A Support Vector Machine Classifier Approach for Predicting Preeclampsia and Gestational Hypertension

Early detection and accurate prediction of gestational hypertension/preeclampsia are crucial at present for the health and well-being of pregnant women and the fetus. Preeclampsia is a condition characterized by high blood pressure, and it gives a sign of damage to other organ systems such as the liver and kidneys. Observing the blood pressure levels such as systolic blood pressure (SBP) and diastolic blood pressure (DBP) are a primary aspect of identifying and distinguishing between individuals with preeclampsia, hypertension, or normal blood pressure levels during pregnancy and monitoring these parameters is a routine part of prenatal care. Regular prenatal care and blood pressure monitoring help health-care providers identify any concerning trends early on, allowing for timely intervention and appropriate management to minimize risks associated with preeclampsia and gestational hypertension. In this work, the multi-kernel classifier, support vector machines (SVM) is primarily used to evaluate the impact of SBP and DBP levels and some other factors viz. age, blood sugar, body temperature, heart rate, etc. The kernel types of SVM such as linear, sigmoid, radial basis function (RBF), and polynomial were used to achieve the performance outcomes such as Kappa statistics, true-positive rate (TP rate), false-positive rate (FP rate), precision, recall, F measure, accuracy, and receiver operating characteristic (ROC). The findings demonstrated that linear and polynomial kernels outperformed well for all the test cases of the problem taken.