{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:47:58Z","timestamp":1778168878169,"version":"3.51.4"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T00:00:00Z","timestamp":1678060800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000865","name":"Bill and Melinda Gates Foundation","doi-asserted-by":"publisher","award":["OPP1141535"],"award-info":[{"award-number":["OPP1141535"]}],"id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000865","name":"Bill and Melinda Gates Foundation","doi-asserted-by":"publisher","award":["OPP1033514"],"award-info":[{"award-number":["OPP1033514"]}],"id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30 AI50410 and D43 TW009340"],"award-info":[{"award-number":["P30 AI50410 and D43 TW009340"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate estimates of gestational age (GA) at birth are important for preterm birth surveillance but can be challenging to obtain in low income countries. Our objective was to develop machine learning models to accurately estimate GA shortly after birth using clinical and metabolomic data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We derived three GA estimation models using ELASTIC NET multivariable linear regression using metabolomic markers from heel-prick blood samples and clinical data from a retrospective cohort of newborns from Ontario, Canada. We conducted internal model validation in an independent cohort of Ontario newborns, and external validation in heel prick and cord blood sample data collected from newborns from prospective birth cohorts in Lusaka, Zambia and Matlab, Bangladesh. Model performance was measured by comparing model-derived estimates of GA to reference estimates from early pregnancy ultrasound.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Samples were collected from 311 newborns from Zambia and 1176 from Bangladesh. The best-performing model accurately estimated GA within about 6 days of ultrasound estimates in both cohorts when applied to heel prick data (MAE 0.79 weeks (95% CI 0.69, 0.90) for Zambia; 0.81 weeks (0.75, 0.86) for Bangladesh), and within about 7 days when applied to cord blood data (1.02 weeks (0.90, 1.15) for Zambia; 0.95 weeks (0.90, 0.99) for Bangladesh).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Algorithms developed in Canada provided accurate estimates of GA when applied to external cohorts from Zambia and Bangladesh. Model performance was superior in heel prick data as compared to cord blood data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0281074","type":"journal-article","created":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T13:28:27Z","timestamp":1678109307000},"page":"e0281074","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3341-9022","authenticated-orcid":true,"given":"Steven","family":"Hawken","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robin","family":"Ducharme","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malia S. Q.","family":"Murphy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brieanne","family":"Olibris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Brianne","family":"Bota","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lindsay A.","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1475-4079","authenticated-orcid":true,"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Little","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beth K.","family":"Potter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kathryn M.","family":"Denize","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Monica","family":"Lamoureux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Henderson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katelyn J.","family":"Rittenhouse","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joan T.","family":"Price","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Humphrey","family":"Mwape","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bellington","family":"Vwalika","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Musonda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8082-4178","authenticated-orcid":true,"given":"Jesmin","family":"Pervin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. K. Azad","family":"Chowdhury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anisur","family":"Rahman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pranesh","family":"Chakraborty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9590-7216","authenticated-orcid":true,"given":"Jeffrey S. A.","family":"Stringer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kumanan","family":"Wilson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2023,3,6]]},"reference":[{"key":"pone.0281074.ref001","article-title":"Global, regional, and national levels and trends in under-5 mortality between 1990 and 2015, with scenario-based projections to 2030: A systematic analysis by the un Inter-Agency Group for Child Mortality Estimation","author":"D You","year":"2015","journal-title":"The Lancet"},{"key":"pone.0281074.ref002","article-title":"Determinants and consequences of discrepancies in menstrual and ultrasonographic gestational age estimates.","author":"I Morin","year":"2005","journal-title":"BJOG Int J Obstet Gynaecol."},{"key":"pone.0281074.ref003","article-title":"Determining gestational age in a low-resource setting: Validity of last menstrual period.","author":"RE Rosenberg","year":"2009","journal-title":"J Health Popul Nutr."},{"key":"pone.0281074.ref004","doi-asserted-by":"crossref","first-page":"3415","DOI":"10.1016\/S2214-109X(19)30060-9","article-title":"Reducing the global burden of preterm births","volume":"7","author":"B Vwalika","year":"2019","journal-title":"Lancet Glob Health"},{"key":"pone.0281074.ref005","article-title":"Validity of postnatal assessments of gestational age: A comparison of the method of Ballard et al.","author":"GR Alexander","year":"1992","journal-title":"and early ultrasonography. Am J Obstet Gynecol"},{"key":"pone.0281074.ref006","article-title":"Inaccuracy of Dubowitz gestational age in low birth weight infants 8072.","author":"JA Spinnato","year":"1984","journal-title":"ObstetGynecol."},{"key":"pone.0281074.ref007","doi-asserted-by":"crossref","first-page":"Fa103","DOI":"10.1136\/adc.2010.189761.48","article-title":"The external ballard examination does notassess gestational age accurately in a ruralfield setting in the Gambiara","volume":"95","author":"M Taylor","year":"2010","journal-title":"Arch Dis Child Fetal Neonatal Ed"},{"key":"pone.0281074.ref008","article-title":"How intravenous immunoglobulin is used in clinical practice: Audits of two Sydney teaching hospitals","author":"E W Lin M","year":"2007","journal-title":"Internal medicine journal"},{"key":"pone.0281074.ref009","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0198919","article-title":"Improving preterm newborn identification in low-resource settings with machine learning.","volume":"14","author":"KJ Rittenhouse","year":"2019","journal-title":"PLoS ONE."},{"key":"pone.0281074.ref010","article-title":"Born Too Soon: The Global Action Report on Preterm Birth.","author":"PMNCH March of Dimes","year":"2012","journal-title":"Geneva, Switzerland"},{"key":"pone.0281074.ref011","volume-title":"Every Newborn Action Plan","author":"World Health Organisation (WHO)","year":"2014"},{"key":"pone.0281074.ref012","article-title":"Metabolomics of prematurity: Analysis of patterns of amino acids, enzymes, and endocrine markers by categories of gestational age","author":"K Wilson","year":"2014","journal-title":"Pediatr Res"},{"key":"pone.0281074.ref013","article-title":"Postnatal Prediction of Gestational Age Using Newborn Fetal Hemoglobin Levels.","author":"K Wilson","year":"2017","journal-title":"EBioMedicine"},{"key":"pone.0281074.ref014","article-title":"Accurate prediction of gestational age using newborn screening analyte data.","author":"K Wilson","year":"2016","journal-title":"Am J Obstet Gynecol."},{"key":"pone.0281074.ref015","doi-asserted-by":"crossref","first-page":"515.e1","DOI":"10.1016\/j.ajog.2015.11.028","article-title":"Predicting gestational age using neonatal metabolic markers.","volume":"214","author":"KK Ryckman","year":"2016","journal-title":"Am J Obstet Gynecol"},{"key":"pone.0281074.ref016","doi-asserted-by":"crossref","first-page":"511.e1","DOI":"10.1016\/j.ajog.2015.11.029","article-title":"Gestational dating by metabolic profile at birth: A California cohort study.","volume":"214","author":"LL Jelliffe-Pawlowski","year":"2016","journal-title":"Am J Obstet Gynecol"},{"key":"pone.0281074.ref017","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.ebiom.2016.11.032","article-title":"Postnatal Prediction of Gestational Age Using Newborn Fetal Hemoglobin Levels.","volume":"15","author":"K Wilson","year":"2017","journal-title":"EBioMedicine"},{"key":"pone.0281074.ref018","doi-asserted-by":"crossref","first-page":"e015615","DOI":"10.1136\/bmjopen-2016-015615","article-title":"Performance of a postnatal metabolic gestational age algorithm: a retrospective validation study among ethnic subgroups in Canada.","volume":"7","author":"S Hawken","year":"2017","journal-title":"BMJ Open"},{"key":"pone.0281074.ref019","article-title":"External validation of postnatal gestational age estimation using newborn metabolic profiles in Matlab, Bangladesh.","author":"MS Murphy","year":"2019","journal-title":"eLife"},{"key":"pone.0281074.ref020","article-title":"Regularization and variable selection via the elastic net.","author":"H Zou","year":"2005","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"key":"pone.0281074.ref021","article-title":"External validation of postnatal gestational age estimation using newborn metabolic profiles in matlab, Bangladesh.","volume":"8","author":"MSQ Murphy","year":"2019","journal-title":"eLife"},{"key":"pone.0281074.ref022","doi-asserted-by":"crossref","first-page":"25","DOI":"10.12688\/gatesopenres.12820.1","article-title":"The Zambian Preterm Birth Prevention Study (ZAPPS): Cohort characteristics at enrollment.","volume":"2","author":"MC Castillo","year":"2018","journal-title":"Gates Open Res."},{"key":"pone.0281074.ref023","article-title":"Incidental screen positive findings in a prospective cohort study in Matlab, Bangladesh: Insights into expanded newborn screening for low-resource settings.","author":"MSQ Murphy","year":"2019","journal-title":"Orphanet J Rare Dis."},{"key":"pone.0281074.ref024","doi-asserted-by":"crossref","first-page":"e000365","DOI":"10.1136\/bmjgh-2017-000365","article-title":"Postnatal gestational age estimation using newborn screening blood spots: a proposed validation protocol","volume":"2","author":"MSQ Murphy","year":"2017","journal-title":"BMJ Glob Health"},{"key":"pone.0281074.ref025","first-page":"844","article-title":"INTERGROWTH-21st very preterm size at birth reference charts","author":"J Villar","year":"2016","journal-title":"The Lancet. Lancet Publishing Group"},{"key":"pone.0281074.ref026","article-title":"External validation of postnatal gestational age estimation using newborn metabolic profiles in Matlab, Bangladesh.","author":"MS Murphy","year":"2019","journal-title":"eLife."},{"key":"pone.0281074.ref027","first-page":"115","article-title":"Validity of postnatal assessments of gestational age in low birthweight infants from a Caribbean community 8071.","volume":"12","author":"PY Robillard","year":"1992","journal-title":"JPerinatol."},{"key":"pone.0281074.ref028","article-title":"Access to pathology and laboratory medicine services: a crucial gap","author":"ML Wilson","year":"2018","journal-title":"The Lancet"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0281074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T13:28:55Z","timestamp":1678109335000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0281074"}},"subtitle":[],"editor":[{"given":"Iman","family":"Al-Saleh","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,3,6]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0281074","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.07.21.20158196","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,6]]}}}