A hybrid random forest and particle swarm optimization model for early preeclampsia detection

Abstract

Preeclampsia has become a serious medical problem in the world. Currently, there is no routine or comprehensive screening program in place for preeclampsia, which means that preventive measures are not as effective as they could be, potentially resulting in higher rates of illness and death among mothers and infant. The main purpose of this study is to predict early of preeclampsia using random forest algorithms. This study used a quantitative approach with samples 504. The data were analyzed using random forest with particle swarm optimization (PSO). Random forest have been an accuracy rate of 96.08%, for the area under the curve (AUC), precision, sensitivity, and specificity each (0.971; 97.06%; 97.06%; and 94.12%). Model significantly increased 1.39% after optimize from 94.69% to 96.08%. The design process model algorithm has been validated that have a high level of accuracy based on literature reviews. The quality of services offered will certainly influence people to utilize technology-based services more than conventional ones. Recommendation for field technology and health is building an application model for early prediction of preeclampsia based on machine learning (ML) which is an effort for health workers to provide optimal antenatal care and step in changing technology-based pregnancy checks as initial prevention for pregnant women so that preeclampsia can be avoided.