Balancing cerebrovascular disease data with integrated ensemble learning and SVM-SMOTE

AbstractThe paper addresses the challenge of imbalanced classification in the context of cerebrovascular diseases, including stroke, transient ischemic attack (TIA), and vascular dementia. The imbalanced nature of cerebrovascular disease datasets poses significant challenges to conventional machine learning algorithms, making precise diagnosis and effective management difficult. The aim of the paper is to propose a novel approach, the INTEL_SS algorithm, which combines ensemble learning techniques with Support Vector Machine-Synthetic Minority Over-sampling Technique (SVM-SMOTE) to effectively handle the imbalanced nature of cerebrovascular disease datasets. The goal is to improve the accuracy of diagnosis and management of cerebrovascular diseases through advanced machine learning techniques. The proposed methodology involves several key steps, including preprocessing, SVM-SMOTE, and ensemble learning. Preprocessing techniques are used to improve the quality of the dataset, SVM-SMOTE is employed to address class imbalance, and ensemble learning methods such as bagging, boosting, and stacking are utilized to improve overall classification performance. The experimental results demonstrate that the INTEL_SS algorithm outperforms existing methods in terms of accuracy, precision, recall, F1-score, and AUC-ROC. Performance metrics are used to assess the effectiveness of the proposed approach, and the results consistently show the superiority of INTEL_SS compared to state-of-the-ar...
Source: Network Modeling Analysis in Health Informatics and Bioinformatics - Category: Bioinformatics Source Type: research