Data-driven decision making for the screening of cognitive impairment in primary care: a machine learning approach using data from the ELSA-Brasil study

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.authorSZLEJF, C.
dc.contributor.authorBATISTA, A. F. M.
dc.contributor.authorBERTOLA, L.
dc.contributor.authorLOTUFO, P. A.
dc.contributor.authorBENSENOR, I. M.
dc.contributor.authorCHIAVEGATTO FILHO, A. D. P.
dc.contributor.authorSUEMOTO, C. K.
dc.date.accessioned2023-04-14T17:21:52Z
dc.date.available2023-04-14T17:21:52Z
dc.date.issued2023
dc.description.abstractThe systematic assessment of cognitive performance of older people without cognitive complaints is controversial and unfeasible. Identifying individuals at higher risk of cognitive impairment could optimize resource allocation. We aimed to develop and test machine learning models to predict cognitive impairment using variables obtainable in primary care settings. In this cross-sectional study, we included 8,291 participants of the baseline assessment of the ELSA-Brasil study, who were aged between 50 and 74 years and were free of dementia. Cognitive performance was assessed with a neuropsychological battery and cognitive impairment was defined as global cognitive z-score below 2 standard deviations. Variables used as input to the prediction models included demographics, social determinants, clinical conditions, family history, lifestyle, and laboratory tests. We developed machine learning models using logistic regression, neural networks, and gradient boosted trees. Participants' mean age was 58.3 +/- 6.2 years, 55% were female. Cognitive impairment was present in 328 individuals (4%). Machine learning algorithms presented fair to good discrimination (areas under the ROC curve between 0.801 and 0.873). Extreme Gradient Boosting presented the highest discrimination, high specificity (97%), and negative predictive value (97%). Seventy-six percent of the individuals with cognitive impairment were included among the highest ranked individuals by this algorithm. In conclusion, we developed and tested a machine learning model to predict cognitive impairment based on primary care data that presented good discrimination and high specificity. These characteristics could support the detection of patients who would not benefit from cognitive assessment, facilitating the allocation of human and economic resources.eng
dc.description.indexMEDLINE
dc.description.indexPubMed
dc.description.indexWoS
dc.description.indexScopus
dc.description.indexScielo
dc.description.sponsorshipBrazilian Ministry of Health
dc.description.sponsorshipCNPq [01060010.00RS, 01060212.00BA, 01060300.00ES, 01060278.00MG, 010 60115.00SP, 0106071.00RJ]
dc.identifier.citationBRAZILIAN JOURNAL OF MEDICAL AND BIOLOGICAL RESEARCH, v.56, n.1, article ID e12475, 8p, 2023
dc.identifier.doi10.1590/1414-431X2023e12475
dc.identifier.eissn1414-431X
dc.identifier.issn0100-879X
dc.identifier.urihttps://observatorio.fm.usp.br/handle/OPI/52841
dc.language.isoeng
dc.publisherASSOC BRAS DIVULG CIENTIFICAeng
dc.relation.ispartofBrazilian Journal of Medical and Biological Research
dc.rightsopenAccesseng
dc.rights.holderCopyright ASSOC BRAS DIVULG CIENTIFICAeng
dc.subjectArtificial intelligenceeng
dc.subjectCognitioneng
dc.subjectPredictioneng
dc.subjectPrimary careeng
dc.subject.otherrisk scoreeng
dc.subject.otherdementia riskeng
dc.subject.otherpredictioneng
dc.subject.wosBiologyeng
dc.subject.wosMedicine, Research & Experimentaleng
dc.titleData-driven decision making for the screening of cognitive impairment in primary care: a machine learning approach using data from the ELSA-Brasil studyeng
dc.typearticleeng
dc.type.categoryoriginal articleeng
dc.type.versionpublishedVersioneng
dspace.entity.typePublication
hcfmusp.author.externalBATISTA, A. F. M.:Univ Sao Paulo, Fac Saude Publ, Dept Epidemiol, Sao Paulo, SP, Brazil; Insper Inst Ensino & Pesquisa, Sao Paulo, SP, Brazil
hcfmusp.author.externalBERTOLA, L.:Univ Sao Paulo, Hosp Univ, Ctr Pesquisa Clin & Epidemiol, Sao Paulo, SP, Brazil
hcfmusp.author.externalCHIAVEGATTO FILHO, A. D. P.:Univ Sao Paulo, Fac Saude Publ, Dept Epidemiol, Sao Paulo, SP, Brazil
hcfmusp.citation.scopus1
hcfmusp.contributor.author-fmusphcCLAUDIA SZLEJF JERUSSALMY
hcfmusp.contributor.author-fmusphcPAULO ANDRADE LOTUFO
hcfmusp.contributor.author-fmusphcISABELA JUDITH MARTINS BENSEñOR
hcfmusp.contributor.author-fmusphcCLAUDIA KIMIE SUEMOTO
hcfmusp.description.articlenumbere12475
hcfmusp.description.issue1
hcfmusp.description.volume56
hcfmusp.origemWOS
hcfmusp.origem.pubmed36722661
hcfmusp.origem.scieloSCIELO:S0100-879X2023000100607
hcfmusp.origem.scopus2-s2.0-85147186557
hcfmusp.origem.wosWOS:000927104100001
hcfmusp.publisher.cityRIBEIRAO PRETOeng
hcfmusp.publisher.countryBRAZILeng
hcfmusp.relation.referenceAlzheimer's Association, POL BRIEF EARL DET Deng
hcfmusp.relation.reference[Anonymous], WORLD REP AG HLTHeng
hcfmusp.relation.referenceAquino EML, 2012, AM J EPIDEMIOL, V175, P315, DOI 10.1093/aje/kwr294eng
hcfmusp.relation.referenceBarnes DE, 2020, J AM GERIATR SOC, V68, P103, DOI 10.1111/jgs.16182eng
hcfmusp.relation.referenceBarnes DE, 2014, ALZHEIMERS DEMENT, V10, P656, DOI 10.1016/j.jalz.2013.11.006eng
hcfmusp.relation.referenceBelleville S, 2017, NEUROPSYCHOL REV, V27, P328, DOI 10.1007/s11065-017-9361-5eng
hcfmusp.relation.referenceBertola L, 2021, EUR J NEUROL, V28, P3972, DOI 10.1111/ene.15042eng
hcfmusp.relation.referenceBertola L, 2020, NEUROPSYCHOLOGY, V34, P227, DOI 10.1037/neu0000597eng
hcfmusp.relation.referenceBertolucci PHF, 2001, ARQ NEURO-PSIQUIAT, V59, P532, DOI 10.1590/S0004-282X2001000400009eng
hcfmusp.relation.referenceChawla NV, 2002, J ARTIF INTELL RES, V16, P321, DOI 10.1613/jair.953eng
hcfmusp.relation.referenceDaoud E., 2019, INT J COMPUT INF ENG, V13, P6, DOI [10.5281/zenodo.3607805, DOI 10.5281/ZENODO.3607805, 10.5281/ ZENODO.3607805]eng
hcfmusp.relation.referenceExalto LG, 2014, ALZHEIMERS DEMENT, V10, P562, DOI 10.1016/j.jalz.2013.05.1772eng
hcfmusp.relation.referenceFichman Helenice Charchat, 2009, Dement. neuropsychol., V3, P49, DOI 10.1590/S1980-57642009DN30100010eng
hcfmusp.relation.referenceResende EDF, 2019, JAMA NEUROL, V76, P633, DOI 10.1001/jamaneurol.2019.0362eng
hcfmusp.relation.referenceFriedman JH, 2001, ANN STAT, V29, P1189, DOI 10.1214/aos/1013203451eng
hcfmusp.relation.referenceHamdan Amer C., 2009, Psychol. Neurosci., V2, P199, DOI 10.3922/j.psns.2009.2.012eng
hcfmusp.relation.referenceHaykin S., 1998, NEURAL NETWORKS COMPeng
hcfmusp.relation.referenceHou XH, 2019, J NEUROL NEUROSUR PS, V90, P373, DOI 10.1136/jnnp-2018-318212eng
hcfmusp.relation.referenceHu MY, 2021, J MED INTERNET RES, V23, DOI 10.2196/20298eng
hcfmusp.relation.referenceInstitute for Health Metrics and Evaluation, GBD COMPAREeng
hcfmusp.relation.referenceJessen F, 2011, PLOS ONE, V6, DOI 10.1371/journal.pone.0016852eng
hcfmusp.relation.referenceKaffashian S, 2011, EUR HEART J, V32, P2326, DOI 10.1093/eurheartj/ehr133eng
hcfmusp.relation.referenceKivipelto M, 2006, LANCET NEUROL, V5, P735, DOI 10.1016/S1474-4422(06)70537-3eng
hcfmusp.relation.referenceLivingston G, 2020, LANCET, V396, P413, DOI 10.1016/S0140-6736(20)30367-6eng
hcfmusp.relation.referenceLundberg SM, 2017, NIPS Peng
hcfmusp.relation.referenceMachado Thais Helena, 2009, Dement. neuropsychol., V3, P55, DOI 10.1590/S1980-57642009DN30100011eng
hcfmusp.relation.referenceNa KS, 2019, SCI REP-UK, V9, DOI 10.1038/s41598-019-39478-7eng
hcfmusp.relation.referenceOwens DK, 2020, JAMA-J AM MED ASSOC, V323, P757, DOI 10.1001/jama.2020.0435eng
hcfmusp.relation.referencePottie K, 2016, CAN MED ASSOC J, V188, P37, DOI 10.1503/cmaj.141165eng
hcfmusp.relation.referenceRajkomar A, 2019, NEW ENGL J MED, V380, P1347, DOI 10.1056/NEJMra1814259eng
hcfmusp.relation.referenceReijmer YD, 2011, DEMENT GERIATR COGN, V31, P152, DOI 10.1159/000324437eng
hcfmusp.relation.referenceSachdev PS, 2014, NAT REV NEUROL, V10, P634, DOI 10.1038/nrneurol.2014.181eng
hcfmusp.relation.referenceSchmidt MI, 2015, INT J EPIDEMIOL, V44, P68, DOI 10.1093/ije/dyu027eng
hcfmusp.relation.referenceStern Y, 2020, ALZHEIMERS DEMENT, V16, P1305, DOI 10.1016/j.jalz.2018.07.219eng
hcfmusp.relation.referenceTang EYH, 2015, PLOS ONE, V10, DOI 10.1371/journal.pone.0136181eng
hcfmusp.relation.referenceThe Gerontological Society of America, GER SOC AM WORKGR COeng
hcfmusp.relation.referenceDorogush AV, 2018, Arxiveng
hcfmusp.relation.referenceVuoksimaa Eero, 2016, Alzheimers Dement (Amst), V4, P118eng
hcfmusp.relation.referenceWalters K, 2016, BMC MED, V14, DOI 10.1186/s12916-016-0549-yeng
hcfmusp.relation.referenceWeissberger GH, 2017, NEUROPSYCHOL REV, V27, P354, DOI 10.1007/s11065-017-9360-6eng
hcfmusp.scopus.lastupdate2024-05-10
relation.isAuthorOfPublicationedad4acd-a98b-417f-9e0a-c5953926f75c
relation.isAuthorOfPublicationcb0c8dbb-6df5-4294-8d8e-e96645a3cec1
relation.isAuthorOfPublication6911f59e-7ec9-4ad2-b746-580bf8b3d64d
relation.isAuthorOfPublicationf2cec589-a4ad-4b49-a515-19f8c359b34b
relation.isAuthorOfPublication.latestForDiscoveryedad4acd-a98b-417f-9e0a-c5953926f75c
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
art_SZLEJF_Datadriven_decision_making_for_the_screening_of_cognitive_.PDF
Tamanho:
386.15 KB
Formato:
Adobe Portable Document Format
Descrição:
publishedVersion (English)
Baixar
Coleções
Artigos e Materiais de Revistas Científicas - FM/MCM
Artigos e Materiais de Revistas Científicas - LIM/20
Artigos e Materiais de Revistas Científicas - LIM/22
Artigos e Materiais de Revistas Científicas - LIM/66