{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T06:04:46Z","timestamp":1789452286273,"version":"build-2803163510"},"reference-count":62,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"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. Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Postpartum depression (PPD) is associated with severe adverse outcomes, yet timely risk stratification remains challenging. Existing machine learning models are often limited by insufficient external validation, limited interpretability, and lack of accessible clinical tools. This study aimed to develop and externally validate an explainable machine learning model with a web-based calculator for predicting postpartum depressive symptoms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cohort study included 553 women from two hospitals, comprising 403 in the development cohort and 150 in an independent external validation cohort. The development cohort was divided into training and internal test sets. Screening-positive postpartum depressive symptoms at 6 weeks postpartum were defined as an Edinburgh Postnatal Depression Scale (EPDS) score \u22659. Five machine learning models were developed using demographic, psychosocial, and obstetric predictors. Model discrimination was assessed using the area under the receiver operating characteristic curve (AUC), with calibration and decision curve analyses performed additionally. SHapley Additive exPlanations (SHAP) were used for model interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Screening-positive rates were 38.0% in the development cohort and 26.0% in the external validation cohort. Tree-based ensemble models showed broadly comparable performance. eXtreme Gradient Boosting (XGBoost) was selected based on its numerically highest mean cross-validated AUC and balanced overall performance, with AUCs of 0.895 \u00b1 0.033 in cross-validation, 0.845 (95% confidence interval [CI]: 0.751\u20130.940) in the internal test set, and 0.820 (95% CI: 0.743\u20130.889) in the external validation cohort. Calibration was acceptable in the internal test set, whereas absolute risk was overestimated in the external validation cohort. Decision curve analysis indicated potential net clinical benefit. SHAP identified age, marital relationship quality, prenatal depressive symptoms, monthly personal income, and sleep disturbance as important model-based contributors. A four-predictor web calculator was developed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The explainable XGBoost model showed promising discrimination for predicting EPDS-defined postpartum depressive symptoms. However, given the modest external validation sample and evidence of risk overestimation, further prospective multicenter validation and recalibration are needed before routine clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2026.1887667","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:36:37Z","timestamp":1789450597000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and external validation of an explainable XGBoost model with a web-based calculator for risk prediction of postpartum depressive symptoms"],"prefix":"10.3389","volume":"17","author":[{"given":"Qian","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Obstetrics and Gynecology, the Second People\u2019s Hospital of Bengbu City","place":["Bengbu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, General Hospital of Huainan Oriental Hospital Group","place":["Huainan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, the Second People\u2019s Hospital of Bengbu City","place":["Bengbu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liwei","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, the Second People\u2019s Hospital of Bengbu City","place":["Bengbu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMcp1607649","article-title":"Postpartum depression","volume":"375","author":"Stewart","year":"2016","journal-title":"N Engl J Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1038\/s41398-021-01663-6","article-title":"Mapping global prevalence of depression among postpartum women","volume":"11","author":"Wang","year":"2021","journal-title":"Transl Psychiatry"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2023.0069","article-title":"Prevalence of perinatal depression in low- and middle-income countries a systematic review and meta-analysis","volume":"80","author":"Roddy Mitchell","year":"2023","journal-title":"JAMA Psychiatry"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2018.08.001","article-title":"Prevalence and incidence of postpartum depression among healthy mothers: a systematic review and meta-analysis","volume":"104","author":"Shorey","year":"2018","journal-title":"J Psychiatr Res"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.46486","article-title":"Trends in postpartum depression by race, ethnicity, and prepregnancy body mass index","volume":"7","author":"Khadka","year":"2024","journal-title":"JAMA Netw Open"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fgwh.2024.1347388","article-title":"A consensus statement on perinatal mental health during the COVID-19 pandemic and recommendations for post-pandemic recovery and re-build","volume":"5","author":"Jackson","year":"2024","journal-title":"Front Glob Womens Health"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2021.06.058","article-title":"Maternal thoughts of self-harm and their association with future offspring mental health problems","volume":"293","author":"Paul","year":"2021","journal-title":"J Affect Disord"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s00737-021-01121-8","article-title":"Perinatal suicidality: prevalence and correlates in a South African birth cohort","volume":"24","author":"Mare","year":"2021","journal-title":"Arch Womens Ment Health"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2021.00615","article-title":"Preventing pregnancy-related mental health deaths: insights from 14 US maternal mortality review committees, 2008-17","volume":"40","author":"Trost","year":"2021","journal-title":"Health Aff"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1177\/1745506519844044","article-title":"Consequences of maternal postpartum depression: a systematic review of maternal and infant outcomes","volume":"15","author":"Slomian","year":"2019","journal-title":"Womens Health (Lond)"},{"key":"B11","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.jad.2021.05.088","article-title":"Factors influencing paternal postpartum depression: a systematic review and meta-analysis","volume":"293","author":"Wang","year":"2021","journal-title":"J Affect Disord"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.4088\/JCP.20m13735","article-title":"Postpartum depression and psychosis and subsequent severe mental illnesses in mothers and neurodevelopmental disorders in children: a nationwide study","volume":"82","author":"Chen","year":"2021","journal-title":"J Clin Psychiatry"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1111\/jog.14064","article-title":"Does maternal postpartum depression affect children's developmental outcomes","volume":"45","author":"Aoyagi","year":"2019","journal-title":"J Obstet Gynaecol Res"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2017.12.013","article-title":"Effect of maternal postpartum depression on offspring's growth","volume":"228","author":"Farias-Antunez","year":"2018","journal-title":"J Affect Disord"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20769","article-title":"Perinatal mental health: a review of progress and challenges","volume":"19","author":"Howard","year":"2020","journal-title":"World Psychiatry"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1186\/s12871-021-01543-y","article-title":"Postoperative delirium prediction using machine learning models and preoperative electronic health record data","volume":"22","author":"Bishara","year":"2022","journal-title":"BMC Anesthesiol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103507","article-title":"Development and validation of a machine learning-based model for 90-day prognosis outcome in spontaneous intracerebral hemorrhage patients based on non-contrast computed tomography: a multicenter retrospective observational study","volume":"88","author":"Wei","year":"2025","journal-title":"EClinicalMedicine"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-052008","article-title":"Assessment of difference in postpartum depression among caesarean and vaginally delivered women at 6-week follow-up in hospitals in Pune District, India: an observational cohort study","volume":"11","author":"Doke","year":"2021","journal-title":"BMJ Open"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2020.11.053","article-title":"Postpartum depression and its association with intimate partner violence and inadequate social support in Ethiopia: a systematic review and meta-analysis","volume":"279","author":"Desta","year":"2021","journal-title":"J Affect Disord"},{"key":"B20","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1186\/s12888-019-2401-3","article-title":"Education level and risk of postpartum depression: results from the Japan Environment and Children's Study (JECS)","volume":"19","author":"Matsumura","year":"2019","journal-title":"BMC Psychiatry"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2022.08.070","article-title":"Application of machine learning in predicting the risk of postpartum depression: a systematic review","volume":"318","author":"Zhong","year":"2022","journal-title":"J Affect Disord"},{"key":"B22","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1186\/s12884-021-04087-8","article-title":"Estimation of postpartum depression risk from electronic health records using machine learning","volume":"21","author":"Amit","year":"2021","journal-title":"BMC Pregnancy Childbirth"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2022.04.093","article-title":"Machine learning in the prediction of postpartum depression: a review","volume":"309","author":"Cellini","year":"2022","journal-title":"J Affect Disord"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.11817\/j.issn.1672-7347.2020.190655","article-title":"Risk prediction for postpartum depression based on random forest","volume":"45","author":"Xiao","year":"2020","journal-title":"Zhong Nan Da Xue Xue Bao Yi Xue Ban"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1002\/da.23123","article-title":"Development and validation of a machine learning-based postpartum depression prediction model: a nationwide cohort study","volume":"38","author":"Hochman","year":"2021","journal-title":"Depress Anxiety"},{"key":"B26","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1186\/s12967-025-06289-6","article-title":"Prediction of postpartum depression in women: development and validation of multiple machine learning models","volume":"23","author":"Qi","year":"2025","journal-title":"J Transl Med"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.2196\/15516","article-title":"Machine learning models for the prediction of postpartum depression: application and comparison based on a cohort study","volume":"8","author":"Zhang","year":"2020","journal-title":"JMIR Med Inform"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jad.2020.09.113","article-title":"Development and validation of a machine learning algorithm for predicting the risk of postpartum depression among pregnant women","volume":"279","author":"Zhang","year":"2021","journal-title":"J Affect Disord"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1565374","article-title":"Postpartum depression risk prediction using explainable machine learning algorithms","volume":"12","author":"Huang","year":"2025","journal-title":"Front Med"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1097\/00006199-200109000-00004","article-title":"Predictors of postpartum depression: an update","volume":"50","author":"Beck","year":"2001","journal-title":"Nurs Res"},{"key":"B31","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.jad.2015.11.014","article-title":"Identifying the women at risk of antenatal anxiety and depression: a systematic review","volume":"191","author":"Biaggi","year":"2016","journal-title":"J Affect Disord"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.midw.2026.104778","article-title":"Risk-prediction models for postpartum depression: assessment of risk of bias using PROBAST+AI","volume":"159","author":"Wang","year":"2026","journal-title":"Midwifery"},{"key":"B33","doi-asserted-by":"publisher","first-page":"768","DOI":"10.3390\/nu15030768","article-title":"Association between Edinburgh Postnatal Depression Scale and serum levels of ketone bodies and vitamin D, thyroid function, and iron metabolism","volume":"15","author":"Noshiro","year":"2023","journal-title":"Nutrients"},{"key":"B34","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1186\/s12967-024-04896-3","article-title":"Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcome of patients with spontaneous intracerebral hemorrhage","volume":"22","author":"Geng","year":"2024","journal-title":"J Transl Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13080897","article-title":"Predictive analysis of postpartum depression using machine learning","volume":"13","author":"Kim","year":"2025","journal-title":"Healthc"},{"key":"B37","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1186\/s12967-020-02620-5","article-title":"Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost","volume":"18","author":"Hou","year":"2020","journal-title":"J Transl Med"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.wneu.2022.04.044","article-title":"XGBoost machine learning algorism performed better than regression models in predicting mortality of moderate-to-severe traumatic brain injury","volume":"163","author":"Wang","year":"2022","journal-title":"World Neurosurg"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.i3140","article-title":"External validation of clinical prediction models using big datasets from e-health records or IPD meta-analysis: opportunities and challenges","volume":"353","author":"Riley","year":"2016","journal-title":"Bmj"},{"key":"B40","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1186\/s12874-022-01801-8","article-title":"Methodological guidance for the evaluation and updating of clinical prediction models: a systematic review","volume":"22","author":"Binuya","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"van der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100804","article-title":"Leakage and the reproducibility crisis in machine-learning-based science","volume":"4","author":"Kapoor","year":"2023","journal-title":"Patterns (N Y)"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1002\/sim.9025","article-title":"Minimum sample size for external validation of a clinical prediction model with a binary outcome","volume":"40","author":"Riley","year":"2021","journal-title":"Stat Med"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1111\/jocn.16121","article-title":"Prevalence and risk factors of postpartum depression in women: a systematic review and meta-analysis","volume":"31","author":"Liu","year":"2022","journal-title":"J Clin Nurs"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2024.01.135","article-title":"Prevalence and risk factors of postpartum depressive symptoms at 42 days among 2462 women in China","volume":"350","author":"Wang","year":"2024","journal-title":"J Affect Disord"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2020.07.046","article-title":"Prevalence of perinatal depression and its determinants in Mainland China: a systematic review and meta-analysis","volume":"277","author":"Nisar","year":"2020","journal-title":"J Affect Disord"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1111\/jocn.16351","article-title":"Postpartum depression and social support: a longitudinal study of the first six months as parents","volume":"32","author":"Zheng","year":"2023","journal-title":"J Clin Nurs"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.172.5.433","article-title":"Detecting postnatal depression in Chinese women. Validation of the Chinese version of the Edinburgh Postnatal Depression Scale","volume":"172","author":"Lee","year":"1998","journal-title":"Br J Psychiatry"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m4022","article-title":"Accuracy of the Edinburgh Postnatal Depression Scale (EPDS) for screening to detect major depression among pregnant and postpartum women: systematic review and meta-analysis of individual participant data","volume":"371","author":"Levis","year":"2020","journal-title":"BMJ"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9092899","article-title":"Machine learning-based predictive modeling of postpartum depression","volume":"9","author":"Shin","year":"2020","journal-title":"J Clin Med"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1007\/s10995-012-1089-5","article-title":"Postpartum depression in adolescent and adult mothers: comparing prenatal risk factors and predictive models","volume":"17","author":"Nunes","year":"2013","journal-title":"Matern Child Health J"},{"key":"B54","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1624\/105812402X88939","article-title":"Postpartum depression, marital dysfunction, and infant outcome: a longitudinal study","volume":"11","author":"Roux","year":"2002","journal-title":"J Perinat Educ"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1111\/jog.15266","article-title":"Machine learning prediction models for postpartum depression: a multicenter study in Japan","volume":"48","author":"Matsuo","year":"2022","journal-title":"J Obstet Gynaecol Res"},{"key":"B56","doi-asserted-by":"publisher","first-page":"7877","DOI":"10.1038\/s41598-021-86368-y","article-title":"Predicting women with depressive symptoms postpartum with machine learning methods","volume":"11","author":"Andersson","year":"2021","journal-title":"Sci Rep"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2011.12.008","article-title":"Clinical relevance of comorbidity in anxiety disorders: a report from the Netherlands Study of Depression and Anxiety (NESDA)","volume":"137","author":"Hofmeijer-Sevink","year":"2012","journal-title":"J Affect Disord"},{"key":"B58","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.whi.2009.11.003","article-title":"How much does low socioeconomic status increase the risk of prenatal and postpartum depressive symptoms in first-time mothers","volume":"20","author":"Goyal","year":"2010","journal-title":"Womens Health Issues"},{"key":"B59","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.jad.2023.10.103","article-title":"The predictive effect of mid-pregnancy sleep disorders on perinatal depression within women with or without depression in early pregnancy: a prospective cohort study","volume":"345","author":"Bai","year":"2024","journal-title":"J Affect Disord"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1038\/s41577-019-0190-z","article-title":"Sleep and inflammation: partners in sickness and in health","volume":"19","author":"Irwin","year":"2019","journal-title":"Nat Rev Immunol"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2011.01.011","article-title":"Insomnia as a predictor of depression: a meta-analytic evaluation of longitudinal epidemiological studies","volume":"135","author":"Baglioni","year":"2011","journal-title":"J Affect Disord"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2018.2530","article-title":"The science of prognosis in psychiatry a review","volume":"75","author":"Fusar-Poli","year":"2018","journal-title":"JAMA Psychiatry"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1887667\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:36:39Z","timestamp":1789450599000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1887667\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":62,"alternative-id":["10.3389\/fpsyt.2026.1887667"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2026.1887667","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]},"article-number":"1887667"}}