Pre-eclampsia is one of the most severe pregnancy-related disorders and continues to be a major contributor to maternal and infant morbidity globally. The early detection of this disorder is difficult owing to the intricate relationship between clinical, demographic, and pregnancy- related variables. Traditional screening methods are highly dependent on manual analysis and are often ineffective in identifying high-risk cases at an early stage. This paper proposes an automated, non-IoT, machine learning-based clinical decision support system for the early detection of pre-eclampsia using routine antenatal data. Patients are classified into low, moderate, and high-risk categories to help clinicians take early action. To improve interpretability and reliability, artificial intelligence methods are integrated to identify prominent risk factors contributing to each prediction. Experimental results show that the proposed system enhances the accuracy of early risk detection while maintaining clinical interpretability, there by bridging the gap between artificial intelligence research and maternal healthcare practice.