{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T09:24:20Z","timestamp":1787217860430,"version":"build-2736575974"},"reference-count":32,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Artificial intelligence may improve obstetric risk stratification by identifying clinically meaningful patterns that are not captured by single-outcome prediction models. This study evaluated whether unsupervised machine learning applied to first-trimester maternal, biophysical, and biochemical data could identify phenotypes associated with adverse obstetric outcomes. Methods: We analyzed 1583 first-trimester records that were ambispectively collected including maternal characteristics, obstetric history, mean arterial pressure, uterine artery pulsatility index, nuchal translucency, and PAPP-A. Principal component analysis followed by k-means clustering was used to derive AI phenotypes. Associations were tested for hypertensive, metabolic, delivery, neonatal, and actionable obstetric outcomes. Robustness of the clustering solution and phenotype\u2013outcome associations was assessed using inverse probability weighting, false discovery rate correction, adverse-event burden scoring, cross-algorithm agreement analyses, and multiple sensitivity analyses. Results: Four clinically interpretable phenotypes were identified. Phenotype 4 represented a cardiometabolic\u2013vascular subgroup that showed the greatest enrichment for adverse obstetric outcomes. It had higher rates of maternal metabolic or hypertensive complications (52.4%; RR 4.31) and clinically actionable adverse pregnancy outcomes (57.1%; RR 2.31). These associations remained significant after false discovery rate correction and were consistent in inverse probability weighting analyses. Phenotype 4 also had the highest cumulative adverse-event burden score (1.29 versus 0.35\u20130.47). Exploratory analyses demonstrated high specificity (97.2%) but limited sensitivity for clinically actionable adverse pregnancy outcomes. Incremental discrimination over conventional predictors was observed only for selected secondary outcomes, including early preterm birth and low Apgar score. Conclusions: Unsupervised AI phenotyping identified a cardiometabolic\u2013vascular pregnancy subgroup associated with increased obstetric morbidity.<\/jats:p>","DOI":"10.3390\/diagnostics16162654","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:10:20Z","timestamp":1787213420000},"page":"2654","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Machine Learning for the Identification of Latent First-Trimester Obstetric Phenotypes Associated with Maternal and Perinatal Morbidity"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8233-3295","authenticated-orcid":false,"given":"Alexandra-Elena","family":"Cristofor","sequence":"first","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9112-7039","authenticated-orcid":false,"given":"Alexandru","family":"Carauleanu","sequence":"additional","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4718-392X","authenticated-orcid":false,"given":"Ingrid-Andrada","family":"Vasilache","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Biological Sciences, \u2018\u0218tefan cel Mare\u2019 University, 720229 Suceava, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8200-6969","authenticated-orcid":false,"given":"Iustina","family":"Condriuc","sequence":"additional","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioana","family":"Rosu","sequence":"additional","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolina","family":"Susanu","sequence":"additional","affiliation":[{"name":"Faculty of Medicine and Pharmacy, \u201cDun\u0103rea de Jos\u201d University, 47 Domneasc\u0103 Street, 800008 Galati, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2345-1077","authenticated-orcid":false,"given":"Dragos","family":"Nemescu","sequence":"additional","affiliation":[{"name":"Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"C646","DOI":"10.1152\/ajpcell.00293.2024","article-title":"Implications of pregnancy on cardiometabolic disease risk: Preeclampsia and gestational diabetes","volume":"327","author":"Elgazzaz","year":"2024","journal-title":"Am. J. Physiol. Cell Physiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"102804","DOI":"10.1016\/j.jacadv.2026.102804","article-title":"Cardiometabolic Health in Pregnancy: Prevention, Management, and Long-Term Implications","volume":"5","author":"Harrington","year":"2026","journal-title":"JACC Adv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"S1071","DOI":"10.1016\/j.ajog.2020.07.020","article-title":"First trimester preeclampsia screening and prediction","volume":"226","author":"Chaemsaithong","year":"2020","journal-title":"Am. J. Obstet. Gynecol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1002\/uog.18900","article-title":"First-trimester screening for pre-eclampsia: Time to act","volume":"50","author":"Nicolaides","year":"2017","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_5","first-page":"103.e101","article-title":"Competing risks model in screening for preeclampsia by maternal factors and biomarkers at 11\u201313 weeks gestation","volume":"214","author":"Wright","year":"2016","journal-title":"Am. J. Obstet. Gynecol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1159\/000341264","article-title":"Competing Risks Model in Early Screening for Preeclampsia by Biophysical and Biochemical Markers","volume":"33","author":"Akolekar","year":"2012","journal-title":"Fetal Diagn. Ther."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1161\/HYPERTENSIONAHA.123.22584","article-title":"Prospective Validation of First-Trimester Screening for Preterm Preeclampsia in Nulliparous Women (PREDICTION Study)","volume":"81","author":"Guerby","year":"2024","journal-title":"Hypertension"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1002\/uog.27622","article-title":"Comparison of different methods of first-trimester screening for preterm pre-eclampsia: Cohort study","volume":"64","author":"Matallana","year":"2024","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1111\/1471-0528.17983","article-title":"First-Trimester Prediction Models Based on Maternal Characteristics for Adverse Pregnancy Outcomes: A Systematic Review and Meta-Analysis","volume":"132","author":"Becking","year":"2025","journal-title":"BJOG"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Thong, E.P., Ghelani, D.P., Manoleehakul, P., Yesmin, A., Slater, K., Taylor, R., Collins, C., Hutchesson, M., Lim, S.S., and Teede, H.J. (2022). Optimising Cardiometabolic Risk Factors in Pregnancy: A Review of Risk Prediction Models Targeting Gestational Diabetes and Hypertensive Disorders. J. Cardiovasc. Dev. Dis., 9.","DOI":"10.3390\/jcdd9020055"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1002\/dmrr.2803","article-title":"Clustering of metabolic risk factors and adverse pregnancy outcomes: A prospective cohort study","volume":"32","author":"Lei","year":"2016","journal-title":"Diabetes\/Metab. Res. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"04333","DOI":"10.7189\/jogh.15.04333","article-title":"Pre-pregnancy and gestational cardiometabolic disorders and risk of preterm birth and infant mortality","volume":"15","author":"Cheng","year":"2025","journal-title":"J. Glob. Health"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Torres-Torres, J., Espino-Y-Sosa, S., Mart\u00ednez-Portilla, R., Borboa-Olivares, H., Estrada-Gutierrez, G., Acevedo-Gallegos, S., Ruiz-Ramirez, E., Velasco-Espin, M., Cerda-Flores, P., and Ramirez-Gonzalez, A. (2024). A Narrative Review on the Pathophysiology of Preeclampsia. Int. J. Mol. Sci., 25.","DOI":"10.3390\/ijms25147569"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"La Fauci, L., D\u2019Anna, R., Gulino, F., Barracato, C., Zangla, E., Nibali, C., Di Benedetto, A., and Corrado, F. (2026). Clinical and Metabolic Predictors of Hypertensive Disorders in Pregnancies Complicated by Gestational Diabetes Mellitus: A Retrospective Cohort Study. J. Clin. Med., 15.","DOI":"10.3390\/jcm15103835"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.jfma.2023.11.013","article-title":"Advanced maternal age-related clustering of metabolic abnormalities is associated with risks of adverse pregnancy outcomes","volume":"123","author":"Yen","year":"2024","journal-title":"J. Formos. Med. Assoc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e156","DOI":"10.1093\/eurjpc\/zwab121","article-title":"Association of pre-pregnancy cardiovascular risk factor burden with adverse maternal and offspring outcomes","volume":"29","author":"Wang","year":"2022","journal-title":"Eur. J. Prev. Cardiol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e018494","DOI":"10.1161\/JAHA.120.018494","article-title":"Impact of Chronic Hypertension and Antihypertensive Treatment on Adverse Perinatal Outcomes: Systematic Review and Meta-Analysis","volume":"10","author":"Barrett","year":"2021","journal-title":"J. Am. Heart Assoc."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Melinte-Popescu, A.S., Vasilache, I.A., Socolov, D., and Melinte-Popescu, M. (2023). Predictive Performance of Machine Learning-Based Methods for the Prediction of Preeclampsia-A Prospective Study. J. Clin. Med., 12.","DOI":"10.3390\/jcm12020418"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Vasilache, I.A., Scripcariu, I.S., Doroftei, B., Bernad, R.L., C\u0103r\u0103uleanu, A., Socolov, D., Melinte-Popescu, A.S., Vicoveanu, P., Harabor, V., and Mihalceanu, E. (2024). Prediction of Intrauterine Growth Restriction and Preeclampsia Using Machine Learning-Based Algorithms: A Prospective Study. Diagnostics, 14.","DOI":"10.3390\/diagnostics14040453"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1016\/j.molmed.2021.01.007","article-title":"Data-driven modeling of pregnancy-related complications","volume":"27","author":"Espinosa","year":"2021","journal-title":"Trends Mol. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1111\/1471-0528.70262","article-title":"Phenotyping Preeclampsia Using Unsupervised Machine Learning: A Prospective Cohort Study","volume":"133","author":"Houri","year":"2026","journal-title":"BJOG"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"A4368020","DOI":"10.1161\/circ.152.suppl_3.4368020","article-title":"Abstract 4368020: Derivation and Validation of a Machine Learning Approach for Preeclampsia Phenotyping","volume":"152","author":"Huang","year":"2025","journal-title":"Circulation"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zu, Y., Lu, X., Wang, Y., Zheng, J., Xu, X., and Yan, J. (2025). Organ-system-based subclassification of preeclampsia using machine learning predicts pregnancy outcomes. BMC Pregnancy Childbirth, 25.","DOI":"10.1186\/s12884-025-07892-7"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Ngo, A.L., Liao, L.D., Harvill, R., Marafino, B.J., Chehab, R.F., Greenberg, M.B., and Ferrara, A. (2026). Data-Driven Phenotypic Clusters of Gestational Diabetes Mellitus and Associations with Risk of Perinatal Complications and Postpartum Diabetes. Diabetes Care, dc252131.","DOI":"10.2337\/figshare.31244731"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1111\/ppe.12938","article-title":"Machine learning-based placental clusters and their associations with adverse pregnancy outcomes","volume":"37","author":"Petersen","year":"2023","journal-title":"Paediatr. Perinat. Epidemiol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"bbaa369","DOI":"10.1093\/bib\/bbaa369","article-title":"Towards deep phenotyping pregnancy: A systematic review on artificial intelligence and machine learning methods to improve pregnancy outcomes","volume":"22","author":"Davidson","year":"2021","journal-title":"Brief. Bioinform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2633494120986544","DOI":"10.1177\/2633494120986544","article-title":"A review of maternal overweight and obesity and its impact on cardiometabolic outcomes during pregnancy and postpartum","volume":"15","author":"Grieger","year":"2021","journal-title":"Ther. Adv. Reprod. Health"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1089\/jwh.2024.0927","article-title":"A Latent Class Analysis of Pre-Pregnancy Multimorbidity Patterns in a Delivery Cohort at a Safety-Net Hospital","volume":"34","author":"Garcia","year":"2025","journal-title":"J. Women\u2019s Health"},{"key":"ref_29","first-page":"1472","article-title":"First-Trimester Machine Learning to Predict Preeclampsia in Normotensive Pregnancies by American Heart Association Guidelines","volume":"43","author":"Horgan","year":"2025","journal-title":"Am. J. Perinatol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1111\/1471-0528.17837","article-title":"Phenotypes of maternal vascular malperfusion placental pathology and adverse pregnancy outcomes: A retrospective cohort study","volume":"131","author":"Zur","year":"2024","journal-title":"BJOG Int. J. Obstet. Gynaecol."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Li, Y., Cao, J., Li, J., Zhu, J., Li, Y.-M., Wang, D.-P., Liu, H., Yang, H.-L., He, Y., and Hu, L. (2022). Screening high-risk population of persistent postpartum hypertension in women with preeclampsia using latent class cluster analysis. BMC Pregnancy Childbirth, 22.","DOI":"10.1186\/s12884-022-05003-4"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"04099","DOI":"10.7189\/jogh.16.04099","article-title":"Pregnancy complications and caesarean section: A latent class analysis","volume":"16","author":"Jiang","year":"2026","journal-title":"J. Glob. Health"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2654\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:34:53Z","timestamp":1787214893000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":32,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16162654"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16162654","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]}}}