Unsupervised Machine Learning to Identify High Likelihood of Dementia in Population-Based Surveys: Development and Validation Study

• Published in: Journal of medical Internet research 2018-07, Vol.20 (7), p.e10493-e10493
• Main Authors: Cleret de Langavant, Laurent, Bayen, Eleonore, Yaffe, Kristine
• Format: Article
• Language: English
• Subjects: Activities of daily living; Age; Aging; Algorithms; Classification; Climbing; Clustering; Cognition & reasoning; Cognitive-behavioral factors; Datasets; Dementia; Dementia - diagnosis; Dementia - pathology; Female; Humans; Limitations; Longitudinal Studies; Machine learning; Male; Medical diagnosis; Mental depression; Middle Aged; Mobility; Older people; Original Paper; Polls & surveys; Population; Population-based studies; Prevalence; Principal components analysis; Retirement; Software; Surveys; Undiagnosed; Unsupervised Machine Learning - trends; Validation studies; Validation Studies as Topic; Validity; Variables; Walking
• ISSN: 1438-8871; 1439-4456; 1438-8871
• DOI: 10.2196/10493

Dementia is increasing in prevalence worldwide, yet frequently remains undiagnosed, especially in low- and middle-income countries. Population-based surveys represent an underinvestigated source to identify individuals at risk of dementia. The aim is to identify participants with high likelihood of dementia in population-based surveys without the need of the clinical diagnosis of dementia in a subsample. Unsupervised machine learning classification (hierarchical clustering on principal components) was developed in the Health and Retirement Study (HRS; 2002-2003, N=18,165 individuals) and validated in the Survey of Health, Ageing and Retirement in Europe (SHARE; 2010-2012, N=58,202 individuals). Unsupervised machine learning classification identified three clusters in HRS: cluster 1 (n=12,231) without any functional or motor limitations, cluster 2 (N=4841) with walking/climbing limitations, and cluster 3 (N=1093) with both functional and walking/climbing limitations. Comparison of cluster 3 with previously published predicted probabilities of dementia in HRS showed that it identified high likelihood of dementia (probability of dementia >0.95; area under the curve [AUC]=0.91). Removing either cognitive or both cognitive and behavioral measures did not impede accurate classification (AUC=0.91 and AUC=0.90, respectively). Three clusters with similar profiles were identified in SHARE (cluster 1: n=40,223; cluster 2: n=15,644; cluster 3: n=2335). Survival rate of participants from cluster 3 reached 39.2% (n=665 deceased) in HRS and 62.2% (n=811 deceased) in SHARE after a 3.9-year follow-up. Surviving participants from cluster 3 in both cohorts worsened their functional and mobility performance over the same period. Unsupervised machine learning identifies high likelihood of dementia in population-based surveys, even without cognitive and behavioral measures and without the need of clinical diagnosis of dementia in a subsample of the population. This method could be used to tackle the global challenge of dementia.