Maternal Health Risk Classification: Random Forest and Evolutionary Algorithms

Mother health is a serious issue, and accurate prediction of pregnant health risks is crucial for delivering appropriate care and minimizing mother mortality. The goal of this study was to categorize maternal health risks using the Random Forest approach in conjunction with Evolutionary Weighting for feature optimization. The dataset contained several health indicators and risk factors related to maternal well-being. After thorough testing and evaluation, the Random Forest technique with Evolutionary Weighting attained the highest classification accuracy of 82,18%. This simplified technique improved prediction capacities by identifying and selecting the most critical variables for risk assessment. The findings emphasize the importance of feature optimization by Evolutionary Weighting in generating accurate and reliable maternal health risk classification, which can aid in targeted therapies and healthcare planning to promote the well-being of pregnant women.