Data-driven decision making for the screening of cognitive impairment in primary care: a machine learning approach using data from the ELSA-Brasil study
Carregando...
Citações na Scopus
1
Tipo de produção
article
Data de publicação
2023
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
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
Referências
- Alzheimer's Association, POL BRIEF EARL DET D
- [Anonymous], WORLD REP AG HLTH
- Aquino EML, 2012, AM J EPIDEMIOL, V175, P315, DOI 10.1093/aje/kwr294
- Barnes DE, 2020, J AM GERIATR SOC, V68, P103, DOI 10.1111/jgs.16182
- Barnes DE, 2014, ALZHEIMERS DEMENT, V10, P656, DOI 10.1016/j.jalz.2013.11.006
- Belleville S, 2017, NEUROPSYCHOL REV, V27, P328, DOI 10.1007/s11065-017-9361-5
- Bertola L, 2021, EUR J NEUROL, V28, P3972, DOI 10.1111/ene.15042
- Bertola L, 2020, NEUROPSYCHOLOGY, V34, P227, DOI 10.1037/neu0000597
- Bertolucci PHF, 2001, ARQ NEURO-PSIQUIAT, V59, P532, DOI 10.1590/S0004-282X2001000400009
- Chawla NV, 2002, J ARTIF INTELL RES, V16, P321, DOI 10.1613/jair.953
- Daoud E., 2019, INT J COMPUT INF ENG, V13, P6, DOI [10.5281/zenodo.3607805, DOI 10.5281/ZENODO.3607805, 10.5281/ ZENODO.3607805]
- Exalto LG, 2014, ALZHEIMERS DEMENT, V10, P562, DOI 10.1016/j.jalz.2013.05.1772
- Fichman Helenice Charchat, 2009, Dement. neuropsychol., V3, P49, DOI 10.1590/S1980-57642009DN30100010
- Resende EDF, 2019, JAMA NEUROL, V76, P633, DOI 10.1001/jamaneurol.2019.0362
- Friedman JH, 2001, ANN STAT, V29, P1189, DOI 10.1214/aos/1013203451
- Hamdan Amer C., 2009, Psychol. Neurosci., V2, P199, DOI 10.3922/j.psns.2009.2.012
- Haykin S., 1998, NEURAL NETWORKS COMP
- Hou XH, 2019, J NEUROL NEUROSUR PS, V90, P373, DOI 10.1136/jnnp-2018-318212
- Hu MY, 2021, J MED INTERNET RES, V23, DOI 10.2196/20298
- Institute for Health Metrics and Evaluation, GBD COMPARE
- Jessen F, 2011, PLOS ONE, V6, DOI 10.1371/journal.pone.0016852
- Kaffashian S, 2011, EUR HEART J, V32, P2326, DOI 10.1093/eurheartj/ehr133
- Kivipelto M, 2006, LANCET NEUROL, V5, P735, DOI 10.1016/S1474-4422(06)70537-3
- Livingston G, 2020, LANCET, V396, P413, DOI 10.1016/S0140-6736(20)30367-6
- Lundberg SM, 2017, NIPS P
- Machado Thais Helena, 2009, Dement. neuropsychol., V3, P55, DOI 10.1590/S1980-57642009DN30100011
- Na KS, 2019, SCI REP-UK, V9, DOI 10.1038/s41598-019-39478-7
- Owens DK, 2020, JAMA-J AM MED ASSOC, V323, P757, DOI 10.1001/jama.2020.0435
- Pottie K, 2016, CAN MED ASSOC J, V188, P37, DOI 10.1503/cmaj.141165
- Rajkomar A, 2019, NEW ENGL J MED, V380, P1347, DOI 10.1056/NEJMra1814259
- Reijmer YD, 2011, DEMENT GERIATR COGN, V31, P152, DOI 10.1159/000324437
- Sachdev PS, 2014, NAT REV NEUROL, V10, P634, DOI 10.1038/nrneurol.2014.181
- Schmidt MI, 2015, INT J EPIDEMIOL, V44, P68, DOI 10.1093/ije/dyu027
- Stern Y, 2020, ALZHEIMERS DEMENT, V16, P1305, DOI 10.1016/j.jalz.2018.07.219
- Tang EYH, 2015, PLOS ONE, V10, DOI 10.1371/journal.pone.0136181
- The Gerontological Society of America, GER SOC AM WORKGR CO
- Dorogush AV, 2018, Arxiv
- Vuoksimaa Eero, 2016, Alzheimers Dement (Amst), V4, P118
- Walters K, 2016, BMC MED, V14, DOI 10.1186/s12916-016-0549-y
- Weissberger GH, 2017, NEUROPSYCHOL REV, V27, P354, DOI 10.1007/s11065-017-9360-6