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

被引:0
|
作者
Szlejf, C. [1 ,2 ]
Batista, A. F. M. [3 ,4 ]
Bertola, L. [1 ]
Lotufo, P. A. [1 ]
Bensenor, I. M. [1 ]
Chiavegatto Filho, A. D. P. [3 ]
Suemoto, C. K. [1 ,5 ]
机构
[1] Univ Sao Paulo, Hosp Univ, Ctr Pesquisa Clin & Epidemiol, Sao Paulo, SP, Brazil
[2] Hosp Israelita Albert Einstein, Sao Paulo, SP, Brazil
[3] Univ Sao Paulo, Fac Saude Publ, Dept Epidemiol, Sao Paulo, SP, Brazil
[4] Insper Inst Ensino & Pesquisa, Sao Paulo, SP, Brazil
[5] Univ Sao Paulo, Fac Med, Div Geriatria, Sao Paulo, SP, Brazil
关键词
Artificial intelligence; Cognition; Prediction; Primary care; RISK SCORE; DEMENTIA RISK; PREDICTION;
D O I
10.1590/1414-431X2023e12475
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
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.
引用
收藏
页数:8
相关论文
共 50 条
  • [21] A Modern Approach to Security: Using Systems Engineering and Data-Driven Decision-Making
    Cano, Lester A.
    Staid, Andrea
    2016 IEEE INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY (ICCST), 2016,
  • [22] Building Energy Performance Prediction Using Machine Learning: A Data-Driven Decision-Making Framework for Energy Retrofits
    Murrieum, Munahil
    Jafari, Amirhosein
    Akhavian, Reza
    CONSTRUCTION RESEARCH CONGRESS 2020: COMPUTER APPLICATIONS, 2020, : 436 - 447
  • [23] Data-driven Decision-making Strategies for Electricity Retailers: A Deep Reinforcement Learning Approach
    Liu, Yuankun
    Zhang, Dongxia
    Gooi, Hoay Beng
    CSEE JOURNAL OF POWER AND ENERGY SYSTEMS, 2021, 7 (02): : 358 - 367
  • [24] A Data-driven Decision-making Approach for Complex Product Design Based on Deep Learning
    Lai, Zou
    Fu, Siqin
    Yu, Hang
    Lan, Shulin
    Yang, Chen
    PROCEEDINGS OF THE 2021 IEEE 24TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN (CSCWD), 2021, : 238 - 243
  • [25] A data-driven decision-making optimization approach for inconsistent lithium-ion cell screening
    Chengbao Liu
    Jie Tan
    Xuelei Wang
    Journal of Intelligent Manufacturing, 2020, 31 : 833 - 845
  • [26] Data-Driven Machine Learning Approach for Predicting Missing Values in Large Data Sets: A Comparison Study
    Elezaj, Ogerta
    Yildirim, Sule
    Kalemi, Edlira
    MACHINE LEARNING, OPTIMIZATION, AND BIG DATA, MOD 2017, 2018, 10710 : 268 - 285
  • [27] A data-driven decision-making optimization approach for inconsistent lithium-ion cell screening
    Liu, Chengbao
    Tan, Jie
    Wang, Xuelei
    JOURNAL OF INTELLIGENT MANUFACTURING, 2020, 31 (04) : 833 - 845
  • [28] Association between dietary patterns and renal function in a cross-sectional study using baseline data from the ELSA-Brasil cohort
    Silva Junior, G. B.
    Fraser, S. D. S.
    Neri, A. K. M.
    Xavier, R. M. F.
    Mota, R. M. S.
    Lopes, A. A.
    Mill, J. G.
    Barreto, S. M.
    Luft, V. C.
    Chor, D.
    Santos, C. A. S. T.
    Lotufo, P. A.
    Matos, S. M. A.
    BRAZILIAN JOURNAL OF MEDICAL AND BIOLOGICAL RESEARCH, 2020, 53 (12)
  • [29] A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning
    Dominguez, Lauren Genith Isaza
    Robles-Gomez, Antonio
    Pastor-Vargas, Rafael
    IEEE ACCESS, 2025, 13 : 10978 - 11002
  • [30] Machine learning & deep learning in data-driven decision making of drug discovery and challenges in high-quality data acquisition in the pharmaceutical industry
    Kumar, Sethu Arun
    Ananda Kumar, Thirumoorthy Durai
    Beeraka, Narasimha M.
    Pujar, Gurubasavaraj Veeranna
    Singh, Manisha
    Narayana Akshatha, Handattu Sankara
    Bhagyalalitha, Meduri
    FUTURE MEDICINAL CHEMISTRY, 2022, 14 (04) : 245 - 270