Deep hybrid model for maternal health risk classification in pregnancy: synergy of ANN and random forest

Abstract

Introduction: Maternal health is a critical aspect of public health that affects the wellbeing of both mothers and infants. Despite medical advancements, maternal mortality rates remain high, particularly in developing countries. AI-based models provide new ways to analyze and interpret medical data, which can ultimately improve maternal and fetal health outcomes. Methods: This study proposes a deep hybrid model for maternal health risk classification in pregnancy, which utilizes the strengths of artificial neural networks (ANN) and random forest (RF) algorithms. The proposed model combines the two algorithms to improve the accuracy and efficiency of risk classification in pregnant women. The dataset used in this study consists of features such as age, systolic and diastolic blood pressure, blood sugar, body temperature, and heart rate. The dataset is divided into training and testing sets, with 75% of the data used for training and 25% used for testing. The output of the ANN and RF classifier is considered, and a maximum probability voting system selects the output with the highest probability as the most correct. Results: Performance is evaluated using various metrics, such as accuracy, precision, recall, and F1 score. Results showed that the proposed model achieves 95% accuracy, 97% precision, 97% recall, and an F1 score of 0.97 on the testing dataset. Discussion: The deep hybrid model proposed in this study has the potential to improve the accuracy and efficiency of maternal health risk classification in pregnancy, leading to better health outcomes for pregnant women and their babies. Future research could explore the generalizability of this model to other populations, incorporate unstructured medical data, and evaluate its feasibility for clinical use.