Ukrainian Journal Health of Woman. 2025. 3(178): 5-11. doi: 10.15574/HW.2025.3(178).511
Savchuk R. M., Ledin D. S., Zhdanovych O. I., Kolomiichenko T. V., Zhdanovych R. I.
Shupyk National Healthcare University of Ukraine, Kyiv

For citation: Savchuk RM, Ledin DS, Zhdanovych OI, Kolomiichenko TV, Zhdanovych RI. (2025). Mathematical model for predicting adverse perinatal outcomes in women with COVID-19. Ukrainian Journal Health of Woman. 3(178): 5-11. doi: 10.15574/HW.2025.3(178).511
Article received: Mar 02, 2025. Accepted for publication: May 21, 2025.

The aim: to create a mathematical model for predicting adverse perinatal outcomes in women with COVID-19.
Materials and methods. To build a mathematical prediction model, candidate indicators were selected whose frequency significantly differed in the groups of pregnant women with significant perinatal disorders (group O1, n=50) and without such disorders (group O2, n=150), and odds ratio (OR) calculations were performed. To assess the significance of the indicators in points and assign threshold values, the expert evaluation method, the Delphi method, was used.
Results. The most statistically significant indicators for predicting perinatal disorders in pregnant women with COVID-19 are laboratory indicators associated with COVID-19, indicators of disease severity, stress, the presence of anxiety and depression, and endocrine pathology. The constructed model (scale) for predicting perinatal disorders in pregnant women with COVID-19 includes 24 indicators and can be used in 2 stages: 1 – at the prehospital stage and/or at the beginning of hospitalization (9 indicators), 2 – in the dynamics of the disease at the hospital stage (15 indicators). The ease of use (scoring), as well as the established fairly high accuracy (86.7%), sensitivity (87.5%), and specificity (86.4%) of the prediction model, allow us to recommend it for use in clinical practice.
Conclusions. The implementation of a model for predicting perinatal disorders in pregnant women with COVID-19 for the purpose of early identification of high-risk patients, their timely hospitalization, and treatment will reduce the incidence of perinatal complications, morbidity, and mortality of the mother and child.
The research was carried out in accordance with the principles of the Declaration of Helsinki. The study protocol was approved by the Local Ethics Committee of the institution mentioned in the paper. The informed consent of the patient was obtained for conducting the studies.
No conflict of interests was declared by the authors.
Keywords: pregnancy, COVID-19, perinatal disorders, prediction, prevention.
REFERENCES

1. Aabakke AJ, Petersen TG, Wojdemann K et al. (2023). Risk factors for and pregnancy outcomes after SARS‐CoV‐2 in pregnancy according to disease severity: a nationwide cohort study with validation of the SARS‐CoV‐2 diagnosis. Acta obstetricia et gynecologica Scandinavica. 102.3: 282-293. https://doi.org/10.1111/aogs.14512; PMid:36695168 PMCid:PMC9951376

2. Ajirak M, Heiselman C, Fuchs A et al. (2021). Bayesian Nonparametric Dimensionality Reduction of Categorical Data for Predicting Severity of COVID-19 in Pregnant Women. Proc Eur Signal Process Conf EUSIPCO. 2021: 1980-1984. https://doi.org/10.23919/EUSIPCO54536.2021.9616021; PMid:35291722 PMCid:PMC8920026

3. Cunningham FG, Leveno KJ, Bloom SL. (2005). Williams obstetrics. 22nd ed. McGraw-Hill Professional Publishing: 1440.

4. McClymont E, Albert AY, Alton GD et al. (2022). Association of SARS-CoV-2 Infection During Pregnancy With Maternal and Perinatal Outcomes. JAMA. 327(20): 1983-1991. https://doi.org/10.1001/jama.2022.5906; PMid:35499852 PMCid:PMC9062768

5. Metz TD, Clifton RG, Hughes BL et al. (2022). Association of SARS-CoV-2 Infection With Serious Maternal Morbidity and Mortality From Obstetric Complications. JAMA. 327(8):748-759. https://doi.org/10.1001/jama.2022.1190; PMid:35129581 PMCid:PMC8822445

6. Mukhamediya A, Arupzhanov I, Zollanvari A et al. (2024). Predicting Intensive Care Unit Admission in COVID-19-Infected Pregnant Women Using Machine Learning. J Clin Med. 13(24): 7705. https://doi.org/10.3390/jcm13247705; PMid:39768627 PMCid:PMC11677355

7. Rad HS, Röhl J, Stylianou N et al. (2022). The Effects of COVID-19 on the Placenta During Pregnancy. Front Immunol. 13: 998406. https://doi.org/10.3389/fimmu.2022.998406; PMid:36159853 PMCid:PMC9496642

8. Raffetti E, Bolton T, Nolan J et al. (2024). COVID-19 diagnosis, vaccination during pregnancy, and adverse pregnancy outcomes of 865,654 women in England and Wales: a population-based cohort study. The Lancet Regional Health – Europe. 45: 101037. https://doi.org/10.1016/j.lanepe.2024.101037; PMid:39262452 PMCid:PMC11388188

9. Regan AK, Arah OA, Fell DB, Sullivan SG. (2022). SARS-CoV-2 Infection During Pregnancy and Associated Perinatal Health Outcomes: A National US Cohort Study. The Journal of Infectious Diseases. 5(225): 759-767. https://doi.org/10.1093/infdis/jiab626; PMid:34958090 PMCid:PMC8755310

10. Siston AM, Rasmussen SA, Honein MA et al. (2010). Pandemic 2009 Influenza A(H1N1) Virus Illness Among Pregnant Women in the United States. JAMA. 303(15): 1517-1525. https://doi.org/10.1001/jama.2010.479; PMid:20407061 PMCid:PMC5823273

11. Smith LH, Dollinger CY, VanderWeele TJ, Wyszynski DF, Hernández-Díaz S. (2022). Timing and severity of COVID-19 during pregnancy and risk of preterm birth in the International Registry of Coronavirus Exposure in Pregnancy. BMC Pregnancy Childbirth. 22(1): 775. https://doi.org/10.1186/s12884-022-05101-3; PMid:36258186 PMCid:PMC9578260

12. Villar J, Ariff S, Gunier RB et al. (2021). Maternal and Neonatal Morbidity and Mortality Among Pregnant Women With and Without COVID-19 Infection: The INTERCOVID Multinational Cohort Study. JAMA Pediatr. 175(8): 817-826. https://doi.org/10.1001/jamapediatrics.2021.1050; PMid:33885740 PMCid:PMC8063132

13. Young D, Houshmand B, Tan CC et al. (2023). Predicting adverse outcomes in pregnant patients positive for SARS-CoV-2: a machine learning approach- a retrospective cohort study. BMC Pregnancy Childbirth. 23(1): 553. https://doi.org/10.1186/s12884-023-05679-2; PMid:37532986 PMCid:PMC10394879

14. Yousif MG, Zeiny L, Tawfeeq S, Al-Amran F, Sadeq AM, Al-Jumeily D. (2023, Sep). Predicting perinatal outcomes in women affected by COVID-19: An artificial intelligence (AI) approach. J Med Life. 16(9): 1421-1427. https://doi.org/10.25122/jml-2023-0214; PMid:38107716 PMCid:PMC10719791