XGBoost-based prediction of spontaneous preterm birth using maternal factors and serum markers: a retrospective cohort study

XGBoost-based prediction of spontaneous preterm birth using maternal factors and serum markers: a retrospective cohort study | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article XGBoost-based prediction of spontaneous preterm birth using maternal factors and serum markers: a retrospective cohort study Ying Gao, Xiaoqin Huang, Caihua Tan, Lingyan Chen, Xin Zhao, Jinying Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6970183/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 18 Nov, 2025 Read the published version in BMC Pregnancy and Childbirth → Version 1 posted 15 You are reading this latest preprint version Abstract Background: Spontaneous preterm birth (sPTB) is a significant global health issue, contributing to neonatal morbidity and mortality. Existing predictive models for sPTB have shown limited accuracy, highlighting the need for improved prenatal care to identify high-risk pregnancies early. This study aimed to develop a more accurate predictive model by integrating maternal factors and serum markers using machine learning techniques. Methods: A retrospective cohort study was conducted using data from the Longgang Newborn cohort between January 1, 2020, and November 31, 2024. Women who delivered a singleton birth at 28–42 weeks’ gestation were included. We excluded cases of multiple pregnancy, iatrogenic preterm birth, cervical incompetence, and deliveries before 28 weeks. Data on maternal characteristics, pregnancy outcomes, and healthcare utilization were extracted. Predictors included maternal age, body mass index, pre-existing health conditions, socioeconomic variables, smoking status, gravidity, prior abortions, prior cesarean birth, and placental factors. We employed LASSO regression for feature selection and developed prediction models using XGBoost and logistic regression. Model performance was evaluated using sensitivity, specificity, PPV, NPV, and AUC. Results: The study included 19383 participants, with 572 (2.94%) experiencing sPTB. LASSO regression identified five significant factors: age, education, type 2 diabetes mellitus, PAPPA, and AFP. The XGBoost model showed superior performance with an AUC of 0.737 in the training dataset and 0.636 in the validation dataset, outperforming the logistic model. Conclusion: Our XGBoost machine learning based model, offers a promising approach for predicting sPTB with high accuracy. The integration of maternal factors and serum markers could enhance prenatal care by identifying high-risk pregnancies earlier, potentially reducing the incidence of sPTB and its associated complications. spontaneous preterm birth predictive model machine learning serum markers Figures Figure 1 Figure 2 Figure 3 Figure 4 Background Preterm birth (PTB), defined as delivery before 37 weeks of gestation, is a significant global health challenge, contributing significantly to neonatal morbidity and mortality. PTB occurs in approximately 9.9% of all live births, with 65–70% of these cases attributed to spontaneous preterm birth (sPTB) (1, 2). Children born preterm are at an elevated risk for a spectrum of long-term health complications, including respiratory issues, neurodevelopmental delays, obesity, and cardiovascular diseases (3). Despite advancements in prenatal care, the prediction and prevention of sPTB remain challenging, with current strategies showing limited effectiveness, particularly in women without a history of sPTB (4, 5). The etiology of PTB is multifactorial, with recent research suggesting that placental insufficiency may play a more critical role than previously thought, especially in pregnancies beyond 32 weeks (6). This shift in understanding is supported by the association between placental insufficiency and conditions like preeclampsia and fetal growth restriction, which are linked to sPTB. Serum markers related to placental function, such as β- human chorionic gonadotropin (β-hCG), pregnancy associated plasma protein A (PAPPA), alpha fetoprotein (AFP), and unconjugated E3 (uE3), have emerged as potential predictors of sPTB (7, 8). Given the gaps in current predictive models and the need for more effective tools, this study aims to analyze the correlation between maternal factors and serum markers from first and mid-trimester Down syndrome screening with the occurrence of sPTB. By constructing a multivariate predictive model using logistic regression and machine learning, we seek to enhance the early identification and prevention of preterm birth, ultimately improving maternal and infant outcomes. Methods Study design and population We design a retrospective cohort study using data from Longgang Newborn cohort between January 1, 2020, and November 31, 2024. The study population comprised women who delivered a singleton birth at 28–42 weeks’ gestation in a tertiary hospital. Multiple pregnancy, iatrogenic preterm birth, cervical incompetence, delivered < 28 gestational week, missing data were excluded. The primary outcome was sPTB defined as delivery before 37 weeks without induction or cesarean section. Data collection and variables Data were extracted from the hospital database, which includes maternal characteristics, pregnancy outcomes, and healthcare utilization. Potential predictors included maternal age, body mass index (BMI), pre-existing health conditions, socioeconomic variables, smoking status and alcohol consumption of husband, gravidity, prior abortions, prior caesarean birth, and serum biomarkers from serological screening. Model development and validation After data standardization, Least Absolute Shrinkage and Selection Operator (LASSO) with 5-fold cross-validation is employed to automatically search for the optimal value of the regularization parameter λ. The model is then trained using the selected λ and the standardized data to obtain the coefficients for each feature. Prediction models were developed using the following machine learning classifiers: logistic regression, eXtreme Gradient Boosting (XGBoost). The dataset was divided into two parts: 80% for training the classifiers and 20% for model validation. The training dataset was balanced using random oversampling techniques. GridSearchCV from the Scikit-learning (sklearn) library was utilized to conduct five - fold cross - validation on the model. The model is trained on the training set and validated on the validation set, with performance metrics calculated in each iteration. The average of these metrics across all iterations is then used as the final evaluation result for the model. This approach ensures that the optimal hyperparameter combination is found within the given grid, yielding a more reliable outcome. Performance evaluation Model performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristics (ROC) curve. The performance metrics were calculated on both the training and the validation dataset to assess the generalizability of the models. Statistical analysis Statistical analyses were conducted using Python (version 3.13.2). LASSO regression, implemented with the sklearn library, was employed to select influential factors with non-zero regression coefficients from the dataset. Prediction models were developed using machine learning classifiers from the sklearn library, including logistic regression, XGBoost. The training dataset was balanced using random oversampling techniques to address class imbalance. GridSearchCV was utilized to conduct five-fold cross-validation on the models, ensuring the identification of the optimal hyperparameter combination. Model performance was evaluated using a suite of metrics calculated on the validation dataset, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the ROC curve. The area under curve (AUC) values were generated using the pROC package. Data visualization was conducted using matplotlib package. Statistical significance was determined using the chi-square test and the Mann-Whitney U test for categorical and continuous variables, respectively. A p-value of less than 0.05 was considered statistically significant, indicating a meaningful difference between groups. The conversion of MoM (multiple of the median) values is the ratio of the patient's test value to the average value of the full-term delivery population at the same gestational age. The MoM values included in predictive models have undergone logarithmic transformation, specifically using the natural logarithm (ln) to normalize the data and enhance the model's predictive accuracy. Results Characteristics The study included 19383 participants, with 18811 (97.06%) experiencing term delivery and 572 (2.94%) experiencing sPTB (Fig. 1 , Table 1 ). The median age was 29 years, and the median BMI was 20.83 kg/m². Majority of the participants were Han ethnicity (97.06%), high educated (70.24%) and insurance covered (70.28%). Significant differences were observed in serum biomarkers. The median levels of PAPPA and AFP showed significant differences between the term and sPTB groups (PAPPA: p < 0.001, AFP: p < 0.001). Other biomarkers such as HCG, NT, and uE3 did not exhibit significant differences. Table 1 Demographic of the population Variables Total (n = 19383) 0 (n = 18811) 1 (n = 572) Statistic P Age, years 29.00 (26.00, 32.00) 29.00 (26.00, 32.00) 29.00 (27.00, 32.00) Z=-1.15 0.251 BMI, kg/m 2 20.83 (19.27, 22.77) 20.82 (19.27, 22.77) 20.98 (19.31, 23.14) Z=-1.66 0.097 PAPPA, mU/L 0.98 (0.70, 1.36) 0.99 (0.70, 1.37) 0.91 (0.61, 1.26) Z=-3.64 < 0.001 hcg-1, ng/ml 0.97 (0.65, 1.46) 0.97 (0.65, 1.46) 0.94 (0.62, 1.40) Z=-1.99 0.047 NT, cm 1.00 (0.90, 1.20) 1.00 (0.90, 1.20) 1.00 (0.90, 1.10) Z=-0.54 0.592 AFP, U/ml 0.99 (0.81, 1.22) 0.99 (0.81, 1.21) 1.08 (0.85, 1.39) Z=-6.38 < 0.001 hcg-2, ng/ml 0.97 (0.67, 1.47) 0.97 (0.67, 1.47) 1.02 (0.65, 1.55) Z=-0.48 0.630 uE3, nmol/l 1.02 (0.87, 1.18) 1.02 (0.87, 1.19) 1.01 (0.86, 1.18) Z=-0.50 0.615 PAPPA MoM a 1.00 (0.70, 1.39) 1.00 (0.71, 1.39) 0.93 (0.62, 1.30) Z=-3.65 < 0.001 hcg-1 MoM 1.01 (0.68, 1.52) 1.01 (0.68, 1.52) 0.98 (0.65, 1.47) Z=-1.99 0.047 NT MoM 1.00 (0.90, 1.20) 1.00 (0.90, 1.20) 1.00 (0.90, 1.10) Z=-0.54 0.592 AFP MoM 1.00 (0.82, 1.23) 1.00 (0.82, 1.22) 1.09 (0.86, 1.40) Z=-6.38 < 0.001 hcg-2 MoM 1.00 (0.69, 1.52) 1.00 (0.69, 1.51) 1.04 (0.66, 1.59) Z=-0.43 0.669 uE3 MoM 1.00 (0.85, 1.17) 1.00 (0.85, 1.17) 0.99 (0.84, 1.17) Z=-0.44 0.659 Ethnic χ²=3.86 0.049 Others 570 (2.94) 561 (2.98) 9 (1.57) Han 18813 (97.06) 18250 (97.02) 563 (98.43) Education χ²=0.16 0.694 Low educated 5769 (29.76) 5603 (29.79) 166 (29.02) High educated 13614 (70.24) 13208 (70.21) 406 (70.98) Insurance χ²=0.55 0.459 No 5760 (29.72) 5598 (29.76) 162 (28.32) Yes 13623 (70.28) 13213 (70.24) 410 (71.68) Abortion ≥ 3 times χ²=0.34 0.558 No 19131 (98.70) 18568 (98.71) 563 (98.43) Yes 252 (1.30) 243 (1.29) 9 (1.57) Pregnancy history χ²=0.29 0.592 Primipara 10020 (51.69) 9718 (51.66) 302 (52.80) Multipara 9363 (48.31) 9093 (48.34) 270 (47.20) Alcohol admission (husband) χ²=0.69 0.407 No 13487 (69.58) 13080 (69.53) 407 (71.15) Yes 5896 (30.42) 5731 (30.47) 165 (28.85) Smoking (husband) χ²=0.33 0.567 No 13091 (67.54) 12711 (67.57) 380 (66.43) Yes 6292 (32.46) 6100 (32.43) 192 (33.57) Assisted reproductive technology χ²=0.28 0.595 No 18715 (96.55) 18165 (96.57) 550 (96.15) Yes 668 (3.45) 646 (3.43) 22 (3.85) History of cesarean section χ²=7.62 0.006 No 16810 (86.73) 16336 (86.84) 474 (82.87) Yes 2573 (13.27) 2475 (13.16) 98 (17.13) Asthma - 1.000 No 19371 (99.94) 18799 (99.94) 572 (100.00) Yes 12 (0.06) 12 (0.06) 0 (0.00) Diabetes χ²=14.65 < 0.001 No 15269 (78.78) 14855 (78.97) 414 (72.38) GDM 4029 (20.79) 3875 (20.60) 154 (26.92) T2DM 85 (0.44) 81 (0.43) 4 (0.70) Primary Hypertension χ²=4.88 0.027 No 19326 (99.71) 18759 (99.72) 567 (99.13) Yes 57 (0.29) 52 (0.28) 5 (0.87) BMI = body mass index. PAPPA = Pregnancy Associated Plasma Protein A. AFP = alpha fetoprotein. hcg-1 = human chorionic gonadotropin (hcg) value tested in first trimester. hcg-2 = hcg value tested in second trimester. M: Median, Q₁: 1st Quartile, Q₃: 3st Quartile, Z: Mann-Whitney test, χ²: Chi-square test, -: Fisher exact. a. The conversion of MoM (multiple of the median) values is the ratio of the patient's test value to the average value of the full-term delivery population at the same gestational age. Feature selection by LASSO regression LASSO regression identified five significant factors associated with sPTB: age, education, type 2 diabetes mellitus, PAPPA, and AFP (Fig. 2 ). These factors were selected for their non-zero regression coefficients after pre-screening with univariate logistic regression. SHAP analysis The SHAP plot and bar chart highlighted AFP and PAPPA as the most influential features on the model output, with varying impacts across different instances (Fig. 3 ). T2DM and age also contributed significantly, though with less variability compared to the serum markers. Education had a relatively smaller impact. Model performance The predictive performance of the models was evaluated using a variety of metrics including AUC, accuracy, F1 score, sensitivity, specificity, PPV, and NPV. These metrics were calculated for both the training and validation datasets to assess the models' ability to generalize. In training dataset, the AUC for XGBoost model is 0.737, with a 95%CI of 0.705–0.769 (Fig. 4 ). The AUC for logistic model is 0.621, with a 95%CI of 0.586–0.659. In validation dataset, the AUC for XGBoost model is 0.636, with a 95%CI of 0.570–0.708. The AUC for logistic model is 0.570, with a 95%CI of 0.496–0.647. Table 2 provides a detailed comparison of the XGBoost and logistic models across various performance metrics. The XGBoost model consistently outperformed the logistic model in terms of accuracy, F1 score, sensitivity, and specificity in both the training and validation datasets. XGBoost model achieved an accuracy of 0.67 (95% CI: 0.64, 0.70), an F1 score of 0.63 (95% CI: 0.59, 0.66), a sensitivity of 0.55 (95% CI: 0.51, 0.60), and a specificity of 0.79 (95% CI: 0.76, 0.83). The PPV was 0.72 (95% CI: 0.68, 0.77), and the NPV was 0.64 (95% CI: 0.60, 0.68). The superiority of the XGBoost model is also maintained in the validation set (Table 3 ). Table 2 Predictive power and 95% confidence intervals of models in train dataset for sPTB. Model Train Accuracy Train F1 Score Train Sensitivity Train Specificity Train PPV Train NPV XGBoost 0.67(0.64, 0.7) 0.63(0.59, 0.66) 0.55(0.51, 0.6) 0.79(0.76, 0.83) 0.72(0.68, 0.77) 0.64(0.6, 0.68) Logistic 0.59(0.56, 0.62) 0.59(0.56, 0.63) 0.59(0.55, 0.64) 0.59(0.55, 0.64) 0.59(0.55, 0.63) 0.59(0.54, 0.64) XGBoost = eXtreme Gradient Boosting. PPV = positive predictive value. NPV = negative predictive value. All values are percentages and presented as predictive power (95% confidence interval). Table 3 Predictive power and 95% confidence intervals of models in test dataset for sPTB. Model Test Accuracy Test F1 Score Test Sensitivity Test Specificity Test PPV Test NPV XGBoost 0.59(0.53, 0.66) 0.52(0.44, 0.6) 0.45(0.36, 0.54) 0.74(0.66, 0.82) 0.63(0.53, 0.73) 0.57(0.49, 0.65) Logistic 0.55(0.49, 0.62) 0.53(0.45, 0.61) 0.51(0.42, 0.6) 0.6(0.52, 0.69) 0.56(0.47, 0.65) 0.55(0.46, 0.64) XGBoost = eXtreme Gradient Boosting. PPV = positive predictive value. NPV = negative predictive value. All values are percentages and presented as predictive power (95% confidence interval). Discussion Main findings This study successfully integrated maternal factors and serum markers to predict sPTB with enhanced accuracy using machine learning methods. The XGBoost model demonstrated superior predictive efficiency with an AUC of 0.737, indicating its potential as an effective tool for early identification and intervention. Advanced maternal age emerged as a critical risk factor, underscoring the importance of considering age in predictive models. Serum markers PAPP-A and AFP, reflecting placental function, were identified as primary influential factors, aligning with current understanding of placental insufficiency's role in sPTB. The method combining clinical features and serological indicators is significantly helpful in improving the predictive efficacy(9, 10). PAPP-A and AFP was identified as available predictors of spontaneous preterm birth (sPTB), which were thought to reflect placental function and integrity, which are critical factors in the pathogenesis of preterm birth(11, 12). One study indicated that elevated AFP/PAPP-A or AFP/β-HCG ratio in the first trimester is associated with increased risk for sPTB. The AFP/PAPP-A ratio > 7 is associated with an increased risk of sPTB before 34 weeks with an odds ratio of 2.9, and the AFP/β-hCG ratio > 0.6 indicates a 3.5-fold higher risk of sPTB before 32 weeks. AFP/PAPP-A > 7 indicated 2.9 higher risk of preterm birth before 34 gestational weeks. Moreover, maternal serum AFP or hCG > 2.0 MoM increases the risk of adverse pregnancy outcomes occurring before 37 gestational weeks, including preeclampsia, intrauterine growth restriction, fetal death(12). Therefore, women with elevated PAPPA and AFP levels should receive more rigorous monitoring and follow-up. Incorporating machine learning into predictive models for sPTB presents a valuable opportunity to enhance prenatal care(13). Our model not only boosts the precision of predictions but also efficiently allocates resources by prioritizing the most critical factors. Early identification of pregnancies at high risk empowers healthcare providers to deliver focused interventions, which may decrease the occurrence of sPTB and its related complications. This approach is likely to lower medical expenses and increase operational efficiency in clinical environments, laying a solid groundwork for proactive intervention strategies. Strength and limitations This study's strength lies in its integration of machine learning techniques with a comprehensive set of maternal and serum markers to predict sPTB, which could enhance prenatal care. We verified the effectiveness of this model by using a randomly selected validation set, which is an important highlight compared to previous research. However, limitations include potential biases inherent in the retrospective study design, reliance on a single cohort that may affect generalizability, and the complexity of interpreting machine learning models, which may pose challenges for clinical application. Future research should focus on validating these models in diverse populations and improving their clinical interpretability. Conclusion In conclusion, this study demonstrates the potential of integrating maternal factors and serum markers with machine learning to predict sPTB (AUC 0.737). The XGBoost model particularly shows promise as a powerful tool for improving prenatal risk assessment and guiding early intervention strategies. Abbreviations sPTB spontaneous preterm birth BMI body mass index T2DM type 2 diabetes mellitus β-hCG β- human chorionic gonadotropin PAPPA pregnancy associated plasma protein A AFP alpha fetoprotein uE3 unconjugated E3 M Median MoM multiple of the median IRB institutional review board LASSO Least Absolute Shrinkage and Selection Operator XGBoost eXtreme Gradient Boosting ROC receiver operating characteristics PPV positive predictive value NPV negative predictive value AUC area under curve. Declarations Ethics approval and consent to participate Ethical approval was obtained from the Institutional Review Board (IRB number: LGFYKYXMLL-2024-91). Informed consent was obtained from all subjects. All experiments were performed in accordance with the Declaration of Helsinki. Consent for publication Not applicable. Availability of data and materials The datasets used and analysed during the current study are available from the corresponding author on reasonable request. Competing interests The authors declare that they have no competing interests. Funding This study was funded by the National Natural Science Foundation of China (Grant No. 82471717). Authors' contributions Ying Gao wrote the original draft; Xiaoqin Huang and Caihua Tan contributed to the recruitment of the cohort population and data collection; Lingyan Chen and Xin Zhao jointly contributed to data analysis; Jinying Yang contributed to the conception of the manuscript and its review and editing. Acknowledgements Thank you to all the pregnant women and staff who participated in this study. References Ohuma EO, Moller AB, Bradley E, Chakwera S, Hussain-Alkhateeb L, Lewin A, et al. National, regional, and global estimates of preterm birth in 2020, with trends from 2010: a systematic analysis. Lancet. 2023;402(10409):1261-71. Bhattacharjee E, Maitra A. Spontaneous preterm birth: the underpinnings in the maternal and fetal genomes. NPJ Genom Med. 2021;6(1):43. Mericq V, Martinez-Aguayo A, Uauy R, Iñiguez G, Van der Steen M, Hokken-Koelega A. Long-term metabolic risk among children born premature or small for gestational age. Nat Rev Endocrinol. 2017;13(1):50-62. Hughes K, Ford H, Thangaratinam S, Brennecke S, Mol BW, Wang R. Diagnosis or prognosis? An umbrella review of mid-trimester cervical length and spontaneous preterm birth. Bjog. 2023;130(8):866-79. Prediction and Prevention of Spontaneous Preterm Birth: ACOG Practice Bulletin, Number 234. Obstet Gynecol. 2021;138(2):e65-e90. Morgan TK. Role of the Placenta in Preterm Birth: A Review. Am J Perinatol. 2016;33(3):258-66. Guibourdenche J, Leguy MC, Pidoux G, Hebert-Schuster M, Laguillier C, Anselem O, et al. Biochemical Screening for Fetal Trisomy 21: Pathophysiology of Maternal Serum Markers and Involvement of the Placenta. Int J Mol Sci. 2023;24(8):7669. Chen Y, Dai X, Wu B, Jiang C, Yin Y. Relationship between increased maternal serum free human chorionic gonadotropin levels in the second trimester and adverse pregnancy outcomes: a retrospective cohort study. BMC Womens Health. 2024;24(1):323. Chiu CPH, Feng Q, Chaemsaithong P, Sahota DS, Lau YY, Yeung YK, et al. Prediction of spontaneous preterm birth and preterm prelabor rupture of membranes using maternal factors, obstetric history and biomarkers of placental function at 11-13 weeks. Ultrasound Obstet Gynecol. 2022;60(2):192-9. Oskovi Kaplan ZA, Ozgu-Erdinc AS. Prediction of Preterm Birth: Maternal Characteristics, Ultrasound Markers, and Biomarkers: An Updated Overview. J Pregnancy. 2018;2018:8367571. Celik E, Melekoğlu R, Baygül A, Kalkan U, Şimşek Y. The predictive value of maternal serum AFP to PAPP-A or b-hCG ratios in spontaneous preterm birth. J Obstet Gynaecol. 2022;42(6):1956-61. Tancrède S, Bujold E, Giguère Y, Renald MH, Girouard J, Forest JC. Mid-trimester maternal serum AFP and hCG as markers of preterm and term adverse pregnancy outcomes. J Obstet Gynaecol Can. 2015;37(2):111-6. Lamont RF, Richardson LS, Boniface JJ, Cobo T, Exner MM, Christensen IB, et al. Commentary on a combined approach to the problem of developing biomarkers for the prediction of spontaneous preterm labor that leads to preterm birth. Placenta. 2020;98:13-23. Additional Declarations No competing interests reported. Supplementary Files data.xlsx Cite Share Download PDF Status: Published Journal Publication published 18 Nov, 2025 Read the published version in BMC Pregnancy and Childbirth → Version 1 posted Editorial decision: Revision requested 30 Jul, 2025 Reviews received at journal 29 Jul, 2025 Reviews received at journal 22 Jul, 2025 Reviews received at journal 19 Jul, 2025 Reviewers agreed at journal 17 Jul, 2025 Reviews received at journal 16 Jul, 2025 Reviewers agreed at journal 16 Jul, 2025 Reviewers agreed at journal 15 Jul, 2025 Reviewers agreed at journal 15 Jul, 2025 Reviewers agreed at journal 14 Jul, 2025 Reviewers invited by journal 14 Jul, 2025 Editor invited by journal 30 Jun, 2025 Editor assigned by journal 27 Jun, 2025 Submission checks completed at journal 27 Jun, 2025 First submitted to journal 24 Jun, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6970183","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":486205359,"identity":"12766cb2-b138-435d-a4c9-81d3ae77782e","order_by":0,"name":"Ying Gao","email":"","orcid":"","institution":"Affiliated Shenzhen Women and Children's Hospital (Longgang) of Shantou University Medical College (Longgang District Maternity \u0026 Child Healthcare Hospital of Shenzhen City)","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Gao","suffix":""},{"id":486205360,"identity":"760bcb81-f4ce-4dba-8fbc-2a0f4608d909","order_by":1,"name":"Xiaoqin Huang","email":"","orcid":"","institution":"Longgang District Maternity \u0026 Child Healthcare Hospital of Shenzhen City (Affiliated Shenzhen Women and Children's Hospital (Longgang) of Shantou University Medical College)","correspondingAuthor":false,"prefix":"","firstName":"Xiaoqin","middleName":"","lastName":"Huang","suffix":""},{"id":486205361,"identity":"42bdebfd-ddce-443d-94a6-3f423a847dc7","order_by":2,"name":"Caihua Tan","email":"","orcid":"","institution":"Longgang District Maternity \u0026 Child Healthcare Hospital of Shenzhen City (Affiliated Shenzhen Women and Children's Hospital (Longgang) of Shantou University Medical College)","correspondingAuthor":false,"prefix":"","firstName":"Caihua","middleName":"","lastName":"Tan","suffix":""},{"id":486205362,"identity":"90786cc0-3858-4a5e-b451-bcf9407de46b","order_by":3,"name":"Lingyan Chen","email":"","orcid":"","institution":"Affiliated Shenzhen Women and Children's Hospital (Longgang) of Shantou University Medical College (Longgang District Maternity \u0026 Child Healthcare Hospital of Shenzhen City)","correspondingAuthor":false,"prefix":"","firstName":"Lingyan","middleName":"","lastName":"Chen","suffix":""},{"id":486205363,"identity":"deb570ef-b954-4505-b25b-a1f7e95ae05c","order_by":4,"name":"Xin Zhao","email":"","orcid":"","institution":"Longgang District Maternity \u0026 Child Healthcare Hospital of Shenzhen City (Affiliated Shenzhen Women and Children's Hospital (Longgang) of Shantou University Medical College)","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zhao","suffix":""},{"id":486205364,"identity":"354ef671-ab70-44aa-9e61-9370b217763f","order_by":5,"name":"Jinying Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYDACdsYGKKO5gUgtzIyNEKU8B4nWwgC1RiKRSC38zMztDz622eXJRz5sfsHwyyaxgf3sAbxaJJsZGxtntiUXG95ObLNg7EtLbODJS8CrxeAwY2Mzbxtz4sbZiW0GjD2HjRkkeAzwarEHafnbVp+4ceZBIrUYAEOsmbHtcOJ8CcbmBww/DssR1CIBtGVmz7njiRt4EtsYEhvS5Nh4cvBr4W9vf/DhR1l14vz2w4c/fPhjw8PPfga/FjBgZAO68AADmwTQIgY2wupB4A8Dg3wDA/MHEGMUjIJRMApGAToAAOHZSQikiE4/AAAAAElFTkSuQmCC","orcid":"","institution":"Affiliated Shenzhen Women and Children's Hospital (Longgang) of Shantou University Medical College (Longgang District Maternity \u0026 Child Healthcare Hospital of Shenzhen City)","correspondingAuthor":true,"prefix":"","firstName":"Jinying","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2025-06-25 03:38:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6970183/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6970183/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12884-025-08414-1","type":"published","date":"2025-11-18T15:57:22+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":87048431,"identity":"cfc5dee3-511a-4104-aba9-bc156cc72f39","added_by":"auto","created_at":"2025-07-18 14:50:26","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":148221,"visible":true,"origin":"","legend":"\u003cp\u003eFlow chart of the population selection process.\u003c/p\u003e","description":"","filename":"Figure1.png","url":"https://assets-eu.researchsquare.com/files/rs-6970183/v1/c867c7bb6885633ccfcd80a7.png"},{"id":87047369,"identity":"9b207c33-3a56-49f0-a607-ba9365918de3","added_by":"auto","created_at":"2025-07-18 14:42:26","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":221451,"visible":true,"origin":"","legend":"\u003cp\u003eLasso Paths plot. (A). Cross-Validation Curve displaying the mean squared error against different values of the alpha parameter on a logarithmic scale (B).\u003c/p\u003e","description":"","filename":"Figure2.png","url":"https://assets-eu.researchsquare.com/files/rs-6970183/v1/ffe0fc785c1e1337ebf5f943.png"},{"id":87045916,"identity":"dd044ab8-7161-425d-8b71-6f2fbadfde25","added_by":"auto","created_at":"2025-07-18 14:34:26","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":195907,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP plot. (A). Bar chart displaying the sorted feature importance based on the mean absolute SHAP values (B).\u003c/p\u003e","description":"","filename":"Figure3.png","url":"https://assets-eu.researchsquare.com/files/rs-6970183/v1/5d4a92db69199a5847ca0584.png"},{"id":87045913,"identity":"d2df67bb-7919-4031-a0fe-21bb1a022505","added_by":"auto","created_at":"2025-07-18 14:34:26","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":292169,"visible":true,"origin":"","legend":"\u003cp\u003eROC curves. ROC curves comparison on the training dataset (A) and the test dataset (B).\u003c/p\u003e","description":"","filename":"Figure4.png","url":"https://assets-eu.researchsquare.com/files/rs-6970183/v1/585e8f352efd3ec0126d1568.png"},{"id":96650911,"identity":"42a72edb-f829-4fc3-b635-fee150a70cdf","added_by":"auto","created_at":"2025-11-24 16:12:43","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1575934,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6970183/v1/2e9db09f-9895-4157-be26-72fcbdbb2c3a.pdf"},{"id":87047378,"identity":"a9aa88aa-0e6c-4c96-96fb-bfd10bf0e3f1","added_by":"auto","created_at":"2025-07-18 14:42:26","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5709037,"visible":true,"origin":"","legend":"","description":"","filename":"data.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6970183/v1/323ae699d5232471c15ff7db.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"XGBoost-based prediction of spontaneous preterm birth using maternal factors and serum markers: a retrospective cohort study","fulltext":[{"header":"Background","content":"\u003cp\u003ePreterm birth (PTB), defined as delivery before 37 weeks of gestation, is a significant global health challenge, contributing significantly to neonatal morbidity and mortality. PTB occurs in approximately 9.9% of all live births, with 65\u0026ndash;70% of these cases attributed to spontaneous preterm birth (sPTB) (1, 2). Children born preterm are at an elevated risk for a spectrum of long-term health complications, including respiratory issues, neurodevelopmental delays, obesity, and cardiovascular diseases (3). Despite advancements in prenatal care, the prediction and prevention of sPTB remain challenging, with current strategies showing limited effectiveness, particularly in women without a history of sPTB (4, 5).\u003c/p\u003e\u003cp\u003eThe etiology of PTB is multifactorial, with recent research suggesting that placental insufficiency may play a more critical role than previously thought, especially in pregnancies beyond 32 weeks (6). This shift in understanding is supported by the association between placental insufficiency and conditions like preeclampsia and fetal growth restriction, which are linked to sPTB. Serum markers related to placental function, such as β- human chorionic gonadotropin (β-hCG), pregnancy associated plasma protein A (PAPPA), alpha fetoprotein (AFP), and unconjugated E3 (uE3), have emerged as potential predictors of sPTB (7, 8).\u003c/p\u003e\u003cp\u003eGiven the gaps in current predictive models and the need for more effective tools, this study aims to analyze the correlation between maternal factors and serum markers from first and mid-trimester Down syndrome screening with the occurrence of sPTB. By constructing a multivariate predictive model using logistic regression and machine learning, we seek to enhance the early identification and prevention of preterm birth, ultimately improving maternal and infant outcomes.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eStudy design and population\u003c/h2\u003e\u003cp\u003eWe design a retrospective cohort study using data from Longgang Newborn cohort between January 1, 2020, and November 31, 2024. The study population comprised women who delivered a singleton birth at 28\u0026ndash;42 weeks\u0026rsquo; gestation in a tertiary hospital. Multiple pregnancy, iatrogenic preterm birth, cervical incompetence, delivered\u0026thinsp;\u0026lt;\u0026thinsp;28 gestational week, missing data were excluded. The primary outcome was sPTB defined as delivery before 37 weeks without induction or cesarean section.\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eData collection and variables\u003c/h3\u003e\n\u003cp\u003eData were extracted from the hospital database, which includes maternal characteristics, pregnancy outcomes, and healthcare utilization. Potential predictors included maternal age, body mass index (BMI), pre-existing health conditions, socioeconomic variables, smoking status and alcohol consumption of husband, gravidity, prior abortions, prior caesarean birth, and serum biomarkers from serological screening.\u003c/p\u003e\n\u003ch3\u003eModel development and validation\u003c/h3\u003e\n\u003cp\u003eAfter data standardization, Least Absolute Shrinkage and Selection Operator (LASSO) with 5-fold cross-validation is employed to automatically search for the optimal value of the regularization parameter λ. The model is then trained using the selected λ and the standardized data to obtain the coefficients for each feature. Prediction models were developed using the following machine learning classifiers: logistic regression, eXtreme Gradient Boosting (XGBoost). The dataset was divided into two parts: 80% for training the classifiers and 20% for model validation. The training dataset was balanced using random oversampling techniques. GridSearchCV from the Scikit-learning (sklearn) library was utilized to conduct five - fold cross - validation on the model. The model is trained on the training set and validated on the validation set, with performance metrics calculated in each iteration. The average of these metrics across all iterations is then used as the final evaluation result for the model. This approach ensures that the optimal hyperparameter combination is found within the given grid, yielding a more reliable outcome.\u003c/p\u003e\n\u003ch3\u003ePerformance evaluation\u003c/h3\u003e\n\u003cp\u003eModel performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristics (ROC) curve. The performance metrics were calculated on both the training and the validation dataset to assess the generalizability of the models.\u003c/p\u003e\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eStatistical analyses were conducted using Python (version 3.13.2). LASSO regression, implemented with the sklearn library, was employed to select influential factors with non-zero regression coefficients from the dataset. Prediction models were developed using machine learning classifiers from the sklearn library, including logistic regression, XGBoost. The training dataset was balanced using random oversampling techniques to address class imbalance. GridSearchCV was utilized to conduct five-fold cross-validation on the models, ensuring the identification of the optimal hyperparameter combination. Model performance was evaluated using a suite of metrics calculated on the validation dataset, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the ROC curve. The area under curve (AUC) values were generated using the pROC package. Data visualization was conducted using matplotlib package. Statistical significance was determined using the chi-square test and the Mann-Whitney U test for categorical and continuous variables, respectively. A p-value of less than 0.05 was considered statistically significant, indicating a meaningful difference between groups. The conversion of MoM (multiple of the median) values is the ratio of the patient's test value to the average value of the full-term delivery population at the same gestational age. The MoM values included in predictive models have undergone logarithmic transformation, specifically using the natural logarithm (ln) to normalize the data and enhance the model's predictive accuracy.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003eCharacteristics\u003c/h2\u003e\u003cp\u003eThe study included 19383 participants, with 18811 (97.06%) experiencing term delivery and 572 (2.94%) experiencing sPTB (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). The median age was 29 years, and the median BMI was 20.83 kg/m\u0026sup2;. Majority of the participants were Han ethnicity (97.06%), high educated (70.24%) and insurance covered (70.28%). Significant differences were observed in serum biomarkers. The median levels of PAPPA and AFP showed significant differences between the term and sPTB groups (PAPPA: p\u0026thinsp;\u0026lt;\u0026thinsp;0.001, AFP: p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Other biomarkers such as HCG, NT, and uE3 did not exhibit significant differences.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDemographic of the population\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eVariables\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTotal\u003c/p\u003e\u003cp\u003e(n\u0026thinsp;=\u0026thinsp;19383)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0 (n\u0026thinsp;=\u0026thinsp;18811)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1 (n\u0026thinsp;=\u0026thinsp;572)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eStatistic\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge, years\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e29.00 (26.00, 32.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e29.00 (26.00, 32.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e29.00 (27.00, 32.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-1.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.251\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBMI, kg/m\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e20.83 (19.27, 22.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e20.82 (19.27, 22.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e20.98 (19.31, 23.14)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-1.66\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.097\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePAPPA, mU/L\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.98 (0.70, 1.36)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.99 (0.70, 1.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.91 (0.61, 1.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-3.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehcg-1, ng/ml\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.97 (0.65, 1.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.97 (0.65, 1.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.94 (0.62, 1.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-1.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.047\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNT, cm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.00 (0.90, 1.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 (0.90, 1.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.00 (0.90, 1.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-0.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.592\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAFP, U/ml\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.99 (0.81, 1.22)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.99 (0.81, 1.21)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.08 (0.85, 1.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-6.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehcg-2, ng/ml\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.97 (0.67, 1.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.97 (0.67, 1.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.02 (0.65, 1.55)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-0.48\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.630\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003euE3, nmol/l\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.02 (0.87, 1.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.02 (0.87, 1.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.01 (0.86, 1.18)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-0.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.615\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePAPPA MoM \u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.00 (0.70, 1.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 (0.71, 1.39)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.93 (0.62, 1.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-3.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehcg-1 MoM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.01 (0.68, 1.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.01 (0.68, 1.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.98 (0.65, 1.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-1.99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.047\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNT MoM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.00 (0.90, 1.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 (0.90, 1.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.00 (0.90, 1.10)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-0.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.592\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAFP MoM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.00 (0.82, 1.23)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 (0.82, 1.22)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.09 (0.86, 1.40)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-6.38\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ehcg-2 MoM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.00 (0.69, 1.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 (0.69, 1.51)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.04 (0.66, 1.59)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-0.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.669\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003euE3 MoM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.00 (0.85, 1.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.00 (0.85, 1.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.99 (0.84, 1.17)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eZ=-0.44\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.659\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEthnic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=3.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.049\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOthers\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e570 (2.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e561 (2.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e9 (1.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHan\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e18813 (97.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18250 (97.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e563 (98.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEducation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=0.16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.694\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLow educated\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5769 (29.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5603 (29.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e166 (29.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHigh educated\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e13614 (70.24)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13208 (70.21)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e406 (70.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eInsurance\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.459\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5760 (29.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5598 (29.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e162 (28.32)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e13623 (70.28)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13213 (70.24)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e410 (71.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAbortion\u0026thinsp;\u0026ge;\u0026thinsp;3 times\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=0.34\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.558\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e19131 (98.70)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18568 (98.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e563 (98.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e252 (1.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e243 (1.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e9 (1.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePregnancy history\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=0.29\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.592\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePrimipara\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e10020 (51.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9718 (51.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e302 (52.80)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMultipara\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9363 (48.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e9093 (48.34)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e270 (47.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003eAlcohol admission (husband)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=0.69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.407\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e13487 (69.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13080 (69.53)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e407 (71.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5896 (30.42)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e5731 (30.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e165 (28.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003eSmoking (husband)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=0.33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.567\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e13091 (67.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12711 (67.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e380 (66.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6292 (32.46)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6100 (32.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e192 (33.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003eAssisted reproductive technology\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=0.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.595\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e18715 (96.55)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18165 (96.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e550 (96.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e668 (3.45)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e646 (3.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e22 (3.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003eHistory of cesarean section\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=7.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e16810 (86.73)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16336 (86.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e474 (82.87)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2573 (13.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2475 (13.16)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e98 (17.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAsthma\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1.000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e19371 (99.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18799 (99.94)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e572 (100.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e12 (0.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12 (0.06)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0 (0.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003eDiabetes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=14.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e15269 (78.78)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e14855 (78.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e414 (72.38)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGDM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4029 (20.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3875 (20.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e154 (26.92)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eT2DM\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e85 (0.44)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e81 (0.43)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e4 (0.70)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e\u003cp\u003ePrimary Hypertension\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003eχ\u0026sup2;=4.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.027\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e19326 (99.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18759 (99.72)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e567 (99.13)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e57 (0.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e52 (0.28)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e5 (0.87)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"6\"\u003eBMI\u0026thinsp;=\u0026thinsp;body mass index. PAPPA\u0026thinsp;=\u0026thinsp;Pregnancy Associated Plasma Protein A. AFP\u0026thinsp;=\u0026thinsp;alpha fetoprotein. hcg-1\u0026thinsp;=\u0026thinsp;human chorionic gonadotropin (hcg) value tested in first trimester. hcg-2\u0026thinsp;=\u0026thinsp;hcg value tested in second trimester. M: Median, Q₁: 1st Quartile, Q₃: 3st Quartile, Z: Mann-Whitney test, χ\u0026sup2;: Chi-square test, -: Fisher exact. a. The conversion of MoM (multiple of the median) values is the ratio of the patient's test value to the average value of the full-term delivery population at the same gestational age.\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\n\u003ch3\u003eFeature selection by LASSO regression\u003c/h3\u003e\n\u003cp\u003eLASSO regression identified five significant factors associated with sPTB: age, education, type 2 diabetes mellitus, PAPPA, and AFP (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). These factors were selected for their non-zero regression coefficients after pre-screening with univariate logistic regression.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eSHAP analysis\u003c/h2\u003e\u003cp\u003eThe SHAP plot and bar chart highlighted AFP and PAPPA as the most influential features on the model output, with varying impacts across different instances (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). T2DM and age also contributed significantly, though with less variability compared to the serum markers. Education had a relatively smaller impact.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eModel performance\u003c/h2\u003e\u003cp\u003eThe predictive performance of the models was evaluated using a variety of metrics including AUC, accuracy, F1 score, sensitivity, specificity, PPV, and NPV. These metrics were calculated for both the training and validation datasets to assess the models' ability to generalize.\u003c/p\u003e\u003cp\u003eIn training dataset, the AUC for XGBoost model is 0.737, with a 95%CI of 0.705\u0026ndash;0.769 (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). The AUC for logistic model is 0.621, with a 95%CI of 0.586\u0026ndash;0.659. In validation dataset, the AUC for XGBoost model is 0.636, with a 95%CI of 0.570\u0026ndash;0.708. The AUC for logistic model is 0.570, with a 95%CI of 0.496\u0026ndash;0.647.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e provides a detailed comparison of the XGBoost and logistic models across various performance metrics. The XGBoost model consistently outperformed the logistic model in terms of accuracy, F1 score, sensitivity, and specificity in both the training and validation datasets. XGBoost model achieved an accuracy of 0.67 (95% CI: 0.64, 0.70), an F1 score of 0.63 (95% CI: 0.59, 0.66), a sensitivity of 0.55 (95% CI: 0.51, 0.60), and a specificity of 0.79 (95% CI: 0.76, 0.83). The PPV was 0.72 (95% CI: 0.68, 0.77), and the NPV was 0.64 (95% CI: 0.60, 0.68). The superiority of the XGBoost model is also maintained in the validation set (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003ePredictive power and 95% confidence intervals of models in train dataset for sPTB.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTrain Accuracy\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eTrain F1 Score\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eTrain Sensitivity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eTrain Specificity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eTrain PPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eTrain NPV\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.67(0.64, 0.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.63(0.59, 0.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.55(0.51, 0.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.79(0.76, 0.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.72(0.68, 0.77)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.64(0.6, 0.68)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.59(0.56, 0.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.59(0.56, 0.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.59(0.55, 0.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.59(0.55, 0.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.59(0.55, 0.63)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.59(0.54, 0.64)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"7\"\u003eXGBoost\u0026thinsp;=\u0026thinsp;eXtreme Gradient Boosting. PPV\u0026thinsp;=\u0026thinsp;positive predictive value. NPV\u0026thinsp;=\u0026thinsp;negative predictive value. All values are percentages and presented as predictive power (95% confidence interval).\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003ePredictive power and 95% confidence intervals of models in test dataset for sPTB.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eModel\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTest Accuracy\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eTest F1 Score\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eTest Sensitivity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eTest Specificity\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eTest PPV\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eTest NPV\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eXGBoost\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.59(0.53, 0.66)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.52(0.44, 0.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.45(0.36, 0.54)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.74(0.66, 0.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.63(0.53, 0.73)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.57(0.49, 0.65)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLogistic\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.55(0.49, 0.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.53(0.45, 0.61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.51(0.42, 0.6)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.6(0.52, 0.69)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.56(0.47, 0.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e0.55(0.46, 0.64)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"7\"\u003eXGBoost\u0026thinsp;=\u0026thinsp;eXtreme Gradient Boosting. PPV\u0026thinsp;=\u0026thinsp;positive predictive value. NPV\u0026thinsp;=\u0026thinsp;negative predictive value. All values are percentages and presented as predictive power (95% confidence interval).\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003eMain findings\u003c/h2\u003e\u003cp\u003eThis study successfully integrated maternal factors and serum markers to predict sPTB with enhanced accuracy using machine learning methods. The XGBoost model demonstrated superior predictive efficiency with an AUC of 0.737, indicating its potential as an effective tool for early identification and intervention. Advanced maternal age emerged as a critical risk factor, underscoring the importance of considering age in predictive models. Serum markers PAPP-A and AFP, reflecting placental function, were identified as primary influential factors, aligning with current understanding of placental insufficiency's role in sPTB.\u003c/p\u003e\u003cp\u003eThe method combining clinical features and serological indicators is significantly helpful in improving the predictive efficacy(9, 10). PAPP-A and AFP was identified as available predictors of spontaneous preterm birth (sPTB), which were thought to reflect placental function and integrity, which are critical factors in the pathogenesis of preterm birth(11, 12). One study indicated that elevated AFP/PAPP-A or AFP/β-HCG ratio in the first trimester is associated with increased risk for sPTB. The AFP/PAPP-A ratio\u0026thinsp;\u0026gt;\u0026thinsp;7 is associated with an increased risk of sPTB before 34 weeks with an odds ratio of 2.9, and the AFP/β-hCG ratio\u0026thinsp;\u0026gt;\u0026thinsp;0.6 indicates a 3.5-fold higher risk of sPTB before 32 weeks. AFP/PAPP-A\u0026thinsp;\u0026gt;\u0026thinsp;7 indicated 2.9 higher risk of preterm birth before 34 gestational weeks. Moreover, maternal serum AFP or hCG\u0026thinsp;\u0026gt;\u0026thinsp;2.0 MoM increases the risk of adverse pregnancy outcomes occurring before 37 gestational weeks, including preeclampsia, intrauterine growth restriction, fetal death(12). Therefore, women with elevated PAPPA and AFP levels should receive more rigorous monitoring and follow-up.\u003c/p\u003e\u003cp\u003eIncorporating machine learning into predictive models for sPTB presents a valuable opportunity to enhance prenatal care(13). Our model not only boosts the precision of predictions but also efficiently allocates resources by prioritizing the most critical factors. Early identification of pregnancies at high risk empowers healthcare providers to deliver focused interventions, which may decrease the occurrence of sPTB and its related complications. This approach is likely to lower medical expenses and increase operational efficiency in clinical environments, laying a solid groundwork for proactive intervention strategies.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003eStrength and limitations\u003c/h2\u003e\u003cp\u003eThis study's strength lies in its integration of machine learning techniques with a comprehensive set of maternal and serum markers to predict sPTB, which could enhance prenatal care. We verified the effectiveness of this model by using a randomly selected validation set, which is an important highlight compared to previous research. However, limitations include potential biases inherent in the retrospective study design, reliance on a single cohort that may affect generalizability, and the complexity of interpreting machine learning models, which may pose challenges for clinical application. Future research should focus on validating these models in diverse populations and improving their clinical interpretability.\u003c/p\u003e\u003c/div\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, this study demonstrates the potential of integrating maternal factors and serum markers with machine learning to predict sPTB (AUC 0.737). The XGBoost model particularly shows promise as a powerful tool for improving prenatal risk assessment and guiding early intervention strategies.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003esPTB\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003espontaneous preterm birth\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eBMI\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ebody mass index\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eT2DM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003etype 2 diabetes mellitus\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eβ-hCG\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eβ- human chorionic gonadotropin\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePAPPA\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003epregnancy associated plasma protein A\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAFP\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ealpha fetoprotein\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003euE3\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eunconjugated E3\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eMedian\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eMoM\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003emultiple of the median\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eIRB\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003einstitutional review board\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eLASSO\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eLeast Absolute Shrinkage and Selection Operator\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eXGBoost\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003eeXtreme Gradient Boosting\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eROC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003ereceiver operating characteristics\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003ePPV\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003epositive predictive value\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eNPV\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003enegative predictive value\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv class=\"DefinitionListEntry\"\u003e\u003cdiv class=\"Term\"\u003eAUC\u003c/div\u003e\u003cdiv class=\"Description\"\u003e\u003cp\u003earea under curve.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eEthical approval was obtained from the Institutional Review Board (IRB number: LGFYKYXMLL-2024-91). Informed consent was obtained from all subjects. All experiments were performed in accordance with the Declaration of Helsinki.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets used and analysed during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was funded by the National Natural Science Foundation of China (Grant No. 82471717).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026apos; contributions\u003cbr\u003e\u0026nbsp;\u003c/strong\u003eYing Gao wrote the original draft; Xiaoqin Huang and Caihua Tan contributed to the recruitment of the cohort population and data collection; Lingyan Chen and Xin Zhao jointly contributed to data analysis; Jinying Yang contributed to the conception of the manuscript and its review and editing.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThank you to all the pregnant women and staff who participated in this study.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003eOhuma EO, Moller AB, Bradley E, Chakwera S, Hussain-Alkhateeb L, Lewin A, et al. National, regional, and global estimates of preterm birth in 2020, with trends from 2010: a systematic analysis. Lancet. 2023;402(10409):1261-71.\u003c/li\u003e\n \u003cli\u003eBhattacharjee E, Maitra A. Spontaneous preterm birth: the underpinnings in the maternal and fetal genomes. NPJ Genom Med. 2021;6(1):43.\u003c/li\u003e\n \u003cli\u003eMericq V, Martinez-Aguayo A, Uauy R, I\u0026ntilde;iguez G, Van der Steen M, Hokken-Koelega A. Long-term metabolic risk among children born premature or small for gestational age. Nat Rev Endocrinol. 2017;13(1):50-62.\u003c/li\u003e\n \u003cli\u003eHughes K, Ford H, Thangaratinam S, Brennecke S, Mol BW, Wang R. Diagnosis or prognosis? An umbrella review of mid-trimester cervical length and spontaneous preterm birth. Bjog. 2023;130(8):866-79.\u003c/li\u003e\n \u003cli\u003ePrediction and Prevention of Spontaneous Preterm Birth: ACOG Practice Bulletin, Number 234. Obstet Gynecol. 2021;138(2):e65-e90.\u003c/li\u003e\n \u003cli\u003eMorgan TK. Role of the Placenta in Preterm Birth: A Review. Am J Perinatol. 2016;33(3):258-66.\u003c/li\u003e\n \u003cli\u003eGuibourdenche J, Leguy MC, Pidoux G, Hebert-Schuster M, Laguillier C, Anselem O, et al. Biochemical Screening for Fetal Trisomy 21: Pathophysiology of Maternal Serum Markers and Involvement of the Placenta. Int J Mol Sci. 2023;24(8):7669.\u003c/li\u003e\n \u003cli\u003eChen Y, Dai X, Wu B, Jiang C, Yin Y. Relationship between increased maternal serum free human chorionic gonadotropin levels in the second trimester and adverse pregnancy outcomes: a retrospective cohort study. BMC Womens Health. 2024;24(1):323.\u003c/li\u003e\n \u003cli\u003eChiu CPH, Feng Q, Chaemsaithong P, Sahota DS, Lau YY, Yeung YK, et al. Prediction of spontaneous preterm birth and preterm prelabor rupture of membranes using maternal factors, obstetric history and biomarkers of placental function at 11-13\u0026thinsp;weeks. Ultrasound Obstet Gynecol. 2022;60(2):192-9.\u003c/li\u003e\n \u003cli\u003eOskovi Kaplan ZA, Ozgu-Erdinc AS. Prediction of Preterm Birth: Maternal Characteristics, Ultrasound Markers, and Biomarkers: An Updated Overview. J Pregnancy. 2018;2018:8367571.\u003c/li\u003e\n \u003cli\u003eCelik E, Melekoğlu R, Bayg\u0026uuml;l A, Kalkan U, Şimşek Y. The predictive value of maternal serum AFP to PAPP-A or b-hCG ratios in spontaneous preterm birth. J Obstet Gynaecol. 2022;42(6):1956-61.\u003c/li\u003e\n \u003cli\u003eTancr\u0026egrave;de S, Bujold E, Gigu\u0026egrave;re Y, Renald MH, Girouard J, Forest JC. Mid-trimester maternal serum AFP and hCG as markers of preterm and term adverse pregnancy outcomes. J Obstet Gynaecol Can. 2015;37(2):111-6.\u003c/li\u003e\n \u003cli\u003eLamont RF, Richardson LS, Boniface JJ, Cobo T, Exner MM, Christensen IB, et al. Commentary on a combined approach to the problem of developing biomarkers for the prediction of spontaneous preterm labor that leads to preterm birth. Placenta. 2020;98:13-23.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-pregnancy-and-childbirth","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"prch","sideBox":"Learn more about [BMC Pregnancy and Childbirth](http://bmcpregnancychildbirth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/prch/default.aspx","title":"BMC Pregnancy and Childbirth","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"spontaneous preterm birth, predictive model, machine learning, serum markers","lastPublishedDoi":"10.21203/rs.3.rs-6970183/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6970183/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground:\u003c/strong\u003e Spontaneous preterm birth (sPTB) is a significant global health issue, contributing to neonatal morbidity and mortality. Existing predictive models for sPTB have shown limited accuracy, highlighting the need for improved prenatal care to identify high-risk pregnancies early. This study aimed to develop a more accurate predictive model by integrating maternal factors and serum markers using machine learning techniques.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods:\u003c/strong\u003e A retrospective cohort study was conducted using data from the Longgang Newborn cohort between January 1, 2020, and November 31, 2024. Women who delivered a singleton birth at 28–42 weeks’ gestation were included. We excluded cases of multiple pregnancy, iatrogenic preterm birth, cervical incompetence, and deliveries before 28 weeks. Data on maternal characteristics, pregnancy outcomes, and healthcare utilization were extracted. Predictors included maternal age, body mass index, pre-existing health conditions, socioeconomic variables, smoking status, gravidity, prior abortions, prior cesarean birth, and placental factors. We employed LASSO regression for feature selection and developed prediction models using XGBoost and logistic regression. Model performance was evaluated using sensitivity, specificity, PPV, NPV, and AUC.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e The study included 19383 participants, with 572 (2.94%) experiencing sPTB. LASSO regression identified five significant factors: age, education, type 2 diabetes mellitus, PAPPA, and AFP. The XGBoost model showed superior performance with an AUC of 0.737 in the training dataset and 0.636 in the validation dataset, outperforming the logistic model.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e Our XGBoost machine learning based model, offers a promising approach for predicting sPTB with high accuracy. The integration of maternal factors and serum markers could enhance prenatal care by identifying high-risk pregnancies earlier, potentially reducing the incidence of sPTB and its associated complications.\u003c/p\u003e","manuscriptTitle":"XGBoost-based prediction of spontaneous preterm birth using maternal factors and serum markers: a retrospective cohort study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-18 14:34:21","doi":"10.21203/rs.3.rs-6970183/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-30T06:18:33+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-29T20:49:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-22T12:25:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-19T11:07:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"46457390230355130008594424460495017778","date":"2025-07-17T07:44:11+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-07-16T08:37:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"296623553665558316897639995546107380717","date":"2025-07-16T08:26:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153872929694546675790697080106663295792","date":"2025-07-15T13:15:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"67215872451647770293634925687961755251","date":"2025-07-15T08:03:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"241301777648673694232175129556494744719","date":"2025-07-15T02:38:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-15T01:35:58+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-30T10:13:10+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-28T01:38:12+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-28T01:37:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Pregnancy and Childbirth","date":"2025-06-25T03:24:25+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-pregnancy-and-childbirth","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"prch","sideBox":"Learn more about [BMC Pregnancy and Childbirth](http://bmcpregnancychildbirth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/prch/default.aspx","title":"BMC Pregnancy and Childbirth","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"31c8ae63-44b5-4e87-9612-a2aab5f58b9e","owner":[],"postedDate":"July 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-11-24T16:09:03+00:00","versionOfRecord":{"articleIdentity":"rs-6970183","link":"https://doi.org/10.1186/s12884-025-08414-1","journal":{"identity":"bmc-pregnancy-and-childbirth","isVorOnly":false,"title":"BMC Pregnancy and Childbirth"},"publishedOn":"2025-11-18 15:57:22","publishedOnDateReadable":"November 18th, 2025"},"versionCreatedAt":"2025-07-18 14:34:21","video":"","vorDoi":"10.1186/s12884-025-08414-1","vorDoiUrl":"https://doi.org/10.1186/s12884-025-08414-1","workflowStages":[]},"version":"v1","identity":"rs-6970183","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6970183","identity":"rs-6970183","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}