A novel systematic pipeline for increased predictability and explainability of growth patterns in children using trajectory features

Página do item simplificado
dc.contributorSistema FMUSP-HC: Faculdade de Medicina da Universidade de São Paulo (FMUSP) e Hospital das Clínicas da FMUSP
dc.contributor.authorMASSARA, Paraskevi
dc.contributor.authorLOPEZ-DOMINGUEZ, Lorena
dc.contributor.authorBOURDON, Celine
dc.contributor.authorBASSANI, Diego G.
dc.contributor.authorKEOWN-STONEMAN, Charles D. G.
dc.contributor.authorBIRKEN, Catherine S.
dc.contributor.authorMAGUIRE, Jonathon L.
dc.contributor.authorSANTOS, Ina S.
dc.contributor.authorMATIJASEVICH, Alicia
dc.contributor.authorBANDSMA, Robert H. J.
dc.contributor.authorCOMELLI, Elena M.
dc.date.accessioned2023-10-30T14:39:34Z
dc.date.available2023-10-30T14:39:34Z
dc.date.issued2023
dc.description.abstractObjective: Longitudinal patterns of growth in early childhood are associated with health conditions throughout life. Knowledge of such patterns and the ability to predict them can lead to better prevention and improved health promotion in adulthood. However, growth analyses are characterized by significant variability, and pattern detection is affected by the method applied. Moreover, pattern labelling is typically performed based on ad hoc methods, such as visualizations or clinical experience. Here, we propose a novel pipeline using features extracted from growth trajectories using mathematical, statistical and machine-learning approaches to predict growth patterns and label them in a systematic and unequivocal manner. Methods: We extracted mathematical and clinical features from 9577 children growth trajectories embedded with machine-learning predictions of the growth patterns. We experimented with two sets of features (CAnonical Time-series Characteristics and trajectory features specific to growth), developmental periods and six machine-learning classifiers. Clinical experts provided labels for the detected patterns and decision rules were created to associate the features with the labelled patterns. The predictive capacity of the extracted features was validated on two heterogenous populations (The Applied Research Group for Kids and the 2004 Pelotas Birth Cohort, based in Canada and Brazil, respectively). Results: Features predictive ability measured by accuracy and F1 score was & GE; 80% and & GE; 0.76 respectively in both cohorts. A small number of features (n = 74) was sufficient to distinguish between growth patterns in both cohorts. Slope, intercept of the trajectory, age at peak value, start value and change of the growth measure were among the top identified features. Conclusion: Growth features can be reliably used as predictors of growth patterns and provide an unbiased understanding of growth patterns. They can be used as tool to reduce the effort to repeat analysis and variability concerning anthropometric measures, time points and analytical methods, in the context of the same or similar populations.eng
dc.description.indexMEDLINE
dc.description.indexPubMed
dc.description.indexWoS
dc.description.indexScopus
dc.description.sponsorshipJoannah and Brian Lawson Center for Child Nutrition
dc.description.sponsorshipFaculty of Medicine
dc.description.sponsorshipUniversity of Toronto
dc.description.sponsorshipLawson Family Chair in Microbiome Nutrition Research
dc.description.sponsorshipCanadian Institutes of Health Research
dc.description.sponsorshipWellcome Trust
dc.description.sponsorshipWHO
dc.description.sponsorshipNational Support Program for Centers of Excellence
dc.description.sponsorshipBrazilian National Research Council (CNPq)
dc.description.sponsorshipBrazilian Ministry of Health
dc.description.sponsorshipChildren's Pastorate
dc.description.sponsorshipCNPq
dc.identifier.citationINTERNATIONAL JOURNAL OF MEDICAL INFORMATICS, v.177, article ID 105143, 9p, 2023
dc.identifier.doi10.1016/j.ijmedinf.2023.105143
dc.identifier.eissn1872-8243
dc.identifier.issn1386-5056
dc.identifier.urihttps://observatorio.fm.usp.br/handle/OPI/56168
dc.language.isoeng
dc.publisherELSEVIER IRELAND LTDeng
dc.relation.ispartofInternational Journal of Medical Informatics
dc.rightsrestrictedAccesseng
dc.rights.holderCopyright ELSEVIER IRELAND LTDeng
dc.subjectGrowth patternseng
dc.subjectChildreneng
dc.subjectExplainabilityeng
dc.subjectPredictioneng
dc.subjectTrajectoryeng
dc.subjectFeatureseng
dc.subject.otherbody-mass indexeng
dc.subject.othercohort profileeng
dc.subject.otherchildhoodeng
dc.subject.otherbirtheng
dc.subject.otherinfancyeng
dc.subject.otherheighteng
dc.subject.otherhealtheng
dc.subject.otherriskeng
dc.subject.wosComputer Science, Information Systemseng
dc.subject.wosHealth Care Sciences & Serviceseng
dc.subject.wosMedical Informaticseng
dc.titleA novel systematic pipeline for increased predictability and explainability of growth patterns in children using trajectory featureseng
dc.typearticleeng
dc.type.categoryoriginal articleeng
dc.type.versionpublishedVersioneng
dspace.entity.typePublication
hcfmusp.affiliation.countryCanadá
hcfmusp.affiliation.countryisoca
hcfmusp.author.externalMASSARA, Paraskevi:Univ Toronto, Fac Med, Dept Nutr Sci, Toronto, ON, Canada; Dept Nutr Sci, 1 Kings Coll Circle, Toronto, ON M5S 1A8, Canada
hcfmusp.author.externalLOPEZ-DOMINGUEZ, Lorena:Univ Toronto, Fac Med, Dept Nutr Sci, Toronto, ON, Canada; Hosp Sick Children, Translat Med Program, Toronto, ON, Canada
hcfmusp.author.externalBOURDON, Celine:Hosp Sick Children, Translat Med Program, Toronto, ON, Canada
hcfmusp.author.externalBASSANI, Diego G.:Univ Toronto, Dalla Lana Sch Publ Hlth, Toronto, ON, Canada; Hosp Sick Children, Ctr Global Child Hlth & Child Hlth Evaluat Sci, Toronto, ON, Canada
hcfmusp.author.externalKEOWN-STONEMAN, Charles D. G.:Univ Toronto, Dalla Lana Sch Publ Hlth, Toronto, ON, Canada; St Michaels Hosp, Li Ka Shing Knowledge Inst, Appl Hlth Res Ctr, Toronto, ON, Canada
hcfmusp.author.externalBIRKEN, Catherine S.:Univ Toronto, Fac Med, Dept Pediat, Toronto, ON, Canada; Hosp Sick Children, Child Hlth Evaluat Sci, Toronto, ON, Canada
hcfmusp.author.externalMAGUIRE, Jonathon L.:Univ Toronto, Fac Med, Dept Nutr Sci, Toronto, ON, Canada; Unity Hlth Toronto, Li Ka Shing Knowledge Inst, Toronto, ON, Canada; Hosp Sick Children, Pediat Outcomes Res Team, Toronto, ON, Canada
hcfmusp.author.externalSANTOS, Ina S.:Univ Fed Pelotas, Postgrad Program Epidemiol, Pelotas, Brazil
hcfmusp.author.externalBANDSMA, Robert H. J.:Hosp Sick Children, Translat Med Program, Toronto, ON, Canada; Hosp Sick Children, Div Gastroenterol Hepatol & Nutr, Toronto, ON, Canada; Dept Nutr Sci, 1 Kings Coll Circle, Toronto, ON M5S 1A8, Canada
hcfmusp.author.externalCOMELLI, Elena M.:Univ Toronto, Fac Med, Dept Nutr Sci, Toronto, ON, Canada; Univ Toronto, Joannah & Brian Lawson Ctr Child Nutr, Toronto, ON, Canada; Dept Nutr Sci, 1 Kings Coll Circle, Toronto, ON M5S 1A8, Canada
hcfmusp.citation.scopus0
hcfmusp.contributor.author-fmusphcALICIA MATIJASEVICH MANITTO
hcfmusp.description.articlenumber105143
hcfmusp.description.volume177
hcfmusp.origemWOS
hcfmusp.origem.pubmed37473656
hcfmusp.origem.scopus2-s2.0-85166662242
hcfmusp.origem.wosWOS:001049245600001
hcfmusp.publisher.cityCLAREeng
hcfmusp.publisher.countryIRELANDeng
hcfmusp.relation.referenceAntonisamy B, 2017, J PEDIATR-US, V180, P53, DOI 10.1016/j.jpeds.2016.09.059eng
hcfmusp.relation.referenceAris IM, 2019, INT J EPIDEMIOL, V48, P157, DOI 10.1093/ije/dyy286eng
hcfmusp.relation.referenceBalantekin KN, 2018, EAT BEHAV, V31, P12, DOI 10.1016/j.eatbeh.2018.07.007eng
hcfmusp.relation.referenceBhargava SK, 2004, NEW ENGL J MED, V350, P865, DOI 10.1056/NEJMoa035698eng
hcfmusp.relation.referenceBusert LK, 2016, J NUTR, V146, P1387, DOI 10.3945/jn.115.220137eng
hcfmusp.relation.referenceCarsley S, 2015, INT J EPIDEMIOL, V44, P776, DOI 10.1093/ije/dyu123eng
hcfmusp.relation.referenceCLEVELAND WS, 1979, J AM STAT ASSOC, V74, P829, DOI 10.2307/2286407eng
hcfmusp.relation.referenceCole SZ, 2011, AM FAM PHYSICIAN, V83, P829eng
hcfmusp.relation.referenceCossio-Bolaños MA, 2020, AM J HUM BIOL, V32, DOI 10.1002/ajhb.23398eng
hcfmusp.relation.referencede Onis Mercedes, 2003, Forum Nutr, V56, P238eng
hcfmusp.relation.referenceDietterich T. G., 2004, P 21 INT C MACH LEAR, P28, DOI [10.1145/1015330.1015428, DOI 10.1145/1015330.101542832]eng
hcfmusp.relation.referenceFletcher RR, 2021, FRONT ARTIF INTELL, V3, DOI 10.3389/frai.2020.561802eng
hcfmusp.relation.referenceFrisk V, 2002, DEV NEUROPSYCHOL, V22, P565, DOI 10.1207/S15326942DN2203_2eng
hcfmusp.relation.referenceFulcher B, 2017, CELL SYST, V5, P527, DOI 10.1016/j.cels.2017.10.001eng
hcfmusp.relation.referenceGomula A., 2021, AM J HUM BIOL, V33eng
hcfmusp.relation.referenceGuyon I., 2003, Journal of Machine Learning Research, V3, P1157, DOI 10.1162/153244303322753616eng
hcfmusp.relation.referenceHerle M, 2020, EUR J EPIDEMIOL, V35, P205, DOI 10.1007/s10654-020-00615-6eng
hcfmusp.relation.referenceImai CM, 2014, NUTR METAB CARDIOVAS, V24, P730, DOI 10.1016/j.numecd.2014.01.001eng
hcfmusp.relation.referenceLavin A, 2022, NAT COMMUN, V13, DOI 10.1038/s41467-022-33128-9eng
hcfmusp.relation.referenceLaw CM, 2002, CIRCULATION, V105, P1088, DOI 10.1161/hc0902.104677eng
hcfmusp.relation.referenceLaxer RE, 2018, PLOS ONE, V13, DOI 10.1371/journal.pone.0190405eng
hcfmusp.relation.referenceLennon H, 2018, BMJ OPEN, V8, DOI 10.1136/bmjopen-2017-020683eng
hcfmusp.relation.referenceLeung M, 2018, PLOS ONE, V13, DOI 10.1371/journal.pone.0194565eng
hcfmusp.relation.referenceLópez-Domínguez L, 2023, SCI REP-UK, V13, DOI 10.1038/s41598-023-28485-4eng
hcfmusp.relation.referenceLubba CH, 2019, DATA MIN KNOWL DISC, V33, P1821, DOI 10.1007/s10618-019-00647-xeng
hcfmusp.relation.referenceMarceau K, 2011, DEV PSYCHOL, V47, P1389, DOI 10.1037/a0023838eng
hcfmusp.relation.referenceMassara P, 2021, P 31 ANN INT C COMPU, P220eng
hcfmusp.relation.referenceMassara P, 2021, INT J EPIDEMIOL, V50, P1000, DOI 10.1093/ije/dyab021eng
hcfmusp.relation.referenceMlakar M., 2023, PLOS ONE, V18eng
hcfmusp.relation.referenceOda Junichi, 2009, Proceedings of the 2009 Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing. IIH-MSP 2009, P1134, DOI 10.1109/IIH-MSP.2009.288eng
hcfmusp.relation.referenceParent C, 2013, ACM COMPUT SURV, V45, DOI 10.1145/2501654.2501656eng
hcfmusp.relation.referencePéneau S, 2017, J PEDIATR-US, V186, P64, DOI 10.1016/j.jpeds.2017.02.010eng
hcfmusp.relation.referenceProust-Lima C, 2011, R USER C USER 2011, P66eng
hcfmusp.relation.referenceProust-Lima C, 2017, J STAT SOFTW, V78, P1, DOI 10.18637/jss.v078.i02eng
hcfmusp.relation.referenceR Development Core Team, 2021, R LANG ENV STAT COMP, DOI 10.1038/sj.hdy.6800737eng
hcfmusp.relation.referenceRobinson HA, 2019, PREV MED REP, V14, DOI 10.1016/j.pmedr.2019.100834eng
hcfmusp.relation.referenceSantos IS, 2014, INT J EPIDEMIOL, V43, P1437, DOI 10.1093/ije/dyu144eng
hcfmusp.relation.referenceSantos IS, 2011, INT J EPIDEMIOL, V40, P1461, DOI 10.1093/ije/dyq130eng
hcfmusp.relation.referenceSokol RL, 2019, INT J OBESITY, V43, P1113, DOI 10.1038/s41366-018-0194-yeng
hcfmusp.relation.referenceSpeiser JL, 2019, EXPERT SYST APPL, V134, P93, DOI 10.1016/j.eswa.2019.05.028eng
hcfmusp.relation.referenceTirosh A, 2011, NEW ENGL J MED, V364, P1315, DOI 10.1056/NEJMoa1006992eng
hcfmusp.relation.referenceWen XZ, 2012, BMC MED RES METHODOL, V12, DOI 10.1186/1471-2288-12-38eng
hcfmusp.relation.referenceWorld Health Organization, 2020, LEVELS TRENDS CHILDeng
hcfmusp.scopus.lastupdate2024-04-12
relation.isAuthorOfPublication80ba0f0e-5cf3-4950-adeb-120ca4be5a71
relation.isAuthorOfPublication.latestForDiscovery80ba0f0e-5cf3-4950-adeb-120ca4be5a71
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Nenhuma Miniatura disponível
Nome:
art_MASSARA_A_novel_systematic_pipeline_for_increased_predictability_and_2023.PDF
Tamanho:
2.76 MB
Formato:
Adobe Portable Document Format
Descrição:
publishedVersion (English)
Baixar
Coleções
Artigos e Materiais de Revistas Científicas - FM/MPR
Artigos e Materiais de Revistas Científicas - LIM/39