This study delves into the integration of sophisticated machine learning methodologies and in-person surveys to discern psychological health risks among pregnant women, with a primary focus on the Random Forest classifier's implementation. Pregnancy is a transformative phase marked by substantial psychological adjustments, underscoring the significance of addressing mental health issues for the well-being of both mother and child. Leveraging datasets from Kaggle and surveying 500 pregnant women, the research achieved a commendable accuracy rate of 75.08% in predicting psychological health challenges. Beyond mere accuracy, the study meticulously evaluated metrics such as precision, recall, and specificity, offering a nuanced assessment of the classifier's efficacy. It pioneers the establishment of a computerized prediction framework to aid healthcare practitioners in identifying and mitigating psychological health risks during pregnancy. Moreover, the incorporation of attribute analysis and qualitative insights gleaned from surveys enriches our comprehension, revealing correlations between mood swings, depression, and anxiety with psychological well-being. These findings significantly contribute to advancing our understanding of psychological health dynamics during pregnancy, laying a robust foundation for bespoke interventions and support mechanisms. By seamlessly amalgamating machine learning insights with real-world experiences, the research endeavors to destigmatize mental health challenges in pregnancy and enhance outcomes for both expectant mothers and their unborn offspring. This comprehensive endeavor not only sets a precedent for future research initiatives but also underscores the imperative of upholding participant privacy and confidentiality while empowering healthcare providers in maternal healthcare delivery.