Heart Failure Prediction Heart Failure Prediction Using Machine Learning

Abstract

Abstract : Cardiovascular diseases (CVDs) are the leading cause of death globally. Early detection of heart failure, a common CVD complication, is crucial for improved patient outcomes. This paper presents the development and evaluation of a machine learning model for heart failure prediction using Python Django and an XMPP database. The model utilizes various classification algorithms, including MLP Classifier, XGBoost Classifier, Random Forest Classifier, LightGBM Classifier, and K-Nearest Neighbors Classifier. We employed Sequential Feature Selection (SFS) to identify the most relevant features from the dataset, improving model accuracy and reducing user input requirements. Furthermore, Randomized Search CV was used to optimize the hyperparameters of the best-performing model (MLP Classifier), achieving a cross-validation score of 0.8899. The Django framework facilitates a user-friendly interface for data input and prediction visualization. The XMPP database provides a scalable solution for data storage and potential real-time updates. This research demonstrates the effectiveness of machine learning in predicting heart failure and highlights the potential benefits of such a system for early detection and improved cardiovascular health management IndexTerms – Heart Failure Prediction, Machine Learning, Cardiovascular Disease (CVD), Early Detection.