An important part of clinical data analysis is predicting heart disease based on
medical data. In healthcare, the data is vast and complex, and also it gives massive support in
prediction and decision-making techniques. DM turns an extensive collection into valuable
data. Several studies use data mining approaches to predict heart disease. Heart disease is the
most significant cause of death worldwide, but little research has identified the essential
features to assess heart disease risk. This research paper identifies the Significant features that
predict heart disease and then applies those features to different classification models to try
and discover the best model. The ASHAP BOOST Method is used to determine
characteristics, which specifies each feature's marginal contribution in a machine learning
model. The chosen components are employed in various Ml Algorithms, and the model's
accuracy is identified depending on different performance metrics. For performance and
accuracy in heart disease prediction, a variety of structured machine-learning algorithms were
used and compared.
Key words: component; formatting; style; styling; insert (key words)
|
