{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T21:55:59Z","timestamp":1784757359754,"version":"3.55.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Early-onset preeclampsia (EOPE) represents a particularly severe clinical subtype of preeclampsia (PE) and is frequently complicated by placental abruption, which can result in serious maternal and fetal morbidity or mortality. This study aimed to develop and validate an interpretable machine learning (IML) model for predicting placental abruption in patients with EOPE.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective cohort of 580 EOPE patients who delivered between January 2021 and June 2025 was analyzed and randomly divided into training (70%) and validation (30%) sets. Dual-step feature selection combining LASSO regression and the Boruta algorithm identified the most relevant predictors. Six supervised algorithms, including decision tree (DT), k-nearest neighbor (KNN), logistic regression, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost), were developed and compared. Model performance was evaluated using AUC, F1 score, calibration curve, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) were employed for model interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Eight optimal predictors were selected: urinary protein, placental growth factor (PlGF), diastolic blood pressure (DBP), age, fibrinogen (FIB), prepregnancy BMI, disease severity, and smoking during pregnancy. The RF model achieved the best performance (training AUC\u202f=\u202f0.968; validation AUC\u202f=\u202f0.894), along with the highest accuracy and F1 score among all algorithms. Calibration curves showed strong consistency between predicted and observed probabilities, and DCA confirmed greater net clinical benefit across a wide range of threshold probabilities. The confusion matrix demonstrated high sensitivity and specificity, indicating stable classification performance. SHAP analysis revealed that urinary protein, PlGF, FIB, and DBP were the dominant predictors, where elevated urinary protein and DBP and reduced FIB and PlGF significantly increased abruption risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The SHAP-based RF model demonstrated high predictive accuracy and interpretability, providing a transparent, data-driven framework for individualized risk assessment of placental abruption in EOPE. This interpretable approach may facilitate early risk identification and personalized management in clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2025.1731693","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T09:03:12Z","timestamp":1768208592000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Interpretable machine learning for predicting placental abruption in early-onset preeclampsia: model development and evaluation"],"prefix":"10.3389","volume":"12","author":[{"given":"Lijun","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingli","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiying","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1038\/s41581-019-0119-6","article-title":"Pre-eclampsia: pathogenesis, novel diagnostics and therapies","volume":"15","author":"Phipps","year":"2019","journal-title":"Nat Rev Nephrol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1016\/s0140-6736(15)00070-7","article-title":"Pre-eclampsia","volume":"387","author":"Mol","year":"2016","journal-title":"Lancet"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1097\/OGX.0b013e3182331028","article-title":"A critical review of early-onset and late-onset preeclampsia","volume":"66","author":"Raymond","year":"2011","journal-title":"Obstet Gynecol Surv"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"87","DOI":"10.23736\/s2724-5276.22.06714-3","article-title":"Consequences of early-onset preeclampsia on neonatal morbidity and mortality","volume":"75","author":"Rocha","year":"2023","journal-title":"Minerva Pediatr (Torino)"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"272.e1","DOI":"10.1016\/j.ajog.2015.09.069","article-title":"Severe placental abruption: clinical definition and associations with maternal complications","volume":"214","author":"Ananth","year":"2016","journal-title":"Am J Obstet Gynecol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1097\/01.AOG.0000239439.04364.9a","article-title":"Placental abruption","volume":"108","author":"Oyelese","year":"2006","journal-title":"Obstet Gynecol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.placenta.2019.07.003","article-title":"Are maternal and neonatal outcomes different in placental abruption between women with and without preeclampsia?","volume":"85","author":"Han","year":"2019","journal-title":"Placenta"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jri.2019.07.004","article-title":"The two-stage placental model of preeclampsia: an update","author":"Staff","year":"2019","journal-title":"J Reprod Immunol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1111\/j.1600-0412.2010.01030.x","article-title":"Placental abruption: epidemiology, risk factors and consequences","volume":"90","author":"Tikkanen","year":"2011","journal-title":"Acta Obstet Gynecol Scand"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e16503","DOI":"10.2196\/16503","article-title":"Comparison of multivariable logistic regression and other machine learning algorithms for prognostic prediction studies in pregnancy care: systematic review and Meta-analysis","volume":"8","author":"Sufriyana","year":"2020","journal-title":"JMIR Med Inform"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s11906-024-01297-1","article-title":"Machine learning algorithms versus classical regression models in pre-eclampsia prediction: a systematic review","volume":"26","author":"Tiruneh","year":"2024","journal-title":"Curr Hypertens Rep"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"959649","DOI":"10.3389\/fcvm.2022.959649","article-title":"Comparison of machine learning and logistic regression as predictive models for adverse maternal and neonatal outcomes of preeclampsia: a retrospective study","volume":"9","author":"Zheng","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1186\/s12884-022-04594-2","article-title":"Machine learning to predict pregnancy outcomes: a systematic review, synthesizing framework and future research agenda","volume":"22","author":"Islam","year":"2022","journal-title":"BMC Pregnancy Childbirth"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"780389","DOI":"10.3389\/fbioe.2021.780389","article-title":"Using machine learning to predict complications in pregnancy: a systematic review","volume":"9","author":"Bertini","year":"2021","journal-title":"Front Bioeng Biotechnol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12884-023-06220-1","article-title":"Machine learning models for predicting preeclampsia: a systematic review","volume":"24","author":"Ranjbar","year":"2024","journal-title":"BMC Pregnancy Childbirth"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1111\/joim.12822","article-title":"eDoctor: machine learning and the future of medicine","volume":"284","author":"Handelman","year":"2018","journal-title":"J Intern Med"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"91","DOI":"10.11622\/smedj.2021054","article-title":"Machine learning in medicine: what clinicians should know","volume":"64","author":"Ting Sim","year":"2023","journal-title":"Singapore Med J"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1016\/j.tig.2020.03.005","article-title":"Opening the black box: interpretable machine learning for geneticists","volume":"36","author":"Azodi","year":"2020","journal-title":"Trends Genet"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch","year":"2019","journal-title":"Proc Natl Acad Sci USA"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e83961","DOI":"10.7759\/cureus.83961","article-title":"Artificial intelligence applications in obstetric risk prediction: a systematic review of machine learning models for preeclampsia","volume":"17","author":"Mohamed Dkeen","year":"2025","journal-title":"Cureus"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1161\/atvbaha.124.321673","article-title":"Artificial intelligence and machine learning in preeclampsia","volume":"45","author":"Layton","year":"2025","journal-title":"Arterioscler Thromb Vasc Biol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e237","DOI":"10.1097\/aog.0000000000003891","article-title":"Gestational hypertension and preeclampsia: ACOG practice bulletin, number 222","volume":"135","year":"2020","journal-title":"Obstet Gynecol"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1097\/grf.0000000000000903","article-title":"Placental abruption: pathophysiology, diagnosis, and management","volume":"68","author":"Schneider","year":"2025","journal-title":"Clin Obstet Gynecol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using Shapley additive explanation and application for real data in hospital","volume":"214","author":"Nohara","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e0284315","DOI":"10.1371\/journal.pone.0284315","article-title":"Interpretable machine learning with tree-based Shapley additive explanations: application to metabolomics datasets for binary classification","volume":"18","author":"Bifarin","year":"2023","journal-title":"PLoS One"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.placenta.2025.03.005","article-title":"Development and validation of a risk prediction model for placental abruption in patients with preeclampsia","volume":"164","author":"Yang","year":"2025","journal-title":"Placenta"},{"key":"ref27","first-page":"9","article-title":"A risk factor analysis and prediction model of placental abruption","volume":"12","author":"Huang","year":"2019","journal-title":"Int J Clin Exp Med"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"e00206116","DOI":"10.1590\/0102-311x00206116","article-title":"Advanced maternal age and its association with placenta praevia and placental abruption: a meta-analysis","volume":"34","author":"Martinelli","year":"2018","journal-title":"Cad Saude Publica"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"5548","DOI":"10.1038\/s41598-017-04026-8","article-title":"Mother's pre-pregnancy BMI and placental candidate miRNAs: findings from the ENVIRONAGE birth cohort","volume":"7","author":"Tsamou","year":"2017","journal-title":"Sci Rep"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1201","DOI":"10.1007\/s00404-019-05320-8","article-title":"The impact of pre-pregnancy body mass index and gestational weight gain on placental abruption risk: a systematic review and meta-analysis","volume":"300","author":"Adane","year":"2019","journal-title":"Arch Gynecol Obstet"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1038\/s41371-023-00802-4","article-title":"Placental syndromes and long-term risk of hypertension","volume":"37","author":"Fraser","year":"2023","journal-title":"J Hum Hypertens"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1097\/hjh.0000000000003486","article-title":"Maternal hypertensive traits and adverse outcome in pregnancy: a Mendelian randomization study","volume":"41","author":"Ardissino","year":"2023","journal-title":"J Hypertens"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1179\/acb.2010.035","article-title":"Management of severe preeclampsia","volume":"65","author":"Brichant","year":"2010","journal-title":"Acta Clin Belg"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"S1313","DOI":"10.1016\/j.ajog.2022.06.059","article-title":"Placental abruption at near-term and term gestations: pathophysiology, epidemiology, diagnosis, and management","volume":"228","author":"Brandt","year":"2023","journal-title":"Am J Obstet Gynecol"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e089499","DOI":"10.1136\/bmjopen-2024-089499","article-title":"Impact of maternal smoking and secondhand smoke exposure during singleton pregnancy on placental abruption: analysis of a prospective cohort study (the Japan environment and children's study)","volume":"15","author":"Karumai-Mori","year":"2025","journal-title":"BMJ Open"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1002\/pd.5660","article-title":"The impact of tobacco chemicals and nicotine on placental development","volume":"40","author":"Suter","year":"2020","journal-title":"Prenat Diagn"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"13","DOI":"10.3390\/cells13121009","article-title":"Different lengths of gestational exposure to secondhand smoke or e-cigarette vapor induce the development of placental disease symptoms","volume":"13","author":"Kirkham","year":"2024","journal-title":"Cells"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"25","DOI":"10.3390\/ijms25052741","article-title":"Placental and renal pathways underlying pre-eclampsia","volume":"25","author":"Andronikidi","year":"2024","journal-title":"Int J Mol Sci"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"20503121211058053","DOI":"10.1177\/20503121211058053","article-title":"Association between proteinuria and placental pathology in preeclampsia: a retrospective study","volume":"9","author":"Genest","year":"2021","journal-title":"SAGE Open Med"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1002\/ijgo.14417","article-title":"Fibrinogen for the prediction of severe maternal complications in placental abruption with fetal death after 24 weeks of gestation","volume":"160","author":"Atallah","year":"2023","journal-title":"Int J Gynaecol Obstet"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.blre.2016.08.004","article-title":"Placental growth factor: what hematologists need to know","volume":"31","author":"Newell","year":"2017","journal-title":"Blood Rev"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1097\/01.Aog.0000216014.72503.09","article-title":"Circulating angiogenic factors and placental abruption","volume":"108","author":"Signore","year":"2006","journal-title":"Obstet Gynecol"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1731693\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T09:03:12Z","timestamp":1768208592000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1731693\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":42,"alternative-id":["10.3389\/fmed.2025.1731693"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1731693","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1731693"}}