Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers
Hawken S, Ducharme R, Murphy M, Olibris B, Bota A, Wilson L, Cheng W, Little J, Potter B, Denize K, Lamoureux M, Henderson M, Rittenhouse K, Price J, Mwape H, Vwalika B, Musonda P, Pervin J, Chowdhury A, Rahman A, Chakraborty P, Stringer J, Wilson K. Development and external validation of machine learning algorithms for postnatal gestational age estimation using clinical data and metabolomic markers. PLOS ONE 2023, 18: e0281074. PMID: 36877673, PMCID: PMC9987787, DOI: 10.1371/journal.pone.0281074.Peer-Reviewed Original ResearchConceptsGestational ageCord blood dataClinical dataBlood dataMetabolomic markersEarly pregnancy ultrasoundHeel-prick blood sampleProspective birth cohortMultivariable linear regressionBlood sample dataExternal validationGestational age estimationRetrospective cohortPregnancy ultrasoundHeel prickExternal cohortIndependent cohortBlood samplesBirth cohortNewbornsPostnatal gestational age estimationCohortUltrasound estimatesInternal model validationLow-income countries