{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T18:05:15Z","timestamp":1786125915036,"version":"build-2736575974"},"reference-count":22,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Breastfeeding duration is influenced by a complex interplay of obstetric, physiological, and sociodemographic factors. Traditional linear statistical models often struggle to capture the high-dimensional, non-linear synergistic effects among these variables, while complex deep learning models are prone to overfitting on small clinical datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      To address these challenges, this study proposes an interpretable machine learning framework based on\n                      <jats:bold>eXtreme Gradient Boosting (XGBoost)<\/jats:bold>\n                      . We analyzed clinical follow-up data from 210 postpartum women. The framework incorporates\n                      <jats:bold>Explicit Polynomial Feature Engineering<\/jats:bold>\n                      to construct high-order interaction terms and utilizes\n                      <jats:bold>SMOTE<\/jats:bold>\n                      to resolve class imbalance. Crucially,\n                      <jats:bold>SHAP (SHapley Additive exPlanations)<\/jats:bold>\n                      analysis was employed to provide bidirectional feature attribution.\n                      <jats:bold>Results:<\/jats:bold>\n                      The proposed model achieved robust, cross-validated performance with an\n                      <jats:bold>Accuracy of 76.2% (95% CI: 64.3%\u221288.1%)<\/jats:bold>\n                      , an\n                      <jats:bold>AUC of 0.72 (95% CI: 0.54\u20130.89)<\/jats:bold>\n                      , and a high\n                      <jats:bold>Recall of 0.92<\/jats:bold>\n                      for the long-term breastfeeding group (\u2265 11 months), outperforming traditional baselines. SHAP analysis identified critical non-linear risk patterns. Notably, the interaction between\n                      <jats:bold>\u201cDelivery Mode<\/jats:bold>\n                      \u00d7\n                      <jats:bold>Milk Stasis Duration\u201d<\/jats:bold>\n                      demonstrated that the protective effect of vaginal delivery mitigates stasis risks, whereas Cesarean sections disproportionately amplify the inhibitory effect of milk stasis. Additionally, the negative interaction of\n                      <jats:bold>\u201cEducation<\/jats:bold>\n                      \u00d7\n                      <jats:bold>Feeding Type\u201d<\/jats:bold>\n                      highlighted the compounded risk for highly educated mothers transitioning to mixed feeding.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study confirms that an interpretable XGBoost framework with explicit interaction features effectively overcomes the modeling bottlenecks of small-sample clinical data. By uncovering hidden synergistic risk factors, it provides a data-driven basis for precision lactation support, advocating for targeted interventions for specific high-risk profiles rather than generic education.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0354857","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:25:05Z","timestamp":1786123505000},"page":"e0354857","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncovering complex correlations between multidimensional factors and breastfeeding duration using XGBoost"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7733-5896","authenticated-orcid":true,"given":"Lijing","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanju","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"issue":"10017","key":"pone.0354857.ref001","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1016\/S0140-6736(15)01024-7","article-title":"Breastfeeding in the 21st century: epidemiology, mechanisms, and lifelong effect","volume":"387","author":"CG Victora","year":"2016","journal-title":"Lancet"},{"issue":"10017","key":"pone.0354857.ref002","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/S0140-6736(15)01044-2","article-title":"Why invest, and what it will take to improve breastfeeding practices?","volume":"387","author":"NC Rollins","year":"2016","journal-title":"Lancet"},{"issue":"8","key":"pone.0354857.ref003","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1038\/s41562-021-01108-6","article-title":"Mapping Inequalities in Exclusive Breastfeeding in Low- and Middle-Income Countries, 2000\u20132018","volume":"5","author":"Local Burden of Disease Exclusive Breastfeeding Collaborators","year":"2021","journal-title":"Nat Hum Behav"},{"key":"pone.0354857.ref004","doi-asserted-by":"crossref","first-page":"100971","DOI":"10.1016\/j.eclinm.2021.100971","article-title":"Global Prevalence of WHO Infant Feeding Practices in 57 LMICs in 2010\u20132018 and Time Trends since 2000 for 44 LMICs","volume":"37","author":"X Zong","year":"2021","journal-title":"eClinicalMedicine"},{"issue":"21","key":"pone.0354857.ref005","doi-asserted-by":"crossref","first-page":"8234","DOI":"10.3390\/ijerph17218234","article-title":"Breastfeeding in China: A Review of Changes in the Past Decade","volume":"17","author":"Q Li","year":"2020","journal-title":"Int J Environ Res Public Health"},{"issue":"6","key":"pone.0354857.ref006","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.3390\/nu15061353","article-title":"Factors Affecting the Breastfeeding Duration of Infants and Young Children in China: A Cross-Sectional Study","volume":"15","author":"Z Yang","year":"2023","journal-title":"Nutrients"},{"issue":"2","key":"pone.0354857.ref007","doi-asserted-by":"crossref","DOI":"10.1111\/mcn.13324","article-title":"What are the determinants of low exclusive breastfeeding prevalence in China? A cross-sectional study","volume":"18","author":"Y Duan","year":"2022","journal-title":"Matern Child Nutr"},{"key":"pone.0354857.ref008","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpeds.2018.08.008","article-title":"Factors Associated with Breastfeeding Initiation and Continuation: A Meta-Analysis","volume":"203","author":"SS Cohen","year":"2018","journal-title":"J Pediatr"},{"issue":"4","key":"pone.0354857.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/156482659601700427","article-title":"The Role of Education in Breastfeeding Success","volume":"17","author":"V Vald\u00e9s","year":"1996","journal-title":"Food Nutr Bull"},{"key":"pone.0354857.ref010","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1186\/s12884-016-0876-1","article-title":"The impact of caesarean section on breastfeeding initiation, duration and difficulties in the first four months postpartum","volume":"16","author":"AJ Hobbs","year":"2016","journal-title":"BMC Pregnancy Childbirth"},{"issue":"5","key":"pone.0354857.ref011","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.3945\/ajcn.111.030254","article-title":"Breastfeeding after cesarean delivery: a systematic review and meta-analysis of world literature","volume":"95","author":"E Prior","year":"2012","journal-title":"Am J Clin Nutr"},{"issue":"10","key":"pone.0354857.ref012","doi-asserted-by":"crossref","first-page":"2266","DOI":"10.3390\/nu11102266","article-title":"Breastfeeding Difficulties and Risk for Early Breastfeeding Cessation","volume":"11","author":"ML Gianni","year":"2019","journal-title":"Nutrients"},{"key":"pone.0354857.ref013","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/1746-4358-3-6","article-title":"The role of bacteria in lactational mastitis and some considerations of the use of antibiotic treatment","volume":"3","author":"LJ Kvist","year":"2008","journal-title":"Int Breastfeed J"},{"issue":"2","key":"pone.0354857.ref014","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.ejogrb.2003.10.041","article-title":"Predictive factors of early cessation of breastfeeding","volume":"117","author":"SD Lathouwer","year":"2004","journal-title":"Eur J Obstet Gynecol Reprod Biol"},{"issue":"1","key":"pone.0354857.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0312238","article-title":"Predicting early cessation of exclusive breastfeeding using machine learning techniques","volume":"20","author":"FM Nejsum","year":"2025","journal-title":"PLoS One"},{"key":"pone.0354857.ref016","doi-asserted-by":"crossref","first-page":"183","DOI":"10.4314\/dujopas.v7i4a.19","article-title":"Predicting breastfeeding practice of Nigerian child using machine learning and deep learning algorithms","volume":"7","author":"JO Yusuf","year":"2022","journal-title":"dujopas"},{"issue":"14","key":"pone.0354857.ref017","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine Learning in Medicine","volume":"380","author":"A Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"key":"pone.0354857.ref018","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM; 2016. p. 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"key":"pone.0354857.ref019","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.artmed.2016.12.003","article-title":"Handling limited datasets with neural networks in medical applications: A small-data approach","volume":"75","author":"T Shaikhina","year":"2017","journal-title":"Artif Intell Med"},{"key":"pone.0354857.ref020","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)","volume":"6","author":"A Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"pone.0354857.ref021","doi-asserted-by":"crossref","first-page":"103655","DOI":"10.1016\/j.jbi.2020.103655","article-title":"The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies","volume":"113","author":"AF Markus","year":"2021","journal-title":"J Biomed Inform"},{"key":"pone.0354857.ref022","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"jair"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:25:09Z","timestamp":1786123509000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354857"}},"subtitle":[],"editor":[{"given":"Kwang-Sig","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":22,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,7]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0354857","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]}}}