Predictive analytics of heart disease presence with feature importance based on machine learning algorithms

Abstract

<span>Heart failure disease is a complex clinical issue which has more impact on life of human begins. Hospitals and cardiac centers frequently employ electrocardiogram (ECG) tool to assess and to identify heart failure at early stages. Healthcare professionals are very concerned about the early identification of heart disease. In this research paper we have focused on predictive analysis of cardiac disease by using machine learning algorithms. We have developed python-based software for healthcare research in this paper. This research has more significant work for tracking and establishing numerous health monitoring apps. We have demonstrated information handling that requires adjusting clear-cut portions and working with absolute factors. A quick overview of the various machine learning technologies based on heart disease diagnosis is described clearly in this research. A more reliable way for diagnosing cardiac problems is the random forest classification algorithm. This application needs data analysis, which is crucial owing to its about 95% accuracy rate across training data. We have discussed the tests and findings of the random forest classifier method, which improves the accuracy of heart disease research diagnosis.</span>

Predictive Analytics in Heart Failure Prediction: A Systematic Review

“…Researchers commonly use heart disease and heart failure datasets from the UCI machine learning repository to build predictive models to predict heart failure and the risk of heart failure. [16], [17], and [18] used the Heart Disease dataset of the UCI database to build their models and involved various machine learning algorithms in their construction. They assessed each model with classification metrics like accuracy, precision, F1 score, recall, and AUC-ROC score to discover the performance of each model.…”

A new framework to enhance healthcare monitoring using patient-centric predictive analysis

“…Therefore, this research study proposes remote monitoring with artificial intelligence (AI) and internet of things (IoT) related technologies. For this Patient-centric monitoring is needed for large-scale healthcare centers [3]. Patients are not able to get admission due to heavy crowds during heavy healthcare requests like the coronavirus disease (COVID) period and other critical-care situations, even with a few unconditional climate changes.…”