Prediction of fetal heart disease detection using naive bayes classifier and comparing with linear regression classifier.

This work employed MRI images and unique Naive Bayes (NB) and Linear Regression (LR) algorithms to improve the accuracy and specificity of prenatal heart disease diagnosis. Materials and Strategies: This study compares Innovative Naive Bayes (N=20) to Linear Regression. The total sample size was obtained using g power with an alpha of 0.05, an enrollment ratio of 0.1, a confidence interval of 95 percent, and pre-test power of 80 percent. The groundbreaking Naive Bayes classifier has 88 percent accuracy and 84 percent specificity, whereas the Linear Regression classifier has 84 percent accuracy and 82 percent specificity. The SPSS analysis revealed statistically significant accuracy rate (p=0.001) and specificity (p=0.006). The innovative Naive Bayes classifier detects foetal cardiac disease more effectively than Linear regression, according to a study. [ABSTRACT FROM AUTHOR]