{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T21:59:04Z","timestamp":1791669544238,"version":"4.3.4"},"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T00:00:00Z","timestamp":1738627200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008078","name":"University of Strathclyde","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008078","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000031","name":"Institute of Human Development, Child and Youth Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000031","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009053","name":"Bill and Melinda Gates Institute for Population and Reproductive Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosmedicine.org"],"crossmark-restriction":false},"short-container-title":["PLoS Med"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Preeclampsia is a potentially life-threatening pregnancy complication. Among women whose pregnancies are complicated by preeclampsia, the Preeclampsia Integrated Estimate of RiSk (PIERS) models (i.e., the PIERS Machine Learning [PIERS-ML] model, and the logistic regression-based fullPIERS model) accurately identify individuals at greatest or least risk of adverse maternal outcomes within 48 h following admission. Both models were developed and validated to be used as part of initial assessment. In the United Kingdom, the National Institute for Health and Care Excellence (NICE) recommends repeated use of such static models for ongoing assessment beyond the first 48 h. This study evaluated the models\u2019 performance during such consecutive prediction.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods and findings<\/jats:title>\n<jats:p>This multicountry prospective study used data of 8,843 women (32% white, 30% black, and 26% Asian) with a median age of 31 years. These women, admitted to maternity units in the Americas, sub-Saharan Africa, South Asia, Europe, and Oceania, were diagnosed with preeclampsia at a median gestational age of 35.79 weeks between year 2003 and 2016. The risk differentiation performance of the PIERS-ML and fullPIERS models were assessed for each day within a 2-week post-admission window. The PIERS adverse maternal outcome includes one or more of: death, end-organ complication (cardiorespiratory, renal, hepatic, etc.), or uteroplacental dysfunction (e.g., placental abruption). The main outcome measures were: trajectories of mean risk of each of the uncomplicated course and adverse outcome groups; daily area under the precision-recall curve (AUC-PRC); potential clinical impact (i.e., net benefit in decision curve analysis); dynamic shifts of multiple risk groups; and daily likelihood ratios. In the 2 weeks window, the number of daily outcome events decreased from over 200 to around 10. For both PIERS-ML and fullPIERS models, we observed consistently higher mean risk in the adverse outcome (versus uncomplicated course) group. The AUC-PRC values (0.2\u20130.4) of the fullPIERS model remained low (i.e., close to the daily fraction of adverse outcomes, indicating low discriminative capacity). The PIERS-ML model\u2019s AUC-PRC peaked on day 0 (0.65), and notably decreased thereafter. When categorizing women into multiple risk groups, the PIERS-ML model generally showed good rule-in capacity for the \u201cvery high\u201d risk group, with positive likelihood ratio values ranging from 70.99 to infinity, and good rule-out capacity for the \u201cvery low\u201d risk group where most negative likelihood ratio values were 0. However, performance declined notably for other risk groups beyond 48 h. Decision curve analysis revealed a diminishing advantage for treatment guided by both models over time. The main limitation of this study is that the baseline performance of the PIERS-ML model was assessed on its development data; however, its baseline performance has also undergone external evaluation.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>In this study, we have evaluated the performance of the fullPIERS and PIERS-ML models for consecutive prediction. We observed deteriorating performance of both models over time. We recommend using the models for consecutive prediction with greater caution and interpreting predictions with increasing uncertainty as the pregnancy progresses. For clinical practice, models should be adapted to retain accuracy when deployed serially. The performance of future models can be compared with the results of this study to quantify their added value.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pmed.1004509","type":"journal-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T18:25:24Z","timestamp":1738693524000},"page":"e1004509","update-policy":"https:\/\/doi.org\/10.1371\/journal.pmed.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Consecutive prediction of adverse maternal outcomes of preeclampsia, using the PIERS-ML and fullPIERS models: A multicountry prospective observational study"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1976-9683","authenticated-orcid":true,"given":"Guiyou","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T\u00fcnde","family":"Montgomery-Csob\u00e1n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7243-2115","authenticated-orcid":true,"given":"Wessel","family":"Ganzevoort","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanne J.","family":"Gordijn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kimberley","family":"Kavanagh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Murray","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1355-610X","authenticated-orcid":true,"given":"Laura A.","family":"Magee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6629-318X","authenticated-orcid":true,"given":"Henk","family":"Groen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4136-3070","authenticated-orcid":true,"given":"Peter","family":"von Dadelszen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,2,4]]},"reference":[{"issue":"19","key":"pmed.1004509.ref001","doi-asserted-by":"crossref","first-page":"1817","DOI":"10.1056\/NEJMra2109523","article-title":"Preeclampsia","volume":"386","author":"LA Magee","year":"2022","journal-title":"N Engl J Med"},{"issue":"18","key":"pmed.1004509.ref002","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1016\/j.jacc.2020.03.028","article-title":"Incidence and Long-Term Outcomes of Hypertensive Disorders of Pregnancy","volume":"75","author":"VD Garovic","year":"2020","journal-title":"J Am Coll Cardiol"},{"issue":"8","key":"pmed.1004509.ref003","doi-asserted-by":"crossref","first-page":"e0221202","DOI":"10.1371\/journal.pone.0221202","article-title":"Prediction model development of late-onset preeclampsia using machine learning-based methods","volume":"14","author":"JH Jhee","year":"2019","journal-title":"PLoS ONE"},{"issue":"1","key":"pmed.1004509.ref004","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1186\/s12916-017-0827-3","article-title":"Prediction of complications in early-onset pre-eclampsia (PREP): development and external multinational validation of prognostic models","volume":"15","author":"S Thangaratinam","year":"2017","journal-title":"BMC Med"},{"issue":"9761","key":"pmed.1004509.ref005","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":"3","key":"pmed.1004509.ref006","first-page":"Cd004454","article-title":"Antenatal corticosteroids for accelerating fetal lung maturation for women at risk of preterm birth","author":"D Roberts","year":"2006","journal-title":"Cochrane Database Syst Rev"},{"issue":"4","key":"pmed.1004509.ref007","doi-asserted-by":"crossref","first-page":"e238","DOI":"10.1016\/S2589-7500(23)00267-4","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-Csoban","year":"2024","journal-title":"Lancet Digit Health"},{"key":"pmed.1004509.ref008","unstructured":"Hypertension in pregnancy: diagnosis and management. National Institute for Health and Care Excellence: Clinical Guidelines. London: National Institute for Health and Care Excellence (NICE) Copyright NICE 2019; 2019."},{"issue":"1","key":"pmed.1004509.ref009","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1111\/j.1471-0528.2012.03496.x","article-title":"Performance of the fullPIERS model in predicting adverse maternal outcomes in pre-eclampsia using patient data from the PIERS (Pre-eclampsia Integrated Estimate of RiSk) cohort, collected on admission","volume":"120","author":"B Payne","year":"2013","journal-title":"BJOG"},{"issue":"1","key":"pmed.1004509.ref010","doi-asserted-by":"crossref","first-page":"e1001589","DOI":"10.1371\/journal.pmed.1001589","article-title":"A risk prediction model for the assessment and triage of women with hypertensive disorders of pregnancy in low-resourced settings: the miniPIERS (Pre-eclampsia Integrated Estimate of RiSk) multi-country prospective cohort study","volume":"11","author":"BA Payne","year":"2014","journal-title":"PLoS Med"},{"key":"pmed.1004509.ref011","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.preghy.2018.01.004","article-title":"Temporal and external validation of the fullPIERS model for the prediction of adverse maternal outcomes in women with pre-eclampsia","volume":"15","author":"UV Ukah","year":"2019","journal-title":"Pregnancy Hypertens"},{"issue":"4","key":"pmed.1004509.ref012","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1161\/HYPERTENSIONAHA.116.08706","article-title":"External Validation of the fullPIERS Model for Predicting Adverse Maternal Outcomes in Pregnancy Hypertension in Low- and Middle-Income Countries","volume":"69","author":"fullPIERS and miniPIERS Working Groups","year":"2017","journal-title":"Hypertension"},{"key":"pmed.1004509.ref013","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.preghy.2021.09.008","article-title":"The hypertensive disorders of pregnancy: the 2021 International Society for the Study of Hypertension in Pregnancy classification, diagnosis and management recommendations for international practice","volume":"27","author":"LA Magee","year":"2022","journal-title":"Pregnancy Hypertens"},{"issue":"9694","key":"pmed.1004509.ref014","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1016\/S0140-6736(09)60736-4","article-title":"Induction of labour versus expectant monitoring for gestational hypertension or mild pre-eclampsia after 36 weeks\u2019 gestation (HYPITAT): a multicentre, open-label randomised controlled trial","volume":"374","author":"CM Koopmans","year":"2009","journal-title":"Lancet"},{"issue":"24","key":"pmed.1004509.ref015","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1056\/NEJM197306142882405","article-title":"Medical assessment by a Delphi group opinion technic","volume":"288","author":"AV Milholland","year":"1973","journal-title":"N Engl J Med"},{"issue":"12","key":"pmed.1004509.ref016","doi-asserted-by":"crossref","first-page":"1516","DOI":"10.1111\/1471-0528.16319","article-title":"A core outcome set for pre-eclampsia research: an international consensus development study","volume":"127","author":"J Duffy","year":"2020","journal-title":"BJOG"},{"issue":"3","key":"pmed.1004509.ref017","doi-asserted-by":"crossref","first-page":"e0118432","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"},{"issue":"1","key":"pmed.1004509.ref018","doi-asserted-by":"crossref","first-page":"W1","DOI":"10.7326\/M14-0698","article-title":"Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration","volume":"162","author":"KG Moons","year":"2015","journal-title":"Ann Intern Med"},{"issue":"6","key":"pmed.1004509.ref019","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"AJ Vickers","year":"2006","journal-title":"Med Decis Making"},{"key":"pmed.1004509.ref020","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s41512-019-0064-7","article-title":"A simple, step-by-step guide to interpreting decision curve analysis","volume":"3","author":"AJ Vickers","year":"2019","journal-title":"Diagn Progn Res"},{"issue":"6","key":"pmed.1004509.ref021","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1016\/j.eururo.2018.08.038","article-title":"Reporting and Interpreting Decision Curve Analysis: A Guide for Investigators","volume":"74","author":"B Van Calster","year":"2018","journal-title":"Eur Urol"},{"key":"pmed.1004509.ref022","unstructured":"Sankey diagram [updated 2023 Jul 11] [cited 2024 Jan 10]. https:\/\/en.wikipedia.org\/wiki\/Sankey_diagram."},{"key":"pmed.1004509.ref023","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S plus to analyze and compare ROC curves","volume":"12","author":"X Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"issue":"6","key":"pmed.1004509.ref024","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1093\/jamia\/ocx030","article-title":"Calibration drift in regression and machine learning models for acute kidney injury","volume":"24","author":"SE Davis","year":"2017","journal-title":"J Am Med Inform Assoc"},{"key":"pmed.1004509.ref025","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s41512-018-0045-2","article-title":"Dynamic models to predict health outcomes: current status and methodological challenges","volume":"2","author":"DA Jenkins","year":"2018","journal-title":"Diagn Progn Res"},{"key":"pmed.1004509.ref026","article-title":"Performance drift in a mortality prediction algorithm among patients with cancer during the SARS-CoV-2 pandemic","author":"RB Parikh","year":"2022","journal-title":"J Am Med Inform Assoc"},{"issue":"2","key":"pmed.1004509.ref027","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1161\/CIRCOUTCOMES.114.001645","article-title":"Improved Prediction by Dynamic Modeling: An Exploratory Study in the Adult Cardiac Surgery Database of the Netherlands Association for Cardio-Thoracic Surgery","volume":"9","author":"S Siregar","year":"2016","journal-title":"Circ Cardiovasc Qual Outcomes"},{"issue":"1","key":"pmed.1004509.ref028","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1177\/0962280215626466","article-title":"A review of statistical updating methods for clinical prediction models","volume":"27","author":"TL Su","year":"2018","journal-title":"Stat Methods Med Res"},{"issue":"12","key":"pmed.1004509.ref029","doi-asserted-by":"crossref","first-page":"3649","DOI":"10.1177\/0962280218811837","article-title":"Individual dynamic predictions using landmarking and joint modelling: Validation of estimators and robustness assessment","volume":"28","author":"L Ferrer","year":"2019","journal-title":"Stat Methods Med Res"},{"issue":"6","key":"pmed.1004509.ref030","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2021.12426","article-title":"Comparison of Joint and Landmark Modeling for Predicting Cancer Progression in Men With Castration-Resistant Prostate Cancer A Secondary Post Hoc Analysis of the PREVAIL Randomized Clinical Trial","volume":"4","author":"A Finelli","year":"2021","journal-title":"JAMA Netw Open"},{"key":"pmed.1004509.ref031","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s41512-020-00078-z","article-title":"Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods","volume":"4","author":"LM Bull","year":"2020","journal-title":"Diagn Progn Res"},{"issue":"1","key":"pmed.1004509.ref032","article-title":"Improving preeclampsia risk prediction by modeling pregnancy trajectories from routinely collected electronic medical record data","volume":"5","author":"SL Li","year":"2022","journal-title":"NPJ Digit Med"},{"key":"pmed.1004509.ref033","doi-asserted-by":"crossref","DOI":"10.3389\/fsurg.2022.1005974","article-title":"Dynamic risk prediction models for different subtypes of hypertensive disorders in pregnancy","volume":"9","author":"XY Zhang","year":"2022","journal-title":"Front Surg"},{"key":"pmed.1004509.ref034","article-title":"Dynamic gestational week prediction model for pre-eclampsia based on ID3 algorithm","volume":"13","author":"ZW Li","year":"2022","journal-title":"Front Physiol"}],"container-title":["PLOS Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pmed.1004509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T18:25:40Z","timestamp":1738693540000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pmed.1004509"}},"subtitle":[],"editor":[{"given":"Gordon C","family":"Smith","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,2,4]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,2,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pmed.1004509","relation":{},"ISSN":["1549-1676"],"issn-type":[{"value":"1549-1676","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,4]]}}}