Cardiovascular diseases are recognized as one of the major epidemics of our time, emphasizing the need to improve the diagnosis process and enhance its accuracy. The goal of this project is to develop a predictive model for cardiovascular disease based on a carefully analyzed dataset.
We started by gaining a comprehensive understanding of cardiovascular diseases, exploring their definition, and studying their general characteristics. Then, we focused on analyzing and preprocessing our dataset using probability and statistical concepts. This involved handling missing data, dealing with outliers, and transforming variables to ensure the data is suitable for modeling.
Furthermore, we employed various data visualization techniques to extract valuable insights from the dataset. We represented these insights in the form of graphs and charts, enabling a better understanding of the relationships between different variables and their impact on cardiovascular disease prediction.
In order to predict cardiovascular disease, we employed three different algorithms: logistic regression, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). These algorithms were chosen for their ability to handle classification tasks effectively.
After training and fine-tuning each model, we evaluated their performance using appropriate evaluation metrics. All three models demonstrated reasonably acceptable accuracies, indicating their potential for predicting cardiovascular disease. However, the logistic regression model stood out as the most promising approach, showcasing superior performance compared to the other two algorithms.