{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:09:40Z","timestamp":1782846580287,"version":"3.54.5"},"reference-count":28,"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 The maintenance and progression of pregnancy rely on immune homeostasis at the maternal-fetal interface. However, pregnancy complicated by autoimmune abnormalities can disrupt this balance and significantly increase the risk of adverse pregnancy outcomes (APOs).<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to (1) develop an interpretable predictive tool for APOs in patients with immune abnormalities and (2) interpret the models using Shapley additive explanations (SHAP) values.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study retrospectively analyzed clinical data from 288 patients with autoimmune abnormalities at Yichang Central People\u2019s Hospital between 2019 and 2024. Feature selection was performed using both the Boruta algorithm and Least Absolute Shrinkage and Selection Operator regression to identify optimal predictive factors associated with APOs. Nine machine learning models were developed and subsequently underwent a comprehensive comparative evaluation of their predictive performance, leading to the identification of the optimal predictive model. SHAP values were generated to provide interpretable insights into model predictions.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 288 patients were included in the study, 124 (43.06%) of whom had APOs. The extreme gradient boosting algorithm was shown to be the optimal model after a comparison of 9 different models utilizing various metrics. The SHAP analysis showed that crown-rump length at 6\n +0<\/jats:sup>\n to 8\n +6<\/jats:sup>\n weeks, the number of other drugs, the number of complications during pregnancy, gestational sac volume at 6\n +0<\/jats:sup>\n to 8\n +6<\/jats:sup>\n weeks, and yolk sac diameter change at 6\n +0<\/jats:sup>\n to 8\n +6<\/jats:sup>\n weeks were the key predictive factors affecting APOs.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The study developed an interpretable predictive tool for APOs in patients with immune abnormalities, which may assist clinicians in making early intervention decisions.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/84087","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T13:44:47Z","timestamp":1778679887000},"page":"e84087-e84087","source":"Crossref","is-referenced-by-count":0,"title":["Adverse Pregnancy Outcomes in Women With Immune Abnormalities: Machine Learning Model Development and Validation Using First-Trimester Sonographic Features"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5543-4286","authenticated-orcid":false,"given":"Shijin","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8018-6352","authenticated-orcid":false,"given":"Yan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4305-7700","authenticated-orcid":false,"given":"Qiaoyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2468-439X","authenticated-orcid":false,"given":"Qiao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7672-5139","authenticated-orcid":false,"given":"Qinxin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0373-5098","authenticated-orcid":false,"given":"Chang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2497-8711","authenticated-orcid":false,"given":"Rong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4661-7501","authenticated-orcid":false,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,13]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-024-03309-y","article-title":"Autoimmune diseases and adverse pregnancy outcomes: an umbrella review","volume":"22","author":"Singh","journal-title":"BMC Med"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","first-page":"101226","DOI":"10.1016\/j.ajogmf.2023.101226","article-title":"Patients with autoimmune skin diseases are at increased risk of adverse pregnancy outcomes","volume":"6","author":"Keum","journal-title":"Am J Obstet Gynecol MFM"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","first-page":"34","DOI":"10.23736\/S2724-606X.24.05549-0","article-title":"Immune biomarkers in cases of recurrent pregnancy loss and recurrent implantation failure","volume":"77","author":"Cavalcante","journal-title":"Minerva Obstet Gynecol"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1097\/AOG.0000000000005729","article-title":"Association between novel antiphospholipid antibodies and adverse pregnancy outcomes","volume":"145","author":"Moyle","journal-title":"Obstet Gynecol"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s12016-019-08762-9","article-title":"Prediction of adverse pregnancy outcomes in women with systemic lupus erythematosus","volume":"59","author":"Palma Dos Reis","journal-title":"Clin Rev Allergy Immunol"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"47","DOI":"10.5935\/1518-0557.20230052","article-title":"Correlation between diameter of yolk sac on transvaginal ultrasonography at 6-12 weeks of gestation and adverse pregnancy outcomes","volume":"28","author":"Gad","journal-title":"JBRA Assist Reprod"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.21037\/atm-20-3623","article-title":"Endometrial cavity fluid is associated with deleterious pregnancy outcomes in patients undergoing fertilization\/intracytoplasmic sperm injection: a retrospective cohort study","volume":"9","author":"Zhang","journal-title":"Ann Transl Med"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.1186\/s12887-022-03426-8","article-title":"Correlation between crown-rump length in the first trimester of pregnancy and neonatal outcomes","volume":"22","author":"Xu","journal-title":"BMC Pediatr"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2021.104484","article-title":"Comparison of machine learning and logistic regression models in predicting acute kidney injury: a systematic review and meta-analysis","volume":"151","author":"Song","journal-title":"Int J Med Inform"},{"issue":"5","key":"R10","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1002\/jcsm.13282","article-title":"Explainable machine learning model for predicting skeletal muscle loss during surgery and adjuvant chemotherapy in ovarian cancer","volume":"14","author":"Hsu","journal-title":"J Cachexia Sarcopenia Muscle"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","journal-title":"Crit Care"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1016\/j.redox.2024.103470","article-title":"Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants","volume":"79","author":"Qi","journal-title":"Redox Biol"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.15965","article-title":"Risk factors for adverse pregnancy outcomes in Chinese women: a meta-analysis","volume":"11","author":"Huang","journal-title":"PeerJ"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02752-4","article-title":"Machine learning-based predictive model for post-stroke dementia","volume":"24","author":"Wei","journal-title":"BMC Med Inform Decis Mak"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.981059","article-title":"Prediction of lymph node metastasis in patients with breast invasive micropapillary carcinoma based on machine learning and SHapley Additive exPlanations framework","volume":"12","author":"Jiang","journal-title":"Front Oncol"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1136\/lupus-2022-000769","article-title":"Adverse pregnancy outcomes in women with systemic lupus erythematosus: can we improve predictions with machine learning?","volume":"9","author":"Fazzari","journal-title":"Lupus Sci Med"},{"issue":"11","key":"R17","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1002\/acr.24265","article-title":"Preeclampsia risk prediction model for Chinese pregnant patients with systemic lupus erythematosus","volume":"72","author":"Jiang","journal-title":"Arthritis Care Res (Hoboken)"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-11837-7","article-title":"Prediction of birthweight with early and mid-pregnancy antenatal markers utilising machine learning and explainable artificial intelligence","volume":"15","author":"Pavanya","journal-title":"Sci Rep"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1049\/htl2.70014","article-title":"A model of the first trimester evaluation of foetal movements and their outcomes via explainable artificial intelligence: a multicentric study","volume":"12","author":"Pavanya","journal-title":"Healthc Technol Lett"},{"issue":"11","key":"R20","doi-asserted-by":"publisher","first-page":"2434","DOI":"10.1093\/humrep\/deae212","article-title":"Embryonic size and growth and adverse birth outcomes: the Rotterdam Periconception Cohort","volume":"39","author":"Roelants","journal-title":"Hum Reprod"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.2196\/60887","article-title":"Automatic human embryo volume measurement in first trimester ultrasound from the Rotterdam Periconception Cohort: quantitative and qualitative evaluation of artificial intelligence","volume":"27","author":"Bastiaansen","journal-title":"J Med Internet Res"},{"issue":"10","key":"R22","doi-asserted-by":"publisher","first-page":"1777","DOI":"10.7863\/ultra.15.14.09012","article-title":"Sonographic parameters for prediction of miscarriage: role of 3-dimensional volume measurement","volume":"34","author":"Wie","journal-title":"J Ultrasound Med"},{"issue":"5","key":"R23","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1002\/jum.15810","article-title":"Prediction of adverse pregnancy outcomes using crown-rump length at 11 to 13\u2009+\u20096\u2009weeks of gestation","volume":"41","author":"Kwak","journal-title":"J Ultrasound Med"},{"issue":"9","key":"R24","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.28781","article-title":"A prospective study on correlation of first trimester crown-rump length with birth weight","volume":"14","author":"Patel","journal-title":"Cureus"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.jogoh.2018.10.016","article-title":"Yolk sac size & shape as predictors of first trimester pregnancy outcome: a prospective observational study","volume":"48","author":"Suguna","journal-title":"J Gynecol Obstet Hum Reprod"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"15","DOI":"10.11152\/mu.2014.2066.161.st1gt2","article-title":"Abnormal sonographic appearances of the yolk sac: which can be associated with adverse perinatal outcome?","volume":"16","author":"Tan","journal-title":"Med Ultrason"},{"issue":"4","key":"R27","doi-asserted-by":"publisher","first-page":"547","DOI":"10.12865\/CHSJ.47.04.10","article-title":"Can ultrasound analysis of the yolk sac be a predictor of pregnancy outcome?","volume":"47","author":"Marin","journal-title":"Curr Health Sci J"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","first-page":"2305675","DOI":"10.1080\/14767058.2024.2305675","article-title":"Co-existing chronic hypertension and hypertensive disorders of pregnancy and associated adverse pregnancy outcomes","volume":"37","author":"Sweeney","journal-title":"J Matern Fetal Neonatal Med"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e84087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:18:14Z","timestamp":1782843494000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e84087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,13]]},"references-count":28,"URL":"https:\/\/doi.org\/10.2196\/84087","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,13]]},"article-number":"v14i1e84087"}}