AI-Driven Predictive Modelling and Machine Learning Framework for Classification of Fetal Health Conditions

Abstract: Fetal health monitoring plays a crucial role in ensuring maternal and neonatal well-being by enabling the early identification of potential complications during pregnancy. Conventional fetal assessment methods often depend on manual interpretation of cardiotocography (CTG) signals and clinical expertise, which may lead to inconsistencies and delayed diagnosis. This paper presents an AI-driven predictive modeling and machine learning framework for the classification of fetal health conditions using cardiotocography data. The proposed framework integrates data preprocessing, feature engineering, and machine learning algorithms to classify fetal conditions into Normal, Suspect, and Pathological categories. Various predictive models including Random Forest, Support Vector Machine, Decision Tree, and XGBoost are employed and evaluated based on performance metrics such as accuracy, precision, recall, and F1-score. The framework enhances diagnostic reliability and supports healthcare professionals in making timely clinical decisions. Experimental results demonstrate that the proposed system achieves high classification accuracy and provides an efficient solution for intelligent fetal health assessment.

Keywords: Fetal Health Classification, Machine Learning, Predictive Modeling, Cardiotocography, Artificial Intelligence, Healthcare Analytics, Clinical Decision Support.