Diagnosing Coronary Artery Disease on the Basis of Hard Ensemble Voting Optimization

Abstract

Background and Objectives: Recently, many studies have focused on the early diagnosis of coronary artery disease (CAD), which is one of the leading causes of cardiac-associated death worldwide. The effectiveness of the most important features influencing disease diagnosis determines the performance of machine learning systems that can allow for timely and accurate treatment. We performed a Hybrid ML framework based on hard ensemble voting optimization (HEVO) to classify patients with CAD using the Z-Alizadeh Sani dataset. All categorical features were converted to numerical forms, the synthetic minority oversampling technique (SMOTE) was employed to overcome imbalanced distribution between two classes in the dataset, and then, recursive feature elimination (RFE) with random forest (RF) was used to obtain the best subset of features. Materials and Methods: After solving the biased distribution in the CAD data set using the SMOTE method and finding the high correlation features that affected the classification of CAD patients. The performance of the proposed model was evaluated using grid search optimization, and the best hyperparameters were identified for developing four applications, namely, RF, AdaBoost, gradient-boosting, and extra trees based on an HEV classifier. Results: Five fold cross-validation experiments with the HEV classifier showed excellent prediction performance results with the 10 best balanced features obtained using SMOTE and feature selection. All evaluation metrics results reached > 98% with the HEV classifier, and the gradient-boosting model was the second best classification model with accuracy = 97% and F1-score = 98%. Conclusions: When compared to modern methods, the proposed method perform well in diagnosing coronary artery disease, and therefore, the proposed method can be used by medical personnel for supplementary therapy for timely, accurate, and efficient identification of CAD cases in suspected patients.

Predicting stroke and mortality in mitral stenosis with atrial flutter: A machine learning approach

“…In the sparsely populated data, the risk stratification of the GBM model is appropriate because it can improve the overall predictions by recognizing the nonlinearity in the data. Besides quick convergence and accuracy enhancement, GBM can avoid overfitting early as it can stop learning as soon as it detects overfitting, usually by cross-validation (Mohammedqasim et al, 2022). MS is a classical example of cardiovascular disease in which several factors influence the interplay between its progression (Shah & Sharma, 2022).…”

“…In previous investigations, GBM models have been used successfully for genetic disease predictions, high blood pressure prediction, and cardiovascular disease progression predictions (Chang et al, 2019 ; O'Driscoll et al, 2021 ; Shumake et al, 2021 ). When compared with other ML algorithms like ANN and SVM, GBM has shown a better predictive performance throughout their investigations (Mohammedqasim et al, 2022 ). One other study used a large database to predict outcomes of stroke and searched the performance of ANN, RF, and SVM, but no comparison with GBM was done in this investigation (Zhou et al, 2023 ).…”

“…GBM can slowly but steadily achieve optimization of its predictions by constructing a series of DTs in a step‐wise fashion which efficiently uses the abilities of classification and regression trees and boosting. The predictive performance of the GBM model is excellent when compared with conventional ML techniques, especially in accounting for the variable nonlinear mathematical correlations, meanwhile maintaining interpretability in outcomes and predictions (Mohammedqasim et al, 2022 ). In the sparsely populated data, the risk stratification of the GBM model is appropriate because it can improve the overall predictions by recognizing the nonlinearity in the data.…”

Particle Swarm Optimization-Based Random Forest Framework for the Classification of Chronic Diseases

“…In this dataset, the information about the major three arteries has been added increasing the total number of attributes to 59. The attributes are grouped into four categories: demographic information, symptoms and examination, ECG, and laboratory and echo features [40], [44]. • Exasens Dataset: The dataset was collected at Research Center Borstel, Germany.…”

Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality

“…Due to architectural complexity, defining hyperparameters manually is a difficult and time-consuming operation. The manual approach frequently fails to produce results that are close to optimal [30]. Additionally, hyperparameters may affect how effectively the method performs for advanced machine learning models.…”