This research proposes a novel machine learning approach to detect cardiovascular diseases (CVDs) in electrocardiogram (ECG) images. The goal is to improve diagnostic accuracy and efficiency within the healthcare system. CVDs remain the leading cause of death globally, emphasizing the importance of early and accurate diagnosis for effective treatment. ECG signals provide valuable information for assessing cardiovascular health. The methodology utilizes advanced machine learning algorithms for classification. First, it pre-processes ECG signals to extract relevant features. The results demonstrate the machine learning model's potential as a significant diagnostic tool by showcasing its accuracy in detecting various cardiovascular illnesses from ECG images. Specifically, this research leveraged the power of machine learning to predict four major heart abnormalities: arrhythmias, myocardial infarction (heart attack), heart failure, and hypertrophic cardiomyopathy. This investigation explores how different machine learning methods perform when analyzing ECG images to identify cardiovascular diseases. The primary objective is to identify the algorithm that delivers the highest accuracy in classifying ECG images for CVD detection. Decision trees are best suited for working with data organized in tables, where each entry has specific numerical values or categories. Random forests, like decision trees, are primarily designed to handle data in a tabular format with features like numbers or categories. ECG image analysis necessitates techniques adept at recognizing intricate patterns within the pixels of an image. The ultimate goal is to identify the most effective machine learning approach for accurate CVD detection using ECG images, potentially leading to improved healthcare system efficiency and patient outcomes. In the proposed system the algorithm with the highest accuracy for CVD diagnosis using ECG image analysis is the Decision Tree, achieving 59.36% accuracy.
20 March 2026 in Biomedical and Pharmacology Journal
Early detection of Type 2 Diabetes (T2D) is perilous for remediating patient consequences and dropping long-term complications. This study proposes Scorpi-XStack, a diagnostic framework that integrates a novel bio-inspired optimization algorithm, ScorpiOpt, with stacked ensemble learning to enhance predictive accuracy. ScorpiOpt identifies the most discriminative clinical features by reducing redundancy and improving feature robustness. These selected features are used to train a weighted collaborative classifier containing Random Forest and XGBoost as ignoble learners, for which Logistic Regression is the master learner. The framework was validated on three benchmark datasets—Pima Indian Diabetes (Kaggle), clinical records from Medical City Hospital, Iraq (Mendeley Data), and the Frankfurt Diabetes dataset (GitHub/ResearchGate)—after applying ETL processing, mean/mode imputation for missing values, and z-score normalization. Classical recital remained assessed via stratiform 5-fold cross-validation, springy an accurateness of 98.54%, F1-score of 98.50%, balanced accuracy of 98.52% and AUROC of 99.86%. Compared with existing methods (85–95% accuracy range), Scorpi-XStack demonstrated consistent improvements across multiple performance metrics. While results are promising, limitations such as dataset heterogeneity, potential overfitting, and computational overhead should be noted. Further validation on larger, independent, and multi-center cohorts is necessary to confirm clinical applicability and generalizability.