Predicting the Risk of Preeclampsia using Soft Voting-based Ensemble and Its Recommendation

Preeclampsia is one of the leading causes of maternal deaths and pregnancy-related complications in many low-income countries. Factors related to preeclampsia include lack of prenatal care and access to medical services, lack of facilities, and inadequate diagnosis and treatment of preeclampsia patients. Early detection and prompt treatment of preeclampsia are essential for the prevention of eclampsia and other life-threatening complications. Several studies have developed the risk prediction models for preeclampsia using mobile applications and machine learning techniques. The use of a soft voting-based ensemble method and recommendation system for women at high risk of preeclampsia remains unexplored. We developed a mobile application with two functionalities of preeclampsia prediction and recommendation system for women at high risk of preeclampsia. We employed the soft voting ensemble learning for the preeclampsia prediction. We obtained a high accuracy value of 98.51% ± 0.0186% compared to the six individual classifiers (k-Nearest Neighbors, Linear SVM, RBF SVM, Gaussian Process, Multi-Layer Perceptron, and Ada Boost). Our proposed recommender system also yielded in a high accuracy value of 96.66% ± 0.0229%. Both our proposed ensemble based on soft-voting and recommendation system had small variance values, which indicated high stability.