Comparative Analysis of Machine Learning Models for Fetal Growth and Gestational Age Prediction Using Prenatal Parameters

Accurate estimation of gestational age (GA) and fetal growth is central to prenatal care, but conventional biometric equations may be affected by biological variation and may not fully represent nonlinear relationships among fetal and maternal characteristics. This study comparatively evaluated Extreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), and an Artificial Neural Network (ANN) using the National Institute of Child Health and Human Development (NICHD) Fetal Growth Studies, Singletons cohort. After data screening, 2,641 singleton pregnancies contributed 11,428 ultrasound examinations for GA prediction and 8,214 consecutive current-to-next visit pairs for prediction of next-visit estimated fetal weight (EFW). The GA task used fetal biometry and selected maternal variables, whereas the longitudinal task additionally used current GA, current EFW, and the interval to the next scan. Participant-level data partitioning and five-fold grouped cross-validation were used to prevent leakage between repeated observations from the same pregnancy. On the independent test set, XGBoost produced the lowest error for GA prediction, with a mean absolute error (MAE) of 4.26 days, root mean squared error (RMSE) of 5.71 days, and coefficient of determination (R²) of 0.979, corresponding to a 17.8% lower MAE than the Hadlock four-parameter GA equation. For next-visit EFW prediction, XGBoost achieved an MAE of 98.4 g, RMSE of 142.6 g, and R² of 0.971, representing a 41.6% lower MAE than the NICHD velocity baseline. ANN and SVR followed in that order. The findings support the potential of gradient-boosted trees for prediction from structured longitudinal prenatal data, while external validation, formal subgroup fairness analysis, and prospective deployment evaluation remain necessary before clinical use.

gestational age; fetal growth; prenatal parameters; XGBoost; support vector regression; artificial neural network; estimated fetal weight

1. American College of Obstetricians and Gynecologists. (2017). Committee Opinion No. 700: Methods for estimating the due date. Obstetrics & Gynecology, 129(5), e150-e154. https://doi.org/10.1097/AOG.0000000000002046 [Google Scholar] [Crossref]

2. Buck Louis, G. M., Grewal, J., Albert, P. S., Sciscione, A., Wing, D. A., Grobman, W. A., et al. (2015). Racial/ethnic standards for fetal growth: The NICHD Fetal Growth Studies. American Journal of Obstetrics and Gynecology, 213(4), 449.e1-449.e41. https://doi.org/10.1016/j.ajog.2015.08.032 [Google Scholar] [Crossref]

3. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. https://doi.org/10.1145/2939672.2939785 [Google Scholar] [Crossref]

4. Espinola-Sánchez, M., Limay-Rios, A., Campaña-Acuña, A., & Sanca-Valeriano, S. (2025). Machine learning models for estimating fetal weight based on ultrasonographic biometry: Development and validation study. Digital Health, 11, 20552076251342012. https://doi.org/10.1177/20552076251342012 [Google Scholar] [Crossref]

5. Ezeaku-Ezeme, C. N., Nwankwo, U. C., Ugwu, E. C., & Akpan, A. M. (2021). A medical predictive system for comparative analysis of fetal parameters. GSC Advanced Engineering and Technology, 1(2), 21-30. https://doi.org/10.30574/gscaet.2021.1.2.0032 [Google Scholar] [Crossref]

6. Ezeaku-Ezeme, C., & Ituma, C. (2019). Review of a medical predictive system for medical analysis. International Journal of Scientific & Engineering Research, 10(8), 820-824. [Google Scholar] [Crossref]

7. Feng, M., Wan, L., Li, Z., Qing, L., & Qi, X. (2019). Fetal weight estimation via ultrasound using machine learning. IEEE Access, 7, 87783-87791. https://doi.org/10.1109/ACCESS.2019.2925803 [Google Scholar] [Crossref]

8. Grantz, K. L., Kim, S., Grobman, W. A., Newman, R., Owen, J., Skupski, D., et al. (2018). Fetal growth velocity: The NICHD Fetal Growth Studies. American Journal of Obstetrics and Gynecology, 219(3), 285.e1-285.e36. https://doi.org/10.1016/j.ajog.2018.05.016 [Google Scholar] [Crossref]

9. Grantz, K. L., Grewal, J., Kim, S., Grobman, W. A., Newman, R. B., Owen, J., et al. (2022). Unified standard for fetal growth velocity: The Eunice Kennedy Shriver National Institute of Child Health and Human Development Fetal Growth Studies. American Journal of Obstetrics and Gynecology, 227(6), 916-922.e1. https://doi.org/10.1016/j.ajog.2022.07.045 [Google Scholar] [Crossref]

10. Grewal, J., Grantz, K. L., Zhang, C., Sciscione, A., Wing, D. A., Grobman, W. A., et al. (2018). Cohort profile: NICHD Fetal Growth Studies, Singletons and Twins. International Journal of Epidemiology, 47(1), 25-25l. https://doi.org/10.1093/ije/dyx161 [Google Scholar] [Crossref]

11. Hadlock, F. P., Deter, R. L., Harrist, R. B., & Park, S. K. (1984). Estimating fetal age: Computer-assisted analysis of multiple fetal growth parameters. Radiology, 152(2), 497-501. https://doi.org/10.1148/radiology.152.2.6739822 [Google Scholar] [Crossref]

12. Hadlock, F. P., Harrist, R. B., Sharman, R. S., Deter, R. L., & Park, S. K. (1985). Estimation of fetal weight with the use of head, body, and femur measurements: A prospective study. American Journal of Obstetrics and Gynecology, 151(3), 333-337. https://doi.org/10.1016/0002-9378(85)90298-4 [Google Scholar] [Crossref]

13. Kiserud, T., Piaggio, G., Carroli, G., Widmer, M., Carvalho, J., Neerup Jensen, L., et al. (2017). The World Health Organization fetal growth charts: A multinational longitudinal study of ultrasound biometric measurements and estimated fetal weight. PLOS Medicine, 14(1), e1002220. https://doi.org/10.1371/journal.pmed.1002220 [Google Scholar] [Crossref]

14. Lee, L. H., Bradburn, E., Craik, R., et al. (2023). Machine learning for accurate estimation of fetal gestational age based on ultrasound images. npj Digital Medicine, 6, 36. https://doi.org/10.1038/s41746-023-00774-2 [Google Scholar] [Crossref]

15. Ohuma, E. O., Villar, J., Feng, Y., Xiao, L., Salomon, L. J., Barros, F. C., et al. (2021). Fetal growth velocity standards from the Fetal Growth Longitudinal Study of the INTERGROWTH-21st Project. American Journal of Obstetrics and Gynecology, 224(2), 208.e1-208.e18. https://doi.org/10.1016/j.ajog.2020.07.054 [Google Scholar] [Crossref]

16. Płotka, S. S., Grzeszczyk, M. K., Szenejko, P. I., Żebrowska, K., Szymecka-Samaha, N. A., Łęgowik, T., et al. (2023). Deep learning for estimation of fetal weight throughout the pregnancy from fetal abdominal ultrasound. American Journal of Obstetrics & Gynecology MFM, 5(12), 101182. https://doi.org/10.1016/j.ajogmf.2023.101182 [Google Scholar] [Crossref]

17. Salomon, L. J., Alfirevic, Z., da Silva Costa, F., Deter, R. L., Figueras, F., Ghi, T., et al. (2019). ISUOG Practice Guidelines: Ultrasound assessment of fetal biometry and growth. Ultrasound in Obstetrics & Gynecology, 53(6), 715-723. https://doi.org/10.1002/uog.20272 [Google Scholar] [Crossref]

18. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88 [Google Scholar] [Crossref]

19. Stringer, J. S. A., Pokaprakarn, T., Prieto, J. C., Vwalika, B., Chari, S. V., Sindano, N., et al. (2024). Diagnostic accuracy of an integrated AI tool to estimate gestational age from blind ultrasound sweeps. JAMA, 332(8), 649-657. https://doi.org/10.1001/jama.2024.10770 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet