Enhancing Heart Disease Prediction Through The Hybrid Random Forest–Gradient Boosting-Logistic Regression Model (HRFGLM): A Data-Driven Predictive Framework
TL;DR
This study suggests a methodology for early cardiovascular disease prediction using various machine learning techniques for various prediction objectives, and implemented a few models, which include Gradient Boost, Random Forests, and Linear Regression classifiers getting 75.19% accuracy.
Abstract
Heart disease is currently one of the most significant issues facing the world. One of the most significant illnesses affecting blood vessels and the heart is cardiovascular disease. The toll of death from cardiovascular disease, which is mostly caused by a lack of early disease detection, will be greatly decreased if the risk is predicted beforehand. Anticipating cardiac disease could be a significant medical breakthrough because it is so prevalent. Machine learning approaches anticipate the disease based on the severity of the patient's side effects due to the growing amount of data in the healthcare industry. This study suggests a methodology for early cardiovascular disease prediction using various machine learning techniques for various prediction objectives. Nevertheless, a number of these methods might be enhanced, such as inadequate accuracy. In our research, we have taken the cardicascular diseases dataset and implemented a few models, which include Gradient Boost, Random Forests, and Linear Regression classifiers getting 75.19% accuracy. This work has the advantage of using machine-learning techniques to improve coronary heart disease prediction performance.