Preeclampsia is a type of hypertension condition that can be induced by a variety of circumstances during pregnancy. Typically, a diagnosis is made after 20 weeks of gestation. Several investigations employing machine learning techniques have been undertaken to diagnose preeclampsia. SVM, KNN, random forest, gradient boosting methods, and deep learning approaches are examples of these. These techniques can be implemented to detect preeclampsia earlier in an efficient way for preventing the complications caused. This paper demonstrates how hyperparameter tuning of Support vector classification of the various factors involved in the classification of preeclampsia helps in efficiently separating the patients who are prone to have preeclampsia. The selection of the hyperparameter is done through the Grid Search CV algorithm by iterative trialing of the different hyperparameters.