Paper Title
Prediction of Cardiovascular Disease in Python Using Machine Learning Techniques

Abstract
The congestions at medical facilities globally have been alarming coupled with the pandemic, it has become extremely important to development faster and efficiency means of diagnosis and treatment of aliment without the need to visit a healthcare facility. Heart diseases has a high prevalent rate globally and has accounted for most death recorded. Therefore, this paper seeks to utilize machine learning algorithms in the prediction of cardiovascular disease which is a disease affecting the heart and blood vessels. Stated simply, the aim of this research is to apply classification techniques for the detection of heart disease. An attempt has been made to construct a prediction model using Neural Network, Decision Tree, and Bayesian Classifier. The methodology used is the constructive design because it is expected that a software package will be developed at a later stage for the identified highest classifier. A variety of coding frameworks and libraries, including IPython, NumPy, Pandas, Matplotlib, Python and SciPy were used in the training of the algorithms and the performance of each model was evaluated and compared to each other. The performances of the three machine learning algorithms in terms of accuracy are 85.25%, 71.43%, 91.75% for Naïve bayes, Decision tree and Neural Network respectively. The Neural Network has the highest accuracy while the lowest was Decision tree. It is recommended that Neural network should be used for the prediction of cardiovascular disease when dataset of symptoms is available. Keywords - Machine learning in healthcare, cardiovascular diseases diagnosis, NN in cardiovascular diseases, Naïve bayes in cardiovascular diseases, Decision tree in cardiovascular diseases