{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T18:17:36Z","timestamp":1783016256170,"version":"3.54.6"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100021914","name":"Grand Challenges in Global Health","doi-asserted-by":"publisher","award":["INV-046249"],"award-info":[{"award-number":["INV-046249"]}],"id":[{"id":"10.13039\/100021914","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Maternal mortality in Tanzania remains a public health crisis, with Hypertensive Disorders of Pregnancy (HDP) causing 34% of direct obstetric deaths. In overburdened government clinics, high patient volumes and limited resources often restrict assessments to single-point blood pressure checks, leading to missed diagnoses. This study investigates the potential of machine learning (ML) to move beyond simple threshold detection toward automated risk stratification, aiming to optimize patient flow and prioritize clinical resources for high-risk individuals. We analyzed 337,027 routine records (2023\u20132024) from Tanzania\u2019s Unified Community System (UCS). Data from multiple visits were aggregated into 187,438 unique client records. HDP was defined by standard clinical thresholds (BP\u2009\u2265\u2009140\/90 mmHg). We trained five ML models on a balanced subset and validated the top performer on an independent dataset of over 120,000 records to evaluate its utility as a triage tool. XGBoost was the best performing model, achieving 90.1% accuracy and an AUC of 0.95. The model maintained 100% sensitivity, successfully stratifying 12,603 clients into the high-risk category, including those potentially overlooked by traditional checks. While precision was 14% (representing 6.3 false positives per true case), this high-sensitivity screening approach ensures no at-risk client is missed, allowing providers to focus intensive assessment time where it is most needed. ML-driven risk stratification can transform congested ANC workflows by identifying high-risk clients before they escalate to critical states. By automating the initial triage, health facilities can improve operational efficiency and ensure limited specialist time is dedicated to the most vulnerable patients. We recommend that the Ministry of Health strengthens digital data integration to support the deployment of these stratification tools within routine primary care.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001468","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T17:21:16Z","timestamp":1783012876000},"page":"e0001468","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning for risk stratification of hypertensive disorders of pregnancy: Enhancing clinical efficiency in low-resource antenatal care in Tanzania"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5694-7648","authenticated-orcid":true,"given":"Isaac","family":"Lyatuu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel P.","family":"Mwanga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusuph","family":"Kulindwa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond","family":"Bandio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alen","family":"Kinyina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ntuli","family":"Kapologwe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phineas","family":"Sospeter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Makuwani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2384-4586","authenticated-orcid":true,"given":"James","family":"Tumaini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omari","family":"Sukari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Augustino","family":"Hellar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"pdig.0001468.ref001","volume-title":"Annual Health Sector Performance Profile","author":"Ministry of Health Tanzania","year":"2025"},{"issue":"4","key":"pdig.0001468.ref002","article-title":"Machine learning-enabled maternal risk assessment for women with pre-eclampsia (the PIERS-ML model): a modelling study","volume":"6","author":"T Montgomery-Csob\u00e1n","year":"2024","journal-title":"Lancet Digit Health"},{"key":"pdig.0001468.ref003","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.preghy.2021.10.006","article-title":"Novelelectronic health records applied for prediction of pre-eclampsia: machine-learning algorithms","volume":"26","author":"Y-X Li","year":"2021","journal-title":"Pregnancy Hypertens"},{"issue":"1","key":"pdig.0001468.ref004","doi-asserted-by":"crossref","first-page":"13406","DOI":"10.1038\/s41598-025-98416-y","article-title":"The construction and validation of a prediction model of hypertensive disease in pregnancy","volume":"15","author":"Y Chen","year":"2025","journal-title":"Sci Rep"},{"key":"pdig.0001468.ref005","first-page":"1","article-title":"Classification of hypertension in pregnancy based on random forest and Xgboost fusion model","author":"X Lan","year":"2019","journal-title":"BIBE 2019 Third Int Conf Biol Inf Biomed Eng"},{"issue":"1","key":"pdig.0001468.ref006","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1186\/s12884-022-04594-2","article-title":"Machine learning to predict pregnancy outcomes: a systematic review, synthesizing framework and future research agenda","volume":"22","author":"MN Islam","year":"2022","journal-title":"BMC Pregnancy Childbirth"},{"issue":"9761","key":"pdig.0001468.ref007","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/S0140-6736(10)61351-7","article-title":"Prediction of adverse maternal outcomes in pre-eclampsia: development and validation of the fullPIERS model","volume":"377","author":"P von Dadelszen","year":"2011","journal-title":"Lancet"},{"issue":"5","key":"pdig.0001468.ref008","article-title":"Assessing the effect of mhealth interventions in improving maternal and neonatal care in low- and middle-income countries: a systematic review","volume":"11","author":"SFV Sondaal","year":"2016","journal-title":"PLoS ONE"},{"key":"pdig.0001468.ref009","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.preghy.2017.11.006","article-title":"Prediction of adverse maternal outcomes from pre-eclampsia and other hypertensive disorders of pregnancy: a systematic review","volume":"11","author":"UV Ukah","year":"2018","journal-title":"Pregnancy Hypertens"},{"key":"pdig.0001468.ref010","doi-asserted-by":"crossref","DOI":"10.3389\/fbioe.2021.780389","article-title":"Using machine learning to predict complications in pregnancy: a systematic review","volume":"9","author":"A Bertini","year":"2022","journal-title":"Front Bioeng Biotechnol"},{"issue":"5","key":"pdig.0001468.ref011","doi-asserted-by":"crossref","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":"L Davidson","year":"2021","journal-title":"Brief Bioinform"},{"key":"pdig.0001468.ref012","article-title":"Comparison of multivariable logistic regression and other machine learning algorithms for prognostic prediction studies in pregnancy care: systematic review and meta-analysis","author":"H Sufriyana","year":"2024"},{"key":"pdig.0001468.ref013","volume-title":"Evaluating the quality of care for severe pregnancy complications: the WHO near-miss approach for maternal health","author":"World Health Organization and others","year":"2011"},{"key":"pdig.0001468.ref014","author":"The United Republic of Tanzania Ministry of Health and Social Welfare"},{"key":"pdig.0001468.ref015","article-title":"Unified Community System empowers health care workers and transforms communities in Tanzania","year":"2023","journal-title":"Digit Sq"},{"issue":"1","key":"pdig.0001468.ref016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s41182-023-00561-5","article-title":"Women in low- and middle-income countries receive antenatal care at health institutions, yet not delivered there: a multilevel analysis of 2016-2021 DHS data","volume":"52","author":"MW Merid","year":"2024","journal-title":"Trop Med Health"},{"key":"pdig.0001468.ref017","article-title":"Association between achieving adequate antenatal care and health-seeking behaviors: a study of Demographic and Health Surveys in 47 low- and middle-income countries","journal-title":"PLOS Med"},{"key":"pdig.0001468.ref018","doi-asserted-by":"crossref","first-page":"1259268","DOI":"10.3389\/fdgth.2023.1259268","article-title":"Electronic medical record systems data use in decision-making and associated factors among health managers at public primary health facilities, Dodoma region: a cross-sectional analytical study","volume":"5","author":"EC Kessy","year":"2024","journal-title":"Front Digit Health"},{"issue":"12","key":"pdig.0001468.ref019","doi-asserted-by":"crossref","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring fairness in machine learning to advance health equity","volume":"169","author":"A Rajkomar","year":"2018","journal-title":"Ann Intern Med"},{"issue":"9","key":"pdig.0001468.ref020","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1038\/s41591-019-0548-6","article-title":"Do no harm: a roadmap for responsible machine learning for health care","volume":"25","author":"J Wiens","year":"2019","journal-title":"Nat Med"},{"key":"pdig.0001468.ref021"},{"key":"pdig.0001468.ref022","volume-title":"Antenatal Care Guidelines","author":"Ministry of health CD","year":"2020"},{"issue":"3","key":"pdig.0001468.ref023","doi-asserted-by":"crossref","first-page":"69","DOI":"10.2307\/3583291","article-title":"Management of hypertension in pregnancy as a quality indicator of antenatal care in rural Tanzania","volume":"7","author":"DP Urassa","year":"2003","journal-title":"Afr J Reprod Health"},{"issue":"3","key":"pdig.0001468.ref024","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"T Saito","year":"2015","journal-title":"PLoS One"},{"key":"pdig.0001468.ref025","first-page":"70","article-title":"The effects of random undersampling with simulated class imbalance for big data","author":"T Hasanin","year":"2018","journal-title":"2018 IEEE Int Conf Inf Reuse Integr IRI"},{"key":"pdig.0001468.ref026","volume-title":"Machine Learning (ML) code for predicting Hypertensive Disorder of Pregnancy using UCS Data - Tanzania","author":"I Lyatuu","year":"2024"},{"issue":"2","key":"pdig.0001468.ref027","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1001382","article-title":"Scaling up mHealth: where is the evidence?","volume":"10","author":"M Tomlinson","year":"2013","journal-title":"PLoS Med"},{"key":"pdig.0001468.ref028","doi-asserted-by":"crossref","first-page":"105833","DOI":"10.1016\/j.ijmedinf.2025.105833","article-title":"Utilization, challenges, and training needs of digital health technologies: perspectives from healthcare professionals","volume":"197","author":"R Khan","year":"2025","journal-title":"Int J Med Inform"},{"issue":"4","key":"pdig.0001468.ref029","doi-asserted-by":"crossref","first-page":"337","DOI":"10.3390\/bioengineering11040337","article-title":"The role of AI in hospitals and clinics: transforming healthcare in the 21st century","volume":"11","author":"S Maleki Varnosfaderani","year":"2024","journal-title":"Bioengineering (Basel)"},{"issue":"13","key":"pdig.0001468.ref030","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big data and machine learning in health care","volume":"319","author":"AL Beam","year":"2018","journal-title":"JAMA"},{"key":"pdig.0001468.ref031","author":"H Chen","year":"2025"},{"issue":"1","key":"pdig.0001468.ref032","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1007\/s10791-026-09973-3","article-title":"Enhanced cardiovascular disease risk prediction using explainable machine learning and data balancing","volume":"29","author":"R Khawla","year":"2026","journal-title":"Discov Comput"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T17:21:25Z","timestamp":1783012885000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001468"}},"subtitle":[],"editor":[{"given":"Anna","family":"Khalemsky","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001468","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]}}}