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

Imagem de Miniatura
Arquivos
art_SZLEJF_Datadriven_decision_making_for_the_screening_of_cognitive_.PDF (386.15 KB)
Citações na Scopus
1
Tipo de produção
article
Data de publicação
2023
DOI
SciELO
Scopus
Web of Science
PubMed
Título da Revista
ISSN da Revista
Título do Volume
Editora
ASSOC BRAS DIVULG CIENTIFICA
Autores
BATISTA, A. F. M.
BERTOLA, L.
CHIAVEGATTO FILHO, A. D. P.
Citação
BRAZILIAN JOURNAL OF MEDICAL AND BIOLOGICAL RESEARCH, v.56, n.1, article ID e12475, 8p, 2023
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
The 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.
Palavras-chave
Artificial intelligence, Cognition, Prediction, Primary care
URI
https://observatorio.fm.usp.br/handle/OPI/52841
Referências
  1. Alzheimer's Association, POL BRIEF EARL DET D
  2. [Anonymous], WORLD REP AG HLTH
  3. Aquino EML, 2012, AM J EPIDEMIOL, V175, P315, DOI 10.1093/aje/kwr294
  4. Barnes DE, 2020, J AM GERIATR SOC, V68, P103, DOI 10.1111/jgs.16182
  5. Barnes DE, 2014, ALZHEIMERS DEMENT, V10, P656, DOI 10.1016/j.jalz.2013.11.006
  6. Belleville S, 2017, NEUROPSYCHOL REV, V27, P328, DOI 10.1007/s11065-017-9361-5
  7. Bertola L, 2021, EUR J NEUROL, V28, P3972, DOI 10.1111/ene.15042
  8. Bertola L, 2020, NEUROPSYCHOLOGY, V34, P227, DOI 10.1037/neu0000597
  9. Bertolucci PHF, 2001, ARQ NEURO-PSIQUIAT, V59, P532, DOI 10.1590/S0004-282X2001000400009
  10. Chawla NV, 2002, J ARTIF INTELL RES, V16, P321, DOI 10.1613/jair.953
  11. Daoud E., 2019, INT J COMPUT INF ENG, V13, P6, DOI [10.5281/zenodo.3607805, DOI 10.5281/ZENODO.3607805, 10.5281/ ZENODO.3607805]
  12. Exalto LG, 2014, ALZHEIMERS DEMENT, V10, P562, DOI 10.1016/j.jalz.2013.05.1772
  13. Fichman Helenice Charchat, 2009, Dement. neuropsychol., V3, P49, DOI 10.1590/S1980-57642009DN30100010
  14. Resende EDF, 2019, JAMA NEUROL, V76, P633, DOI 10.1001/jamaneurol.2019.0362
  15. Friedman JH, 2001, ANN STAT, V29, P1189, DOI 10.1214/aos/1013203451
  16. Hamdan Amer C., 2009, Psychol. Neurosci., V2, P199, DOI 10.3922/j.psns.2009.2.012
  17. Haykin S., 1998, NEURAL NETWORKS COMP
  18. Hou XH, 2019, J NEUROL NEUROSUR PS, V90, P373, DOI 10.1136/jnnp-2018-318212
  19. Hu MY, 2021, J MED INTERNET RES, V23, DOI 10.2196/20298
  20. Institute for Health Metrics and Evaluation, GBD COMPARE
  21. Jessen F, 2011, PLOS ONE, V6, DOI 10.1371/journal.pone.0016852
  22. Kaffashian S, 2011, EUR HEART J, V32, P2326, DOI 10.1093/eurheartj/ehr133
  23. Kivipelto M, 2006, LANCET NEUROL, V5, P735, DOI 10.1016/S1474-4422(06)70537-3
  24. Livingston G, 2020, LANCET, V396, P413, DOI 10.1016/S0140-6736(20)30367-6
  25. Lundberg SM, 2017, NIPS P
  26. Machado Thais Helena, 2009, Dement. neuropsychol., V3, P55, DOI 10.1590/S1980-57642009DN30100011
  27. Na KS, 2019, SCI REP-UK, V9, DOI 10.1038/s41598-019-39478-7
  28. Owens DK, 2020, JAMA-J AM MED ASSOC, V323, P757, DOI 10.1001/jama.2020.0435
  29. Pottie K, 2016, CAN MED ASSOC J, V188, P37, DOI 10.1503/cmaj.141165
  30. Rajkomar A, 2019, NEW ENGL J MED, V380, P1347, DOI 10.1056/NEJMra1814259
  31. Reijmer YD, 2011, DEMENT GERIATR COGN, V31, P152, DOI 10.1159/000324437
  32. Sachdev PS, 2014, NAT REV NEUROL, V10, P634, DOI 10.1038/nrneurol.2014.181
  33. Schmidt MI, 2015, INT J EPIDEMIOL, V44, P68, DOI 10.1093/ije/dyu027
  34. Stern Y, 2020, ALZHEIMERS DEMENT, V16, P1305, DOI 10.1016/j.jalz.2018.07.219
  35. Tang EYH, 2015, PLOS ONE, V10, DOI 10.1371/journal.pone.0136181
  36. The Gerontological Society of America, GER SOC AM WORKGR CO
  37. Dorogush AV, 2018, Arxiv
  38. Vuoksimaa Eero, 2016, Alzheimers Dement (Amst), V4, P118
  39. Walters K, 2016, BMC MED, V14, DOI 10.1186/s12916-016-0549-y
  40. Weissberger GH, 2017, NEUROPSYCHOL REV, V27, P354, DOI 10.1007/s11065-017-9360-6

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