Early detection of preeclampsia, a potentially life-threatening pregnancy complication, is critical for maternal and fetal well-being. This study offers an innovative approach to early detection using optimized ensemble learning and an interactive R-Shiny application. Genetic Algorithms are employed to enhance the performance of ensemble models-Random Forest. By optimizing model hyperparameters, feature selection, and the ensemble combination, we achieve superior predictive accuracy. The optimal values for the mtry parameter of Random Forest are 4 and ntree of 9. This outcome was achieved by setting the critical number of individuals to survive at each generation to 2, with a crossover probability of 0.8 and a mutation probability of 0.1. Additionally, an R-Shiny application is developed to provide healthcare professionals with an accessible tool for risk assessment and early intervention. The combination of Genetic Algorithms and ensemble learning, complemented by a user-friendly interface, offers a promising solution for timely preeclampsia diagnosis and proactive healthcare management.