What is the clinical evidence from this study?

Study design: Other. Population: Heart failure (n=297). Intervention: Hybrid Stacked Autoencoder and Support Vector Machines vs. Conventional SVM, L1 and L2 Regularized SVMs. Primary outcome: Accuracy, Sensitivity, Specificity, Matthews correlation coefficient (MCC).

What type of study is this?

This is a Human Clinical Trial study (also classified as: Validation Study).

What question did this study set out to answer?

The main aim is to develop an efficient expert system for accurate heart failure detection using advanced machine learning techniques.

January 10, 2026Scientific Reports0 citationsOpen Access

A hybrid stacked autoencoder and support vector machines-based expert system for heart failure detection

MKMian Muhammad KamalQuanzhou Normal University WKWahab KhanDartmouth College QSQusai Y. Shambour

Key Result

The proposed expert system for heart failure detection achieved a testing accuracy of 97.78%, sensitivity of 97.56%, specificity of 97.96%, and an MCC of 0.955.

Key Points

The main aim is to develop an efficient expert system for accurate heart failure detection using advanced machine learning techniques.
Integrated stacked autoencoder for feature extraction from heart failure risk factors.
Utilized a penalized support vector machine to refine the feature subset for classification.
Employed a non-linear support vector machine with RBF kernel for final classification and evaluation.
Validated the system using a benchmark heart failure dataset and various performance metrics.
Achieved an accuracy of 97.78% in heart failure detection.
Attained sensitivity of 97.56% and specificity of 97.96%.
Matthews correlation coefficient (MCC) reached 0.955, indicating robust performance.
Outperformed existing state-of-the-art methods with a reduced feature set.

Structured PICO

Does a hybrid stacked autoencoder and SVM-based expert system improve heart failure detection accuracy compared to conventional SVM models?

Population

297 individuals from the Cleveland Heart Disease dataset (sourced from V.A. Medical Center in Long Beach and Cleveland Clinic Foundation)

Intervention

Hybrid three-stage expert system integrating a stacked autoencoder for feature extraction, an L1-penalized SVM for feature selection, and a non-linear SVM with RBF kernel for classification

Comparator

Conventional SVM models and L1/L2 penalized linear SVMs

Outcome

Heart failure detection performance measured by accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and area under the curve (AUC)

A novel hybrid machine learning system combining stacked autoencoders and SVMs demonstrated high accuracy (97.78%) in detecting heart failure using a reduced set of clinical features.

Abstract

Heart failure (HF) detection is a critical task in medical diagnostics, often requiring accurate and efficient methods. This paper introduces a novel hybrid three stage expert system designed to improve HF detection. The proposed system integrates stacked autoencoder (AE) for feature extraction, an Formula: see text-penalized support vector machine (SVM) to select high quality subset of features from the autoencoded features, and a non-linear SVM for classification. The stacked AE extracts meaningful features from a set of HF risk factors, while the Formula: see text-SVM refines the feature set by selecting the most relevant features. In the final stage, a non-linear SVM with RBF kernel is used to classify the refined feature subset. The system is validated using a benchmark HF dataset, and its performance is evaluated using various metrics, including accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and area under the curve (AUC). Experimental results show that the proposed system achieves an accuracy of 97.78%, sensitivity of 97.56%, specificity of 97.96%, and an MCC value of 0.955, outperforming current state-of-the-art methods. The system's ability to achieve high performance with a reduced feature set highlights its efficiency. The proposed approach provides a robust solution for HF detection, offering valuable decision support for healthcare professionals.

Ask AI

Helpful

Bookmark

View Full Paper