Identification of High Likelihood of Dementia in Population-Based Surveys using Unsupervised Clustering: a Longitudinal Analysis
Identification of High Likelihood of Dementia in Population-Based Surveys using Unsupervised Clustering: a Longitudinal Analysis
SUMMARY BackgroundDementia is defined by cognitive decline that affects functional status. Longitudinal ageing surveys often lack a clinical diagnosis of dementia though measure cognitive and function over time. We used unsupervised machine learning and longitudinal data to identify transition to probable dementia. MethodsMultiple Factor Analysis was applied to longitudinal function and cognitive data of 15,278 baseline participants (aged 50 years and more) from the Survey of Health, Ageing, and Retirement in Europe (SHARE) (waves 1, 2 and 4–7, between 2004 and 2017). Hierarchical Clustering on Principal Components discriminated three clusters at each wave. We estimated probable or “Likely Dementia” prevalence by sex and age, and assessed whether dementia risk factors increased the risk of being assigned probable dementia status using multistate models. Next, we compared the “Likely Dementia” cluster with self-reported dementia status and replicated our findings in the English Longitudinal Study of Ageing (ELSA) cohort (waves 1–9, between 2002 and 2019, 7,840 participants at baseline). FindingsOur algorithm identified a higher number of probable dementia cases compared with self-reported cases and showed good discriminative power across all waves (AUC ranged from 0.754 [0.722–0.787] to 0.830 [0.800–0.861]). “Likely Dementia” status was more prevalent in older people, displayed a 2:1 female/male ratio and was associated with nine factors that increased risk of transition to dementia: low education, hearing loss, hypertension, drinking, smoking, depression, social isolation, physical inactivity, diabetes, and obesity. Results were replicated in ELSA cohort with good accuracy. InterpretationMachine learning clustering can be used to study dementia determinants and outcomes in longitudinal population ageing surveys in which dementia clinical diagnosis is lacking. FundingFrench Institute for Public Health Research (IReSP), French National Institute for Health and Medical Research (Inserm), NeurATRIS Grant (ANR-11-INBS-0011), and Front-Cog University Research School (ANR-17-EUR-0017).
Bachoud-L¨|vi Anne-Catherine、Gharbi-Meliani Amin、Vandendriessche Henri、Bayen Eleonore、Yaffe Kristine、Husson Fran?ois、de Langavant Laurent Cleret
Equipe neuropsychologie interventionnelle, Institut Mondor de Recherche Biom¨|dicale, D¨|partement d?ˉ¨|tudes cognitives, Ecole normale sup¨|rieure, Universit¨| PSL, Universit¨| Paris-Est Cr¨|teil, AP-HP H?pital Henri Mondor-Albert Chenevier, Centre de r¨|f¨|rence Maladie de Huntington et Service de Neurologie, INSERMEquipe neuropsychologie interventionnelle, Institut Mondor de Recherche Biom¨|dicale, D¨|partement d?ˉ¨|tudes cognitives, Ecole normale sup¨|rieure, Universit¨| PSL, Universit¨| Paris-Est Cr¨|teil, AP-HP H?pital Henri Mondor-Albert Chenevier, Centre de r¨|f¨|rence Maladie de Huntington et Service de Neurologie, INSERMLaboratoire de Neurosciences Cognitives et Computationnelles, D¨|partement d?ˉ¨|tudes cognitives, Ecole normale sup¨|rieure, Universit¨| PSL, INSERMGlobal Brain Health Institute, University of California||Sorbonne Universit¨|, H?pital Piti¨|-Salp¨otri¨¨re¨CAssistance Publique H?pitaux de Paris, D¨|partement de R¨|¨|ducation NeurologiqueGlobal Brain Health Institute, University of California||Departments of Psychiatry, Neurology and Epidemiology and Biostatistics, University of CaliforniaInstitut Agro, Univ Rennes1, CNRS, IRMAREquipe neuropsychologie interventionnelle, Institut Mondor de Recherche Biom¨|dicale, D¨|partement d?ˉ¨|tudes cognitives, Ecole normale sup¨|rieure, Universit¨| PSL, Universit¨| Paris-Est Cr¨|teil, AP-HP H?pital Henri Mondor-Albert Chenevier, Centre de r¨|f¨|rence Maladie de Huntington et Service de Neurologie, INSERM||Global Brain Health Institute, University of California
神经病学、精神病学医学研究方法
Bachoud-L¨|vi Anne-Catherine,Gharbi-Meliani Amin,Vandendriessche Henri,Bayen Eleonore,Yaffe Kristine,Husson Fran?ois,de Langavant Laurent Cleret.Identification of High Likelihood of Dementia in Population-Based Surveys using Unsupervised Clustering: a Longitudinal Analysis[EB/OL].(2025-03-28)[2025-04-28].https://www.medrxiv.org/content/10.1101/2023.02.17.23286078.点此复制
评论