Vec embeddings.
The hybrid model performed slightly lower at 98% accuracy.

Structured PICO

Does training machine learning models (XGBoost) on engineered acoustic features improve heart sound classification accuracy compared to Wav2Vec embeddings?

Population

Heart sound recordings categorized into five classes

Exposure

XGBoost and hybrid CNN+LSTM models trained with ten engineered acoustic features (Log Mel, MFCC, delta, delta-delta, chroma, discrete wavelet transform, zero-crossing rate, energy, spectral centroid, and temporal flatness)

Comparator

Models trained with transformer-based Wav2Vec embeddings

Outcome

Multi-class classification accuracysurrogate

Domain-specific feature engineering combined with XGBoost provides highly accurate (99%) multi-class classification of heart sounds, outperforming transformer-based embeddings.

Main Result

Absolute Event Rate: 99% vs 98%

Abstract

Heart sound-based detection of cardiovascular diseases is a critical task in clinical diagnostics, where early and accurate identification can significantly improve patient outcomes. In this study, we investigate the effectiveness of combining traditional acoustic features and transformer-based Wav2Vec embeddings with advanced machine learning models for multi-class classification of five heart sound categories. Ten engineered acoustic features, i.e., Log Mel, MFCC, delta, delta-delta, chroma, discrete wavelet transform, zero-crossing rate, energy, spectral centroid, and temporal flatness, were extracted as regular features. Four model configurations were evaluated: a hybrid CNN + LSTM and XGBoost trained with either regular features or Wav2Vec embeddings. Models were assessed using a held-out test set with hyperparameter tuning and cross-validation. Results demonstrate that models trained on regular features consistently outperform Wav2Vec-based models, with XGBoost achieving the highest accuracy of 99%, surpassing the hybrid model at 98%. These findings highlight the importance of domain-specific feature engineering and the effectiveness of ensemble learning with XGBoost for robust and accurate heart sound classification, offering a promising approach for early detection and intervention in cardiovascular diseases.

问 AI

Bookmark

View Full Paper