Healthcare Predictive Analytics based on Machine Learning Techniques for Identifying Cardiovascular Risks Screening

Abstract

Cardiovascular diseases (CVDs) can be considered a severe concern to the universal health that affects the mortality rates. Clinical decision-making and early diagnosis can be challenged with the help of intelligent systems, which are based on data-driven models. The suggested solution would utilize the DenseNet-based deep learning model in making accurate predictions of heart disease using UCI Cleveland dataset. The data undergoes pre-processing with systematic data treatment of missing values, removal of duplicates, feature selection via correlation and standardization. In terms of predicting cardiac disease, the proposed model performs exceptionally well, with an accuracy of 99.65, precision of 98.38, recall of 98.77, and F1-score of 97.96. To provide comparative analysis, conventional machine learning classifiers such as KNN, MLP and Logistic Regression. The effectiveness model as demonstrated by the comprehensive performance gains indicate a high level of capturing of complex clinical patterns, which is effective in screening early cardiovascular risks in healthcare predictive analytics and is able to maintain model interpretability, hence making it a promising solution in early and automated heart disease detection in clinical environment.