WombCare AI: An Integrated Machine Learning Framework for Fetal Health Classification and Birth Weight Prediction Using CTG Signal Analysis and Maternal Clinical Data
Keywords:
AdaBoost, Birth weight prediction, Cardiotocography, Clinical decision support, CTG analysis, Early risk detection, Ensemble learning, Fetal health classification, Logistic Regression, Machine learning, Maternal healthcare, Random ForestAbstract
WombCare AI focuses on improving maternal and fetal healthcare through a structured data-driven approach that supports clinical decision-making and early risk identification. The system integrates maternal clinical parameters and CTG signal data to provide a unified understanding of fetal condition and birth outcomes. Traditional monitoring approaches often remain subjective and inconsistent, which creates variability in diagnosis and delays in intervention. The framework of WombCare AI is conceptualized as a machine learning-driven construct that enables predictive analysis and classification by operationalizing clinical data patterns across layered computational processes, thereby facilitating accurate fetal assessment and birth weight estimation while contributing to improved obstetric care outcomes. The system performs two primary tasks, including birth weight prediction and fetal health classification. Regression models such as Random Forest and AdaBoost are utilized to estimate birth weight based on maternal attributes like age, weight, gestation, and lifestyle factors. Classification models, including Logistic Regression and an ensemble of support vector classifiers, Random Forest, decision tree, and AdaBoost, are applied to CTG data to categorize fetal health into Normal, Suspect, and Pathological conditions. The proposed multi-model framework achieves a macro recall of 0.921941, significantly outperforming the Logistic Regression baseline (0.757944), and achieves a test set RMSE of 0.441 in birth weight prediction, demonstrating superior generalization. This dual pipeline approach enables early detection of complications such as fetal distress and low birth weight risk, thereby enhancing diagnostic precision and supporting timely obstetric intervention.
References
S. Adeeba, K. Banujan, B. T. G. S. Kumara and S. Prasanth, “A comparative study of machine learning algorithms for predicting weight range of neonate,” 2022 International Conference on Decision Aid Sciences and Applications (DASA), Chiangrai, Thailand, 2022, pp. 869–873.
M. Feng, L. Wan, Z. Li, L. Qing, and X. Qi, “Fetal weight estimation via ultrasound using machine learning,” IEEE Access, vol. 7, pp. 87783–87791, Jan. 2019.
P. Ashorn et al., “Small vulnerable newborns—big potential for impact,” The Lancet, vol. 401, no. 10389, pp. 1692–1706, May 2023.
Manohar Pavanya et al., “Prediction of birthweight with early and mid-pregnancy antenatal markers utilising machine learning and explainable artificial intelligence,” Scientific Reports, vol. 15, Jul. 2025.
A. Abubakari, G. Kynast-Wolf, and A. Jahn, “Prevalence of abnormal birth weight and related factors in Northern region, Ghana,” BMC Pregnancy and Childbirth, vol. 15, Dec. 2015.
S. V. Gill, T. A. May-Benson, A. Teasdale, and E. G. Munsell, “Birth and developmental correlates of birth weight in a sample of children with potential sensory processing disorder,” BMC Pediatrics, vol. 13, Feb. 2013.
S. M. A. Islam Pollob, Md. M. Abedin, Md. T. Islam, Md. M. Islam, and Md. Maniruzzaman, “Predicting risks of low birth weight in Bangladesh with machine learning,” PLOS ONE, vol. 17, no. 5, May 2022.
W. Khan et al., “Infant birth weight estimation and low birth weight classification in United Arab Emirates using machine learning algorithms,” Scientific Reports, vol. 12, Jul. 2022.
W. T. Bekele, “Machine learning algorithms for predicting low birth weight in Ethiopia,” BMC Medical Informatics and Decision Making, vol. 22, Sep. 2022.
L. Belbasis, M. D. Savvidou, C. Kanu, E. Evangelou, and I. Tzoulaki, “Birth weight in relation to health and disease in later life: An umbrella review of systematic reviews and meta-analyses,” BMC Medicine, vol. 14, Sep. 2016.
J. Li et al., “Comparison of different machine learning approaches to predict small for gestational age infants,” in IEEE Transactions on Big Data, vol. 6, no. 2, pp. 334–346, June 2020.
N. Chandrasekaran, “Induction of labor for a suspected large-for-gestational-age/macrosomic fetus,” Best Practice & Research Clinical Obstetrics & Gynaecology, vol. 77, pp. 110–118, Nov. 2021.
M. Dodd and P. G. Lindqvist, “Antenatal awareness and obstetric outcomes in large fetuses: A retrospective evaluation,” European Journal of Obstetrics, Gynecology, and Reproductive Biology, vol. 256, pp. 314–319, Jan. 2021.
L. Dittkrist et al., “Percent error of ultrasound examination to estimate fetal weight at term in different categories of birth weight with focus on maternal diabetes and obesity,” BMC Pregnancy and Childbirth, vol. 22, Mar. 2022.
K. H. Ahn et al., “Predictors of newborn’s weight for height: A machine learning study using nationwide multicenter ultrasound data,” Diagnostics, vol. 11, no. 7, Jul. 2021.
J. Tao, Z. Yuan, L. Sun, K. Yu, and Z. Zhang, “Fetal birthweight prediction with measured data by a temporal machine learning method,” BMC Medical Informatics & Decision Making, vol. 21, Jan. 2021.
G. Bhavani and C. Jeyalakshmi, “Prediction of clinical risk factors in pregnancy using optimized neural network scheme,” Placenta, vol. 163, pp. 33–42, Apr. 2025.
G. Mohana Priya and S. K. B. Sangeetha, “Improved birthweight prediction with feature‐wise linear modulation, GRU, and attention mechanism in ultrasound data,” Journal of Ultrasound in Medicine, vol. 44, no. 4, pp. 711–725, Dec. 2024.
J. Gao et al., “Fetal birth weight prediction in the third trimester: Retrospective cohort study and development of an ensemble model,” JMIR Pediatrics and Parenting, vol. 8, Mar. 2025.
Hacettepe University Institute of Population Studies, T.R. Presidency of Turkey Directorate of Strategy and Budget, and TUBITAK, Turkey Demographic and Health Survey 2018. Ankara, Turkey, 2019.
