Prediction of pregnancy-related complications in women undergoing assisted reproduction, using machine learning methods.

Objective: To use machine learning methods to develop prediction models of pregnancy complications in women who conceived with assisted reproductive techniques (ART).
Design: A nation-wide register-based cohort study with prospectively collected data.
Setting: Swedish national registers and nationwide quality IVF register.
Patient(s): all nulliparous women who achieved birth within the first 3 ART treatment cycles between 2008 and 2016 in Sweden.
Intervention(s): Characteristics before the use of ART, such as demographics and medical history, were considered potential predictors in the development of before treatment prediction models. ART treatment details were further included in after treatment prediction models.
Main Outcome Measure(s): Potential diagnoses of preeclampsia, placental complications (previa, accreta, and abruption), and postpartum hemorrhage were identified using the International Classification of Diseases recorded in the Swedish Medical Birth and Patient registers, respectively. Multiple prediction model algorithms were performed and compared for each outcome and treatment cycle, including logistic regression, decision tree model, naïve Bayes classification, support vector machine, random forest, and gradient boosting. The performance of each model was assessed with C statistic, and nested cross-validation was used to aid model selection and hyperparameter tuning.
Result(s): A total of 14,732 women gave birth after the first (N = 7,302), second (N = 4,688), or third (N = 2,742) ART cycle, representing birth rates of 24.1%, 23.8%, and 22.0%. Overall prediction performance did not vary much across the different methods used. In the first cycle, the before treatment prediction performance was at best 66%, 66%, and 60% for preeclampsia, placental complications, and postpartum hemorrhage, respectively. Inclusion of after treatment characteristics conferred slight improvement (approximately 1%-5%), as did prediction in later cycles (approximately 1%-5%). The top influential and consistent predictors included age, region of residence, infertility diagnosis, and type of embryo transfer (fresh or frozen) in the later (2 ^nd and 3 ^rd ) cycles. Body mass index was a top predictor of preeclampsia and was also influential for placental complications but not for postpartum hemorrhage.
Conclusion(s): The combined use of demographics, medical history, and ART treatment information was not enough to confidently predict serious pregnancy complications in women who conceived with ART. Future studies are needed to assess if additional longitudinal follow-up during pregnancy can improve the prediction to allow clinical protocol development.
Competing Interests: Declaration of Interests C.W. reports funding from Forte grant number 2016-01202 and the National Institutes of Health (NIH) grant number R01HD088393 for the submitted work; employed as data analyst in Thermo Fisher Scientific, PPD, Evidera after the manuscript completion. A.L.V.J. has nothing to disclose. C.N. is employed as consulting specialist and chief medical manager at the fertility clinic Livio Kungsholmen Stockholm since 2016. A.P. is a medical associate at Cerebriu, a medical artificial intelligence company for radiology. C.A has nothing to disclose. S.H-D. reports funding from NIH grant R01HD088393 for the submitted work; funding from Takeda; consulting fees from JNJ, Moderna, and BWH-MGH outside the submitted work. A.S.O. received personal fees from Abbot for serving on a Scientific and Medical Advisory Council, unrelated to the current work and reports funding from Forte junior research grant no: 2016-01202 for the submitted work; funding from Forte research grant no: 2020-00753, NIH R01 HD088393, Swedish Research council no: 2018-02679, NIH R01 DA048042-01, and NIH R01 HD088393 outside the submitted work.
(Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)