Stage-Specific Models for Predicting Subsequent Pregnancy Loss in Women with Recurrent Spontaneous Abortion.
- 1Department of Maternal and Child Health, School of Public Health, Peking University, Peking University Health Science Center-Weifang Joint Research Center for Maternal and Child Health, Beijing, 100191, People's Republic of China.
- 2School of Public Health, Shandong Second Medical University, Weifang, Shandong, People's Republic of China.
- 3Department of Obstetrics and Gynecology, Weifang Maternal and Child Health Hospital, Weifang, 260000, People's Republic of China.
Abstract
Objective
To develop and internally validate stage-specific models for predicting subsequent pregnancy loss in women with recurrent spontaneous abortion (RSA), and to evaluate changes in discriminatory performance associated with the sequential incorporation of sequentially available clinical, biochemical, hormonal, and environmental information.Methods
In this single-center prospective cohort study, we developed and internally validated three stage-specific models for subsequent pregnancy outcomes. The first-stage model included baseline demographic and reproductive variables; the second-stage model further incorporated preconception serum 25-hydroxyvitamin D (25(OH)D); and the third-stage model additionally included gestational age, prenatal hormonal indicators, and pregnancy-course ambient PM2.5 and O₃ exposure metrics. Logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) models were developed and internally validated using repeated 10-fold cross-validation. Model performance was assessed using ROC-AUC, PR-AUC, Brier score, sensitivity, specificity, and F1 score.Results
Among 470 women with RSA who subsequently conceived, 86 (18.3%) experienced pregnancy loss again. In RF and XGBoost models, discrimination improved most clearly after incorporating gestational age, prenatal hormonal indicators, and ambient PM2.5 and O₃ exposure metrics, whereas the addition of preconception 25(OH)D alone provided little incremental value. In internal validation, the RF-based third-stage model achieved the highest discrimination, with a ROC-AUC of 0.935 (95% CI: 0.874~0.996). The XGBoost-based third-stage model also demonstrated improved discrimination, with a ROC-AUC of 0.870 (95% CI: 0.801~0.938).Conclusions
A stage-specific prediction framework integrating sequentially available clinical, biochemical, and pregnancy-course environmental information improved discrimination for subsequent pregnancy loss among women with RSA, particularly in tree-based models. These findings provide preliminary evidence that progressively incorporating information from different stages of the subsequent pregnancy may improve risk discrimination beyond baseline characteristics alone. However, these findings were derived from internal validation within a single-center cohort, and the third-stage model was limited by a reduced sample size, a small number of pregnancy-loss events, reliance on complete-case analysis, and the use of outcome-anchored environmental exposure metrics that were not available at a predefined prediction time. External validation in larger, independent cohorts and prospective evaluation using exposure windows aligned with a predefined prediction time are needed to determine the robustness and clinical utility of the framework.
Related
- Predicting the immediate and subsequent effects of commercials on product valuation using EEG and deep learning
- MAFF promotes decidual stromal cell senescence by suppressing NRF2-mediated antioxidant responses in recurrent pregnancy loss
- Rare Double Reciprocal Translocations in a Man with Reproductive Success and Recurrent Pregnancy Loss
- Serum relaxin and beta hCG levels in pregnant women with prior recurrent pregnancy loss and composite adverse pregnancy outcomes
- Robust Induction of Spontaneous Recurrent Seizures and Hippocampal Sclerosis with Synthetic Kainic Acid in the Intrahippocampal Kainate Model
BibTeX
@article{qiu2026stagespecific,
title = {{Stage-Specific Models for Predicting Subsequent Pregnancy Loss in Women with Recurrent Spontaneous Abortion.}},
author = {Minyu Qiu and Chenchen Zhang and Xiao Gao and Xin Yuan and Qingqing Tao and Tianyi Zhou and Zhengyang Zhao and Shusheng Luo and Yuelong Ji and Jue Liu and Hai-Jun Wang and Yimei Zhang and Qin Li},
journal = {International journal of women's health},
year = {2026},
month = oct,
doi = {10.2147/ijwh.s637498},
url = {https://europepmc.org/article/MED/42968955},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Stage-Specific Models for Predicting Subsequent Pregnancy Loss in Women with Recurrent Spontaneous Abortion.
AU - Minyu Qiu
AU - Chenchen Zhang
AU - Xiao Gao
AU - Xin Yuan
AU - Qingqing Tao
AU - Tianyi Zhou
AU - Zhengyang Zhao
AU - Shusheng Luo
AU - Yuelong Ji
AU - Jue Liu
AU - Hai-Jun Wang
AU - Yimei Zhang
AU - Qin Li
PY - 2026
DA - 2026/10/28
JO - International journal of women's health
DO - 10.2147/ijwh.s637498
UR - https://europepmc.org/article/MED/42968955
AB - Objective To develop and internally validate stage-specific models for predicting subsequent pregnancy loss in women with recurrent spontaneous abortion (RSA), and to evaluate changes in discriminatory performance associated with the sequential incorporation of sequentially available clinical, biochemical, hormonal, and environmental information.Methods In this single-center prospective cohort study, we developed and internally validated three stage-specific models for subsequent pregnancy outcomes. The first-stage model included baseline demographic and reproductive variables; the second-stage model further incorporated preconception serum 25-hydroxyvitamin D (25(OH)D); and the third-stage model additionally included gestational age, prenatal hormonal indicators, and pregnancy-course ambient PM2.5 and O₃ exposure metrics. Logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) models were developed and internally validated using repeated 10-fold cross-validation. Model performance was assessed using ROC-AUC, PR-AUC, Brier score, sensitivity, specificity, and F1 score.Results Among 470 women with RSA who subsequently conceived, 86 (18.3%) experienced pregnancy loss again. In RF and XGBoost models, discrimination improved most clearly after incorporating gestational age, prenatal hormonal indicators, and ambient PM2.5 and O₃ exposure metrics, whereas the addition of preconception 25(OH)D alone provided little incremental value. In internal validation, the RF-based third-stage model achieved the highest discrimination, with a ROC-AUC of 0.935 (95% CI: 0.874~0.996). The XGBoost-based third-stage model also demonstrated improved discrimination, with a ROC-AUC of 0.870 (95% CI: 0.801~0.938).Conclusions A stage-specific prediction framework integrating sequentially available clinical, biochemical, and pregnancy-course environmental information improved discrimination for subsequent pregnancy loss among women with RSA, particularly in tree-based models. These findings provide preliminary evidence that progressively incorporating information from different stages of the subsequent pregnancy may improve risk discrimination beyond baseline characteristics alone. However, these findings were derived from internal validation within a single-center cohort, and the third-stage model was limited by a reduced sample size, a small number of pregnancy-loss events, reliance on complete-case analysis, and the use of outcome-anchored environmental exposure metrics that were not available at a predefined prediction time. External validation in larger, independent cohorts and prospective evaluation using exposure windows aligned with a predefined prediction time are needed to determine the robustness and clinical utility of the framework.
SN - 1179-1411
ER -