Prediction of Patients’ Outcomes in Cardiovascular Disease

Cardiovascular Disease (CVD) remains a leading cause of mortality worldwide, necessitating effective prediction methods to improve patient outcomes. The study contributed to knowledge by using Support Vector Machine (SVM) to predict the outcome of patient at risk of CVD. This study explored the application of Logistic Regression (LR) and Support Vector Machine (SVM) models for predicting patient outcomes in CVD. In this analysis, patient medical record data was retrieved online from kaggle.com, comprising a dataset of 1,000 instances with 14 features relevant to cardiovascular health. Both Logistic Regression, implemented in SPSS, and SVM, executed using the R package, were employed for predictive modelling. From this study, SVM emerged as the superior model due to its ability to handle high-dimensional data and complex relationships. It has shown potentials in reducing the severity of cardiac diseases by accurately identifying at-risk individuals, thereby enabling timely intervention. The results indicated that the SVM model achieved an impressive accuracy rate of 98.7%, significantly outperforming the LR model of accuracy rate of 97%. Accurate predictions from the SVM model are vital for healthcare experts in identifying individuals at risk and formulating tailored treatment plans. Leveraging advanced machine learning techniques such as SVM can enhance the predictive capabilities regarding cardiovascular disease outcomes. This study underscores the importance of integrating these models into clinical practice to facilitate proactive healthcare measures and ultimately reduce cardiovascular morbidity and mortality rates.