Circulating serum metabolites as predictors of dementia: a machine learning approach in a 21-year follow-up of the Whitehall II cohort study.

Journal: BMC medicine
PMID: 36163029

Abstract

BACKGROUND: Age is the strongest risk factor for dementia and there is considerable interest in identifying scalable, blood-based biomarkers in predicting dementia. We examined the role of midlife serum metabolites using a machine learning approach and determined whether the selected metabolites improved prediction accuracy beyond the effect of age.

Authors

  • Marcos D Machado-Fragua
    Université de Paris, Inserm U1153, Epidemiology of Ageing and Neurodegenerative Diseases, 10 Avenue de Verdun, 75010, Paris, France. marcos.machado@inserm.fr.
  • Benjamin Landré
    Université de Paris, Inserm U1153, Epidemiology of Ageing and Neurodegenerative Diseases, 10 Avenue de Verdun, 75010, Paris, France.
  • Mathilde Chen
    Université de Paris, Inserm U1153, Epidemiology of Ageing and Neurodegenerative Diseases, 10 Avenue de Verdun, 75010, Paris, France.
  • Aurore Fayosse
    Université de Paris, Inserm U1153, Epidemiology of Ageing and Neurodegenerative Diseases, 10 Avenue de Verdun, 75010, Paris, France.
  • Aline Dugravot
    Université de Paris, Inserm U1153, Epidemiology of Ageing and Neurodegenerative Diseases, 10 Avenue de Verdun, 75010, Paris, France.
  • Mika Kivimaki
    Department of Epidemiology and Public Health, University College London, London, UK.
  • Séverine Sabia
    INSERM, U1018, Centre for Research in Epidemiology and Population Health, Paris, France.
  • Archana Singh-Manoux
    Université de Paris, Inserm U1153, Epidemiology of Ageing and Neurodegenerative Diseases, 10 Avenue de Verdun, 75010, Paris, France.

Keywords

External Resources

Popular Topics
Recent Journals