Towards Proactive Measures and Unbiased Early Detection in Cardiovascular Healthcare

Cardiovascular diseases (CVDs) affect both health and economic well-being, hence they introduce many challenges globally. This study highlights on the importance of proactive healthcare measures and equitable access to early detection of CVDs, hoping to alleviate the country’s economic burden and to reduce mortality rates associated with the disease. Leveraging data from the BRFSS 2015 dataset, this work is based on the value of utilizing available information to promote public health initiatives. Through the application of machine learning techniques, including Logistic Regression (LR), Multilayer Perceptron (MLP) and Random Forest (RF), the study aims to identify the most effective predictive model for early detection of heart disease. The model was developed using LR, MLP and RF classifiers with 5-fold cross-validation on a balanced dataset. The performance of these three models was evaluated and compared using metrics such as accuracy, precision, sensitivity, specificity, F1-Score, and AUC Score. The RF model demonstrated the best performance among the three, with an accuracy of 89.68%, a precision of 0.86, a sensitivity of 0.94, a specificity of 0.85, an F1-score of 0.90 and an AUC score of 0.96. The evaluation of these models highlights the transparency and accountability in research practices, with a commitment to advancing healthcare services and technology for the betterment of individuals and communities in the country.