{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T15:50:07Z","timestamp":1792338607006,"version":"4.4.0"},"reference-count":40,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Gestational diabetes mellitus (GDM) affects over 5% of pregnancies worldwide, elevating risks of type 2 diabetes post partum and complications such as fetal death, miscarriage, and congenital abnormalities. Effective GDM management is essential to balance glycemic control and pregnancy outcomes.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n We aim to develop interpretable machine learning models using GDM datasets for predicting adverse pregnancy outcomes and identifying key factors through the Shapley additive explanations (SHAP) algorithm, thus supporting improved maternal and infant health.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Data preprocessing and feature selection were performed, with adaptive synthetic sampling used to address class imbalance. Classification models, including logistic regression, random forest, support vector machine, and extreme gradient boosting, were built and enhanced through the stacking method. Model interpretability was assessed with SHAP to quantify feature contributions.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Among 1670 patients, 200 experienced adverse outcomes. The stacking model outperformed individual models, achieving an accuracy of 85.6%, a sensitivity of 57.8%, a specificity of 95.9%, and an area under the receiver operating characteristic curve of 0.82 on the test set. External validation on 159 patients showed a decline in performance (accuracy 83.6%, area under the receiver operating characteristic curve 0.67). SHAP analysis identified gestational age, glucose control, and diagnosis time among the most influential predictors, providing clinically meaningful insights into risk factors. Additionally, detailed SHAP-based visualization revealed the distribution of different feature values and their nonlinear impact on outcomes, as well as interaction effects between features. These interpretable analyses enabled a deeper understanding of individual and combined feature contributions, thereby enhancing clinical assessment capabilities.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This study underscores the potential of machine learning in predicting adverse outcomes in GDM, with interpretable features offering valuable clinical insights to enhance pregnancy management and maternal-infant health.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/71539","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T07:42:42Z","timestamp":1758094962000},"page":"e71539-e71539","source":"Crossref","is-referenced-by-count":12,"title":["Interpretable Machine Learning for Predicting Adverse Pregnancy Outcomes in Gestational Diabetes: Retrospective Cohort Study"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9820-8461","authenticated-orcid":false,"given":"Jiaxi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8625-1184","authenticated-orcid":false,"given":"Xiali","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1224-6580","authenticated-orcid":false,"given":"Shenyang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4519-397X","authenticated-orcid":false,"given":"Yan","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"R1","unstructured":"Rodriguez BSQ Vadakekut ES Mahdy H . Gestational Diabetes. StatPearls; 2023. URL: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK545196\/ [Accessed 17-07-2025]"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/5320156","article-title":"Determinants of maternal insulin resistance during pregnancy: an updated overview","volume":"2019","author":"Kampmann","journal-title":"J Diabetes Res"},{"key":"R3","unstructured":"Magliano DJ Boyko EJ IDF Diabetes Atlas 10th Edition Scientific Committee. IDF Diabetes Atlas. 10th ed. International Diabetes Federation; 2021. [Medline: 35914061]"},{"issue":"17","key":"R4","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph191710846","article-title":"A systematic review to compare adverse pregnancy outcomes in women with pregestational diabetes and gestational diabetes","volume":"19","author":"Malaza","journal-title":"Int J Environ Res Public Health"},{"issue":"6","key":"R5","doi-asserted-by":"publisher","DOI":"10.3390\/nu11061210","article-title":"Effectiveness of following mediterranean diet recommendations in the real world in the incidence of gestational diabetes mellitus (GDM) and adverse maternal-foetal outcomes: a prospective, universal, interventional study with a single group. The St Carlos study","volume":"11","author":"de la Torre","journal-title":"Nutrients"},{"issue":"7","key":"R6","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1016\/j.jogc.2016.04.002","article-title":"RETIRED: diabetes in pregnancy","volume":"38","author":"Berger","journal-title":"J Obstet Gynaecol Can"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1093\/qjmed\/hcaa167","article-title":"Early gestational diabetes mellitus (GDM) is associated with worse pregnancy outcomes compared with GDM diagnosed at 24-28\u2009weeks gestation despite early treatment","volume":"114","author":"Mustafa","journal-title":"QJM"},{"issue":"12","key":"R8","doi-asserted-by":"publisher","DOI":"10.1007\/s11892-019-1267-6","article-title":"Hyperglycemia during pregnancy and long-term offspring outcomes","volume":"19","author":"Bianco","journal-title":"Curr Diab Rep"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.9.2.14","article-title":"Introduction to machine learning, neural networks, and deep learning","volume":"9","author":"Choi","journal-title":"Transl Vis Sci Technol"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-023-05486-9","article-title":"Application of machine learning to identify risk factors of birth asphyxia","volume":"23","author":"Darsareh","journal-title":"BMC Pregnancy Childbirth"},{"issue":"7","key":"R11","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.41448","article-title":"Machine learning-based approach to predict intrauterine growth restriction","volume":"15","author":"Taeidi","journal-title":"Cureus"},{"issue":"1","key":"R12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-92810-2","article-title":"Proposing a machine learning-based model for predicting nonreassuring fetal heart","volume":"15","author":"Roozbeh","journal-title":"Sci Rep"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Jeyaparam S Agha-Jaffar R Robinson S Khunti K . Association of socioeconomic deprivation on gestational diabetes incidence and perinatal outcomes. Research Square. Preprint posted online on 2023. [doi: 10.21203\/rs.3.rs-2410272\/v1]","DOI":"10.21203\/rs.3.rs-2410272\/v1"},{"key":"R14","unstructured":"GDM dataset.xlsx. figshare. URL: https:\/\/figshare.com\/articles\/dataset\/GDM_Dataset_xlsx\/21806472?file=38695140 [Accessed 26-06-2025]"},{"issue":"8","key":"R15","doi-asserted-by":"publisher","DOI":"10.1007\/s11892-018-1023-3","article-title":"Methods for measuring risk for type 2 diabetes in youth: the oral glucose tolerance test (OGTT)","volume":"18","author":"Chen","journal-title":"Curr Diab Rep"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph19042063","article-title":"Predictors of adverse pregnancy outcomes in pregnant women living with obesity: a systematic review","volume":"19","author":"Fakhraei","journal-title":"Int J Environ Res Public Health"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Garcia EA . ADASYN: Adaptive Synthetic Sampling approach for imbalanced learning. Presented at: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence); Jun 1-8, 2008; Hong Kong. [doi: 10.1109\/IJCNN.2008.4633969]","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2019.107841","article-title":"Projections of the prevalence of hyperglycaemia in pregnancy in 2019 and beyond: results from the International Diabetes Federation Diabetes Atlas, 9th edition","volume":"157","author":"Yuen","journal-title":"Diabetes Res Clin Pract"},{"key":"R19","unstructured":"Diabetes in pregnancy: management from preconception to the postnatal period. National Institute for Health and Care Excellence. URL: https:\/\/www.nice.org.uk\/guidance\/ng3 [Accessed 17-07-2025]"},{"issue":"9","key":"R20","doi-asserted-by":"publisher","first-page":"2046","DOI":"10.2337\/dc22-0579","article-title":"Comparing IADPSG and NICE diagnostic criteria for GDM in predicting adverse pregnancy outcomes","volume":"45","author":"He","journal-title":"Diabetes Care"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2017.12.003","article-title":"ATLANTIC DIP: despite insulin therapy in women with IADPSG diagnosed GDM, desired pregnancy outcomes are still not achieved. What are we missing?","volume":"136","author":"Bogdanet","journal-title":"Diabetes Res Clin Pract"},{"issue":"Suppl 1","key":"R22","doi-asserted-by":"publisher","first-page":"S282","DOI":"10.2337\/dc24-S015","article-title":"15. Management of diabetes in pregnancy: standards of care in diabetes-2024","volume":"47","author":"American Diabetes Association Professional Practice Committee","journal-title":"Diabetes Care"},{"issue":"1","key":"R23","doi-asserted-by":"publisher","first-page":"75","DOI":"10.2337\/dc15-0433","article-title":"Gestational diabetes mellitus in early pregnancy: evidence for poor pregnancy outcomes despite treatment","volume":"39","author":"Sweeting","journal-title":"Diabetes Care"},{"issue":"7","key":"R24","doi-asserted-by":"publisher","first-page":"e90","DOI":"10.2337\/dc16-0200","article-title":"IADPSG and WHO 2013 gestational diabetes mellitus criteria identify obese women with marked insulin resistance in early pregnancy","volume":"39","author":"Harreiter","journal-title":"Diabetes Care"},{"issue":"6","key":"R25","doi-asserted-by":"publisher","DOI":"10.3390\/medicina59061139","article-title":"Intrauterine growth restriction due to gestational diabetes: from pathophysiology to diagnosis and management","volume":"59","author":"Fasoulakis","journal-title":"Medicina (Kaunas)"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1111\/j.1469-7580.2008.01035.x","article-title":"Insulin and the IGF system in the human placenta of normal and diabetic pregnancies","volume":"215","author":"Hiden","journal-title":"J Anat"},{"issue":"4","key":"R27","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1067\/mob.2002.122851","article-title":"A comparison of amniotic fluid fetal pulmonary phospholipids in normal and diabetic pregnancy","volume":"186","author":"Moore","journal-title":"Am J Obstet Gynecol"},{"issue":"6","key":"R28","doi-asserted-by":"publisher","first-page":"e1545","DOI":"10.1542\/peds.2009-2257","article-title":"Hyperglycemia and adverse pregnancy outcome study: neonatal glycemia","volume":"126","author":"Metzger","journal-title":"Pediatrics"},{"issue":"7","key":"R29","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1001\/jamapediatrics.2020.0632","article-title":"Guidelines for management of neonatal hypoglycemia: are they actually applicable?","volume":"174","author":"Dani","journal-title":"JAMA Pediatr"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.l2381","article-title":"Pre-eclampsia: pathophysiology and clinical implications","volume":"366","author":"Burton","journal-title":"BMJ"},{"issue":"12","key":"R31","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1038\/s41574-022-00734-y","article-title":"A global view of hypertensive disorders and diabetes mellitus during pregnancy","volume":"18","author":"Jiang","journal-title":"Nat Rev Endocrinol"},{"issue":"10","key":"R32","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.117.008337","article-title":"Association between gestational hypertension and risk of cardiovascular disease among 617 589 Norwegian women","volume":"7","author":"Riise","journal-title":"J Am Heart Assoc"},{"issue":"9","key":"R33","doi-asserted-by":"publisher","DOI":"10.1007\/s11906-020-01082-w","article-title":"Prevention, diagnosis, and management of hypertensive disorders of pregnancy: a comparison of international guidelines","volume":"22","author":"Sinkey","journal-title":"Curr Hypertens Rep"},{"issue":"2","key":"R34","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s11883-012-0227-2","article-title":"Diabetes and hypertension: is there a common metabolic pathway?","volume":"14","author":"Cheung","journal-title":"Curr Atheroscler Rep"},{"issue":"2","key":"R35","doi-asserted-by":"publisher","first-page":"165354","DOI":"10.1016\/j.bbadis.2018.12.005","article-title":"Oxidative stress: normal pregnancy versus preeclampsia","volume":"1866","author":"Chiarello","journal-title":"Biochim Biophys Acta Mol Basis Dis"},{"issue":"6","key":"R36","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1111\/j.1447-0756.2010.01303.x","article-title":"Role of oxidative stress markers and antioxidants in the placenta of preeclamptic patients","volume":"36","author":"Rani","journal-title":"J Obstet Gynaecol Res"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5581570","article-title":"The role of oxidative stress in hypertensive disorders of pregnancy (preeclampsia, gestational hypertension) and metabolic disorder of pregnancy (gestational diabetes mellitus)","volume":"2021","author":"Phoswa","journal-title":"Oxid Med Cell Longev"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2020.602477","article-title":"Genetics and epigenetics: new insight on gestational diabetes mellitus","volume":"11","author":"Dalfr\u00e0","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"2","key":"R39","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.metabol.2013.10.001","article-title":"Effect of pre-existing maternal obesity, gestational diabetes and adipokines on the expression of genes involved in lipid metabolism in adipose tissue","volume":"63","author":"Lappas","journal-title":"Metab Clin Exp"},{"issue":"9","key":"R40","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1515\/jpm-2023-0170","article-title":"Advanced maternal age (AMA) and 75\u202fg OGTT glucose levels are pedictors for insulin therapy in women with gestational diabetes (GDM)","volume":"51","author":"Koenigbauer","journal-title":"J Perinat Med"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e71539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:00:59Z","timestamp":1782842459000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e71539"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":40,"URL":"https:\/\/doi.org\/10.2196\/71539","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"article-number":"v13i17e71539"}}