Predicting Unfavorable Pregnancy Outcomes in Polycystic Ovary Syndrome (PCOS) Patients Using Machine Learning Algorithms

Overview

Journal Medicina (Kaunas)

Publisher MDPI

Specialty General Medicine

Date 2024 Aug 29

PMID 39202579

Authors

Raluca Mogos

Liliana Gheorghe

Alexandru Carauleanu

Ingrid-Andrada Vasilache

Iulian-Valentin Munteanu

Simona Mogos

Iustina Solomon-Condriuc

Luiza-Maria Baean

Demetra Socolov

Ana-Maria Adam

Cristina Preda

Affiliations

Soon will be listed here.

Abstract

: Polycystic ovary syndrome (PCOS) is a complex disorder that can negatively impact the obstetrical outcomes. The aim of this study was to determine the predictive performance of four machine learning (ML)-based algorithms for the prediction of adverse pregnancy outcomes in pregnant patients diagnosed with PCOS. : A total of 174 patients equally divided into 2 groups depending on the PCOS diagnosis were included in this prospective study. We used the Mantel-Haenszel test to evaluate the risk of adverse pregnancy outcomes for the PCOS patients and reported the results as a crude and adjusted odds ratio (OR) with a 95% confidence interval (CI). A generalized linear model was used to identify the predictors of adverse pregnancy outcomes in PCOS patients, quantifying their impact as risk ratios (RR) with 95% CIs. Significant predictors were included in four machine learning-based algorithms and a sensitivity analysis was employed to quantify their performance. : Our crude estimates suggested that PCOS patients had a higher risk of developing gestational diabetes and had a higher chance of giving birth prematurely or through cesarean section in comparison to patients without PCOS. When adjusting for confounders, only the odds of delivery via cesarean section remained significantly higher for PCOS patients. Obesity was outlined as a significant predictor for gestational diabetes and fetal macrosomia, while a personal history of diabetes demonstrated a significant impact on the occurrence of all evaluated outcomes. Random forest (RF) performed the best when used to predict the occurrence of gestational diabetes (area under the curve, AUC value: 0.782), fetal macrosomia (AUC value: 0.897), and preterm birth (AUC value: 0.901) in PCOS patients. : Complex ML algorithms could be used to predict adverse obstetrical outcomes in PCOS patients, but larger datasets should be analyzed for their validation.

References

Galesanu C, Buzduga C, Florescu A, Moisii L, Ciubotaru V . Diabetes mellitus, chronic complication in patients with acromegaly: case report and review of the literature. Rev Med Chir Soc Med Nat Iasi. 2015; 119(1):92-6. View

Lim S, Kakoly N, Tan J, Fitzgerald G, Bahri Khomami M, Joham A . Metabolic syndrome in polycystic ovary syndrome: a systematic review, meta-analysis and meta-regression. Obes Rev. 2018; 20(2):339-352. DOI: 10.1111/obr.12762. View

. Revised 2003 consensus on diagnostic criteria and long-term health risks related to polycystic ovary syndrome (PCOS). Hum Reprod. 2003; 19(1):41-7. DOI: 10.1093/humrep/deh098. View

Metzger B, Gabbe S, Persson B, Buchanan T, Catalano P, Damm P . International association of diabetes and pregnancy study groups recommendations on the diagnosis and classification of hyperglycemia in pregnancy. Diabetes Care. 2010; 33(3):676-82. PMC: 2827530. DOI: 10.2337/dc09-1848. View

Vasilache I, Scripcariu I, Doroftei B, Bernad R, Carauleanu A, Socolov D . Prediction of Intrauterine Growth Restriction and Preeclampsia Using Machine Learning-Based Algorithms: A Prospective Study. Diagnostics (Basel). 2024; 14(4). PMC: 10887724. DOI: 10.3390/diagnostics14040453. View

Kjerulff L, Sanchez-Ramos L, Duffy D . Pregnancy outcomes in women with polycystic ovary syndrome: a metaanalysis. Am J Obstet Gynecol. 2011; 204(6):558.e1-6. DOI: 10.1016/j.ajog.2011.03.021. View

Lizneva D, Suturina L, Walker W, Brakta S, Gavrilova-Jordan L, Azziz R . Criteria, prevalence, and phenotypes of polycystic ovary syndrome. Fertil Steril. 2016; 106(1):6-15. DOI: 10.1016/j.fertnstert.2016.05.003. View

Palomba S, Falbo A, Chiossi G, Orio F, Tolino A, Colao A . Low-grade chronic inflammation in pregnant women with polycystic ovary syndrome: a prospective controlled clinical study. J Clin Endocrinol Metab. 2014; 99(8):2942-51. DOI: 10.1210/jc.2014-1214. View

Melinte-Popescu M, Vasilache I, Socolov D, Melinte-Popescu A . Prediction of HELLP Syndrome Severity Using Machine Learning Algorithms-Results from a Retrospective Study. Diagnostics (Basel). 2023; 13(2). PMC: 9858219. DOI: 10.3390/diagnostics13020287. View

10.

Kanda S, Chatha U, Odoma V, Pitliya A, AlEdani E, Bhangu J . Effect of Metformin (MTF) Intervention During Pregnancy in Women With Polycystic Ovarian Syndrome (PCOS): A Systematic Review. Cureus. 2023; 15(8):e44166. PMC: 10519644. DOI: 10.7759/cureus.44166. View

11.

Damone A, Joham A, Loxton D, Earnest A, Teede H, Moran L . Depression, anxiety and perceived stress in women with and without PCOS: a community-based study. Psychol Med. 2018; 49(9):1510-1520. DOI: 10.1017/S0033291718002076. View

12.

Hanna F, Wu P, Heald A, Fryer A . Diabetes detection in women with gestational diabetes and polycystic ovarian syndrome. BMJ. 2023; 382:e071675. DOI: 10.1136/bmj-2022-071675. View

13.

Ye Y, Xiong Y, Zhou Q, Wu J, Li X, Xiao X . Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study. J Diabetes Res. 2020; 2020:4168340. PMC: 7306091. DOI: 10.1155/2020/4168340. View

14.

Ursuleanu T, Luca A, Gheorghe L, Grigorovici R, Iancu S, Hlusneac M . Deep Learning Application for Analyzing of Constituents and Their Correlations in the Interpretations of Medical Images. Diagnostics (Basel). 2021; 11(8). PMC: 8393354. DOI: 10.3390/diagnostics11081373. View

15.

Cooney L, Dokras A . Beyond fertility: polycystic ovary syndrome and long-term health. Fertil Steril. 2018; 110(5):794-809. DOI: 10.1016/j.fertnstert.2018.08.021. View

16.

Vanky E, Stridsklev S, Heimstad R, Romundstad P, Skogoy K, Kleggetveit O . Metformin versus placebo from first trimester to delivery in polycystic ovary syndrome: a randomized, controlled multicenter study. J Clin Endocrinol Metab. 2010; 95(12):E448-55. DOI: 10.1210/jc.2010-0853. View

17.

Elasam A, Ahmed M, Ahmed A, Sharif M, Abusham A, Hassan B . The prevalence and phenotypic manifestations of polycystic ovary syndrome (PCOS) among infertile Sudanese women: a cross-sectional study. BMC Womens Health. 2022; 22(1):165. PMC: 9102290. DOI: 10.1186/s12905-022-01762-6. View

18.

Gupta A, Katarya R . Social media based surveillance systems for healthcare using machine learning: A systematic review. J Biomed Inform. 2020; 108:103500. PMC: 7331523. DOI: 10.1016/j.jbi.2020.103500. View

19.

Melinte-Popescu A, Vasilache I, Socolov D, Melinte-Popescu M . Predictive Performance of Machine Learning-Based Methods for the Prediction of Preeclampsia-A Prospective Study. J Clin Med. 2023; 12(2). PMC: 9865606. DOI: 10.3390/jcm12020418. View

20.

Ndefo U, Eaton A, Green M . Polycystic ovary syndrome: a review of treatment options with a focus on pharmacological approaches. P T. 2013; 38(6):336-55. PMC: 3737989. View