Your browser doesn't support javascript.
loading
Clustering analysis and machine learning algorithms in the prediction of dietary patterns: Cross-sectional results of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil).
Silva, Vanderlei Carneiro; Gorgulho, Bartira; Marchioni, Dirce Maria; Araujo, Tânia Aparecida de; Santos, Itamar de Souza; Lotufo, Paulo Andrade; Benseñor, Isabela Martins.
Afiliação
  • Silva VC; Department of Epidemiology, School of Public Health, University of São Paulo, São Paulo, Brazil.
  • Gorgulho B; Center of Clinical and Epidemiological Research, University Hospital, University of São Paulo, São Paulo, Brazil.
  • Marchioni DM; Department of Food and Nutrition, School of Nutrition, Federal University of Mato Grosso, Cuiaba, Brazil.
  • Araujo TA; Department of Nutrition, School of Public Health, University of São Paulo, São Paulo, Brazil.
  • Santos IS; Department of Epidemiology, School of Public Health, University of São Paulo, São Paulo, Brazil.
  • Lotufo PA; Center of Clinical and Epidemiological Research, University Hospital, University of São Paulo, São Paulo, Brazil.
  • Benseñor IM; Center of Clinical and Epidemiological Research, University Hospital, University of São Paulo, São Paulo, Brazil.
J Hum Nutr Diet ; 35(5): 883-894, 2022 10.
Article em En | MEDLINE | ID: mdl-35043491
BACKGROUND: Machine learning investigates how computers can automatically learn. The present study aimed to predict dietary patterns and compare algorithm performance in making predictions of dietary patterns. METHODS: We analysed the data of public employees (n = 12,667) participating in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). The K-means clustering algorithm and six other classifiers (support vector machines, naïve Bayes, K-nearest neighbours, decision tree, random forest and xgboost) were used to predict the dietary patterns. RESULTS: K-means clustering identified two dietary patterns. Cluster 1, labelled the Western pattern, was characterised by a higher energy intake and consumption of refined cereals, beans and other legumes, tubers, pasta, processed and red meats, high-fat milk and dairy products, and sugary beverages; Cluster 2, labelled the Prudent pattern, was characterised by higher intakes of fruit, vegetables, whole cereals, white meats, and milk and reduced-fat milk derivatives. The most important predictors were age, sex, per capita income, education level and physical activity. The accuracy of the models varied from moderate to good (69%-72%). CONCLUSIONS: The performance of the algorithms in dietary pattern prediction was similar, and the models presented may provide support in screener tasks and guide health professionals in the analysis of dietary data.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Verduras / Dieta Tipo de estudo: Observational_studies / Prevalence_studies / Prognostic_studies / Risk_factors_studies Limite: Adult / Humans País/Região como assunto: America do sul / Brasil Idioma: En Ano de publicação: 2022 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Verduras / Dieta Tipo de estudo: Observational_studies / Prevalence_studies / Prognostic_studies / Risk_factors_studies Limite: Adult / Humans País/Região como assunto: America do sul / Brasil Idioma: En Ano de publicação: 2022 Tipo de documento: Article