MATHEMATICAL MODEL FOR PREDICTING THE OCCURRENCE OF PRETERM BIRTH IN WOMEN AT RISK BASED ON THE STUDY OF ESTRADIOL
DOI:
https://doi.org/10.21272/eumj.2025;13(1):293-298Keywords:
preterm birth, pregnancy, hormones, placenta, children, mathematical model, estradiol, placental dysfunction, predictionAbstract
Preterm birth is one of the most pressing problems in modern obstetric practice, which not only endangers the life and health of newborns but also has serious consequences for women's health. They are defined as labour occurring before the 37th week of pregnancy and can be caused by a variety of factors, including biological and endocrine disorders. One of the important hormones that plays a critical role in maintaining a normal pregnancy is estradiol. Low or abnormal levels of this hormone may indicate the presence of disorders that increase the likelihood of preterm birth.
The aim of the study is to develop a mathematical model to determine the probability and percentage of prediction of preterm birth in women at risk based on the study of estradiol.
Materials and methods: The study analysed the level of estradiol in 60 women (including 30 at risk of preterm birth and 30 absolutely healthy women) who were in the Chernivtsi Regional Perinatal Centre. Estradiol levels were assessed both before and after treatment. The logistic regression method was used to develop a mathematical model for predicting preterm birth, which allows to estimate the probability of preterm birth based on changes in estradiol levels. The Welch's T-test was used to test the statistical significance of the results, which allows comparing the mean values of hormone levels before and after treatment and assessing the effectiveness of treatment measures.
Results: A one-unit increase in estradiol increased the odds of preterm birth by 0.985 times (decreased the odds of preterm birth by 1.5%).
Conclusions: The mathematical logistic regression model based on estradiol levels demonstrated an inverse relationship between estradiol levels and the probability of preterm birth, which allows predicting risk based on changes in the concentration of this hormone. An increase in estradiol levels by one unit reduces the likelihood of preterm birth by 1.5%, which opens up new opportunities to improve the prediction and management of pregnancy in women at risk.
Downloads
References
Barbounaki S, Sarantaki A. Construction and validation of a preterm birth risk assessment model using fuzzy analytic hierarchy process. Bosn J Basic Med Sci. 2022;22(2):291-299. https://doi.org/10.17305/bjbms.2021.6431
Conde-Agudelo A, Romero R. Does vaginal progesterone prevent recurrent preterm birth in women with a singleton gestation and a history of spontaneous preterm birth? Evidence from a systematic review and meta-analysis. Am J Obstet Gynecol. 2022;227(3):440-461. https://doi.org/10.1016/j.ajog.2022.04.023
Creswell L, Rolnik DL, Lindow SW, O'Gorman N. Preterm Birth: Screening and Prediction. Int J Womens Health. 2023;15:1981-1997. https://doi.org/10.2147/ijwh.s436624
Defilipo ÉC, Chagas PSC, Drumond CM, Ribeiro LC. Factors associated with premature birth: a case-control study. Rev Paul Pediatr. 2022;40:e2020486. https://doi.org/10.1590/1984-0462/2022/40/2020486in
Hebert CL, Nattino G, Gabbe SG, Gabbe PT, Benedict J, Philips G, et al. Predictive Models for Very Preterm Birth: Developing a Point-of-Care Tool. Am J Perinatol. 2022;39(1):92-98. https://doi.org/10.1055/s-0040-1714423
Hryshchenko OV, Korovai SV, Lakhno IV. Effectiveness of preventive methods and their combinations in the prevention of premature birth. Problems of uninterrupted medical training and science. 2021;2:18-21. https://doi.org/10.31071/promedosvity2021.02.018
Huang X, Zhou Y, Liu B, Huang Y, Wang M, Li N, et al. Prediction model for spontaneous preterm birth less than 32 weeks of gestation in low-risk women with mid-trimester short cervical length: a retrospective cohort study. BMC Pregnancy Childbirth. 2024;24(1):621. https://doi.org/10.1186/s12884-024-06822-3
Jiang B, He WC, Yu JY, Wei SS, Zhang XJ. History of IUD utilization and the risk of preterm birth: a cohort study. Arch Gynecol Obstet. 2022;305(2):349-358. https://doi.org/10.1007/s00404-021-06158-9
Kalinovska IV, Lisova KM, Kozar OM. [Ultrasound characteristics of the development of the fetoplacentary complex in premier pregnancy]. Neonatology, surgery and perinatal medicine. 2022;12(3):29-35. https://doi.org/10.24061/2413-4260.XII.3.45.2022.4
Korovai S, Lakhno I. [Increasing efficiency of preterm birth prediction]. The Journal of VN Karazin Kharkiv National University. Series Medicine. 2021;42:51-57. http://dx.doi.org/10.26565/2313-6693-2021-42-06
Petrenko Ye, Strubchevka KP. [Preterm labor: issues of prognosis, prevention and management (Literature rewiew)]. Women's Reproductive Health. 2021;3:57-64. https://doi.org/10.30841/2708-8731.3.2021.234245
Ran Y, He J, Peng W, Liu Z, Mei Y, Zhou Y, et al. Development and validation of a transcriptomic signature-based model as the predictive, preventive, and personalized medical strategy for preterm birth within 7 days in threatened preterm labor women. EPMA J. 2022;13(1):87-106. https://doi.org/10.1007/s13167-021-00268-9
Rocha ADS, Falcão IR, Teixeira CSS, Alves FJO, Ferreira AJF, Silva NJ, et al. Determinants of preterm birth: proposal for a hierarchical theoretical model. Cien Saude Colet. 2022;27(8):3139-3152. https://doi.org/10.1590/1413-81232022278.03232022
Schmiedecke SS, Thagard AS, Edwards SM, Talley RL, Dornisch EM, Damicis JR, et al. Estrogen receptor 1 appears essential for fetal viability in a murine model of premature birth. Am J Reprod Immunol. 2023;89(3):e13662. https://doi.org/10.1111/aji.13662
Stock SJ, Horne M, Bruijn M, White H, Boyd KA, Heggie R, et al. Development and validation of a risk prediction model of preterm birth for women with preterm labour symptoms (the QUIDS study): A prospective cohort study and individual participant data meta-analysis. PLoS Med. 2021;18(7):e1003686. https://doi.org/10.1371/journal.pmed.1003686
Stock SJ, Horne M, Bruijn M, White H, Heggie R, Wotherspoon L, et al. A prognostic model, including quantitative fetal fibronectin, to predict preterm labour: the QUIDS meta-analysis and prospective cohort study. Health Technol Assess. 2021;25(52):1-168. https://doi.org/10.3310/hta25520
Sun Q, Zou X, Yan Y, Zhang H, Wang S, Gao Y, et al. Machine Learning-Based Prediction Model of Preterm Birth Using Electronic Health Record. J Healthc Eng. 2022;2022:9635526. https://doi.org/10.1155/2022/9635526
Yang X, Zhong Q, Li L, Chen Y, Tang C, Liu T, et al. Development and validation of a prediction model on spontaneous preterm birth in twin pregnancy: a retrospective cohort study. Reprod Health. 2023;20(1):187. https://doi.org/10.1186/s12978-023-01728-3
Zhang Y, Du S, Hu T, Xu S, Lu H, Xu C, et al. Establishment of a model for predicting preterm birth based on the machine learning algorithm. BMC Pregnancy Childbirth. 2023;23(1):779. https://doi.org/10.1186/s12884-023-06058-7
Zimeng L, Jingyuan H, Naiwen Z, Hui L, Liu W, Wei L. Establishment and validation of a predictive model for spontaneous preterm birth in singleton pregnant women. BMC Pregnancy Childbirth. 2024;24(1):595. https://doi.org/10.1186/s12884-024-06772-w
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Petro Tokar
This work is licensed under a Creative Commons Attribution 4.0 International License.
ISSN: 
