Key result
Machine learning approaches using MLPPCA and CHI-square achieve ~98% heart disease prediction accuracy.
Why the study?
Detecting heart disease at an early stage is difficult and challenging for physicians given diverse patient attributes, motivating the use of machine learning to identify disease early.
Machine learning approaches using MLPPCA and CHI-square can detect heart disease with high accuracy (>98%) using the UCI ML repository dataset.
Detection of heart disease at early stage is very difficult and challenging task by the medical physicians without the examination of disease. Heart disease is common disease consistently around the world. That is the reason coronary illness is a basic concern that should be tended to. Nonetheless, it very well may be hard to identify heart disease in view of the different attributes of patient, for example, hypersensitivity, HDL and VDL levels, unusual hear rate. In this manner, the medical field, machine learning can be in distinguishing infections almost immediately and detects HD at early stages. This current work insights prediction for Heart disease by Machine Learning (ML). The aim of this at early stages detect the heart disease by selection some relevant features from the dataset. In this work multiple machine learning classifiers are using to for obtaining better results. The dataset for cardiovascular disease has taken from the UCI ML repository prepare model. Regression and chi square tests are implemented toward recognize main highlights to indentify heart disease. The current approaches MLPPCA and CHI-square give the most accurate heart prediction outcomes 98.08 and 98.25% for the heart disease patients. This method helps in medical science to early detection of disease and obtained accuracy
No takes yet. Share an insight, caveat, or question.
Aggarwal et al. (2022) studied Heart disease. MLPPCA and CHI-square machine learning models was evaluated on Heart disease prediction accuracy. Machine learning approaches using MLPPCA and CHI-square achieved heart disease prediction accuracies of 98.08% and 98.25%, respectively.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: