Use of Artificial Intelligence in Predicting Adverse Pregnancy Outcome

Authors

  • Maria Ghafoor
  • Umm E Aiman Saleem
  • Umm e Kalsoom
  • Amber Mughis
  • Iqra Rehman
  • Mahnoor Baloch

Keywords:

Artificial intelligence, pregnancy, adverse outcomes, risk prediction, maternal health, neonatal outcomes

Abstract

Background: Adverse consequences of pregnancy continue to be a significant determinant of maternal and neonatal morbidity in the low and middle-income countries. Traditional methods of antenatal risk assessment usually do not make it to distinguish the women who will develop complications later. Recent developments in artificial intelligence provide new opportunities of early risk detection based on routine clinical data.

Objective: To evaluate the performance of an artificial intelligence–based prediction model in identifying pregnancies at risk of adverse outcomes.

Methodology: The study was a prospective observational study, which was carried out in Women and Children Hospital, MTI, Dera Ismail Khan, between January 2025 and June 2025. A total of seventy two pregnant women had been enrolled and followed up till delivery. At booking, demographic, obstetric, clinical, laboratory and ultrasound parameters were noted. With the help of artificial intelligence, a model that grouped the participants into the high- and low-risk category was used before delivery. These were pregnancy and neonatal outcomes recorded at birth. The correlation between the AI prediction and the realized outcomes was evaluated by the chi-square test, the measures of diagnostic performance were also computed.

Results: Significant percentages of the participants experienced adverse pregnancy outcomes, and the most common were low birth weight and preterm birth. The adverse outcomes were much more prevalent in women who were considered as high risk based on the AI model than in women who were characterized as low risk (p < 0.001). The model showed a high overall prediction accuracy, sensitivity, and specificity, which suggest that it is a reliable predictor.


Conclusion: Artificial intelligence based risk prediction models can effectively identify pregnancies at risk of adverse outcomes using routine antenatal data. Their integration into standard antenatal care may facilitate early intervention and contribute to improved maternal and neonatal outcomes, particularly in resource-limited settings..

Downloads

Download data is not yet available.

References

1. Islam, M.N., et al., Machine learning to predict pregnancy outcomes: a systematic review, synthesizing framework and future research agenda. 2022. 22(1): p. 348.

2. Davidson, L. and M.R.J.B.i.b. Boland, Towards deep phenotyping pregnancy: a systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes. 2021. 22(5): p. bbaa369.

3. Feduniw, S., et al. Application of artificial intelligence in screening for adverse perinatal outcomes—a systematic review. in Healthcare. 2022. MDPI.

4. Silva Rocha, E.d., et al., On usage of artificial intelligence for predicting mortality during and post-pregnancy: a systematic review of literature. 2022. 22(1): p. 334.

5. Ramakrishnan, R., S. Rao, and J.-R.J.W.s.H. He, Perinatal health predictors using artificial intelligence: a review. 2021. 17: p. 17455065211046132.

6. Bertini, A., et al., Using machine learning to predict complications in pregnancy: a systematic review. 2022. 9: p. 780389.

7. Oprescu, A.M., et al., Artificial intelligence in pregnancy: A scoping review. 2020. 8: p. 181450-181484.

8. Akazawa, M., K.J.J.o.O. Hashimoto, and Gynaecology, Prediction of preterm birth using artificial intelligence: a systematic review. 2022. 42(6): p. 1662-1668.

9. Wen, J.-Y., et al., Artificial intelligence model to predict pregnancy and multiple pregnancy risk following in vitro fertilization-embryo transfer (IVF-ET). 2022. 61(5): p. 837-846.

10. Hassan, M.R., et al., A machine learning approach for prediction of pregnancy outcome following IVF treatment. 2020. 32(7): p. 2283-2297.

11. Huang, C., et al., Using deep learning in a monocentric study to characterize maternal immune environment for predicting pregnancy outcomes in the recurrent reproductive failure patients. 2021. 12: p. 642167.

12. Liu, L., et al., Machine learning algorithms to predict early pregnancy loss after in vitro fertilization-embryo transfer with fetal heart rate as a strong predictor. 2020. 196: p. 105624.

13. Wang, C.-W., et al., Predicting clinical pregnancy using clinical features and machine learning algorithms in in vitro fertilization. 2022. 17(6): p. e0267554.

14. Sufriyana, H., et al., Comparison of multivariable logistic regression and other machine learning algorithms for prognostic prediction studies in pregnancy care: systematic review and meta-analysis. 2020. 8(11): p. e16503.

15. Lee, K.-S. and K.H.J.D. Ahn, Application of artificial intelligence in early diagnosis of spontaneous preterm labor and birth. 2020. 10(9): p. 733.

16. Sufriyana, H., Y.-W. Wu, and E.C.-Y.J.E. Su, Artificial intelligence-assisted prediction of preeclampsia: Development and external validation of a nationwide health insurance dataset of the BPJS Kesehatan in Indonesia. 2020. 54.

17. Sharifi-Heris, Z., et al., Machine learning approach for preterm birth prediction using health records: systematic review. 2022. 10(4): p. e33875.

18. Arabi Belaghi, R., J. Beyene, and S.D.J.P.o. McDonald, Prediction of preterm birth in nulliparous women using logistic regression and machine learning. 2021. 16(6): p. e0252025.

19. Sun, Y.Y., et al., Increasing insulin resistance predicts adverse pregnancy outcomes in women with gestational diabetes mellitus. 2020. 12(6): p. 438-446.

20. Barbounaki, S. and V.G.J.E.J.o.M. Vivilaki, Intelligent systems in obstetrics and midwifery: Applications of machine learning. 2021. 5: p. 58.

Downloads

Published

2025-12-30

How to Cite

1.
Ghafoor M, Aiman Saleem UE, Kalsoom U e, Mughis A, Rehman I, Baloch M. Use of Artificial Intelligence in Predicting Adverse Pregnancy Outcome. J Neonatal Surg [Internet]. 2025 Dec. 30 [cited 2026 Jan. 20];14(33S):262-7. Available from: https://jneonatalsurg.com/index.php/jns/article/view/9797

Issue

Vol. 14 No. 33S (2025): Journal of Neonatal Surgery

Section

Original Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

You are free to:

  • Adapt — remix, transform, and build upon the material for any purpose, even commercially.

Terms:

  • Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
  • No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.