The Naive Bayes classifier predicted heart disease with an accuracy of 98.35%, outperforming Decision Stump (72.28%) and Linear Regression (71.11%) algorithms on the Cleveland dataset.
The Naive Bayes algorithm demonstrated high accuracy (98.35%) in predicting heart disease using the Cleveland dataset, outperforming Decision Stump and Linear Regression.
Absolute Event Rate: 98.35% vs 72.28%
Introduction: Improvised modern lifestyle with more fascination towards fast food causes severe anxieties over human health standards. This renders the society to visit the physicians often, which in turn generates terabytes of diagnostic data. The stored data on critical mining using algorithm provides a wealth of information to clinicians and back them to execute a better treatment. Heart disease rank's first among the charted ailments due to its life-threatening concerns.
Sivakami et al. (Fri,) conducted a other in Heart disease (n=303). Naive Bayes classifier vs. Decision Stump and Linear Regression algorithms was evaluated on Classification accuracy. The Naive Bayes classifier predicted heart disease with an accuracy of 98.35%, outperforming Decision Stump (72.28%) and Linear Regression (71.11%) algorithms on the Cleveland dataset.