Data mining and Machine learning based foetus health analysis system

This paper presented a machine learning based fetus health monitoring system using structured CTG data. The proposed framework achieves high classification accuracy and improves detection of pathological fetal conditions. Future work includes integrating deep learning models for raw CTG waveform analysis, incorporating real time IoT based fetal monitoring devices, applying explainable AI techniques for improved clinical transparency, and implementing federated learning approaches for privacy preserving multihospital collaboration.

[1]    Y. Kumar et al., “Ensemble Learning for Fetal Health Classification Using CTG Data,” IEEE Access, 2023.   [2]    L. Chen et al., “Hybrid Machine Learning Model for Prenatal Risk Prediction,” IEEE Transactions on Artificial Intelligence, 2024.   [3]    S. Patel et al., “Boosting Based Clinical Risk Classification Systems,” IEEE Access, 2023. [4]    R. Sharma et al., “Imbalanced Medical Data Classification Using Cost Sensitive Learning,” IEEE Journal of Biomedical and Health Informatics, 2024.   [5]    H. Lee et al., “Explainable Machine Learning for Clinical Decision Support Systems,” IEEE Transactions on Neural Networks and Learning Systems, 2025.   [6]    A. Singh et al., “Lightweight Predictive Models for Real Time Healthcare Monitoring,” IEEE Internet of Things Journal, 2026.   [7]    T. Nguyen et al., “Optimized Gradient Boosting for Healthcare Risk Prediction,” IEEE Access, 2025.   [8]    M. Roy et al., “Feature Selection Techniques for Medical Data Classification,” IEEE Access, 2024.   [9]    P. Wang et al., “Robust Clinical Data Modeling Using Machine Learning,” IEEE Transactions on Artificial Intelligence, 2025.   [10] J. Brown et al., “AI Based Decision Support Systems in Obstetrics,” IEEE Access, 2026.