<![CDATA[Heart disease is one of the major causes of death, often progressing without any visible signs of the onset of the disease, thereby warranting the need for a data-intensive solution in support of its early screening. This paper proposes an analysis of risk factors for heart diseases using clinical data through the application of descriptive statistics, correlation analysis, and logistic regression. The proposed clinical data for analysis is a secondary clinical dataset that contains information about 918 patients with 12 numerical and categorical variables, with one target or dependent variable: heart disease. Descriptive statistics were employed to reveal information about the characteristics of the provided clinical data, Pearson correlation analysis, as well as Chi-Square tests, were used to examine the association of heart clinical parameters. A logistic regression analysis was employed as the core solution for determining the risk of heart diseases. This paper showed that among 918 patients, 55.3% were diagnosed with heart diseases, with a peak among middle-aged patients. Pearson correlation analysis revealed that no numerical variables were strongly correlated with heart diseases, but among the categorical variables, ChestPainType, ExerciseAngina, and ST_Slope were significantly related to heart diseases. An accuracy of 88.59% with a recall value of 0.93 for heart diseases classes was achieved by using logistic regression analysis. This paper clearly shows that an interpretive approach through statistics could potentially provide support for developing a decision support system for an early heart disease screen for cardiac patients.]]>
Copyrights © 2025
