Search

Cardiovascular problems have emerged as a significant concern, adversely impacting individuals across all age groups. Several recent research studies have used Machine learning (ML) techniques to design decision-making systems for the tremendous data in the medical sector. Although these works obtained promising results, most of the studies focused on small datasets. Since the size of the dataset affects algorithm performance, this study used two datasets, such as Kaggle’s heart disease dataset of over 70,000 records and UCI’s heart disease dataset of 1025 records. In addition to the old features the Pulse Pressure (PP), the Body Mass Index (BMI), and the Mean Arterial Pressure (MAP), three new features are introduced to improve the results. This paper proposes the TLV (Two-Layer Voting) model, which is an ensemble method of hard and soft voting. As part of layer 1, features are shortlisted by soft and hard voting using three statistical methods, including the ANOVA f-test, Chi-squared test, and Mutual Information. In layer 2, soft voting and hard voting performance are compared, which incorporates Multi-Layer Perceptron, Decision Tree, Support Vector Classifier, and Random Forest algorithms. Classification algorithms are hyper-tuned using the GridSearchCV method in the second layer. Using UCI’s heart disease dataset and Kaggle’s CVD dataset, the proposed TLV methodology with soft voting provided the highest accuracy of 99.03% and 88.09%, respectively. The proposed model significantly outperforms existing CAD disease prediction studies.

Testing multivariate normality is an ever-lasting interest in the goodness-of-fit area since the classical Pearson’s chi-squared test. Among the numerous approaches in the construction of tests for multivariate normality, normal characterization is one of the common approaches, which can be divided into the necessary and sufficient characterization and necessary-only characterization. We construct a test for multivariate normality by combining the necessary-only characterization and the idea of statistical representative points in this paper. The main idea is to transform a high-dimensional sample into a one-dimensional one through the necessary normal characterization and then employ the representative-point-based Pearson’s chi-squared test. A limited Monte Carlo study shows a considerable power improvement of the representative-point-based chi-square test over the traditional one. An illustrative example is given to show the supplemental function of the new test when used together with existing ones in the literature.