Analysis and Comparison for Prediction of Diabetic among Pregnant Women using Innovative Support Vector Machine Algorithm over Random Forest Algorithm with Improved Accuracy

Abstract

Aim: To achieve accuracy, sensitivity, and precision in AI (Artificial Intelligence) calculations for the prediction of diabetes among pregnant women, a Support Vector Machine and Random Forest algorithms were utilized. Materials and Methods: Research looked at diabetes in pregnant women using accessible data sets such as the Pima Indian dataset from the UCI website to assess the technique’s usefulness. Support Vector Machine (N=40) and Random Forest (N=40) are the two groups in this study, each having a sample size of 40. A pretest power of 80%, a threshold of 0.05, and a confidence interval of 95% were used to compute the sample size. Results: The accuracy, sensitivity, and precision of an algorithm are used to evaluate its performance. The Support Vector Machine has a 75% accuracy rate, whereas the Random Forest has a 74% accuracy rate. The sensitivity rate of the Support Vector Machine is 65%, whereas the sensitivity rate of the Random Forest is 68%. The Support Vector Machine has a precision rate of 80%, whereas the Random Forest has a precision rate of 76%. The accuracy rate is significantly different with p=0.466,p>0.05. Conclusion: When compared to the innovative Support Vector Machine Algorithm, the Random Forest approach predicts superior classifications in identifying the accuracy, sensitivity, and precision for accessing the rate for diabetes prediction among pregnant women.