Identification of high likelihood of dementia in population-based surveys using unsupervised clustering: a longitudinal analysis.

BACKGROUND: Dementia is defined as a cognitive decline that affects functional status. Longitudinal ageing surveys often lack a clinical diagnosis of dementia though measure cognition and daily function over time. We used unsupervised machine learning and longitudinal data to identify transition to probable dementia. METHODS: Multiple 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, 7840 participants at baseline). RESULTS: Our 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. CONCLUSIONS: Machine learning clustering can be used to study dementia determinants and outcomes in longitudinal population ageing surveys in which dementia clinical diagnosis is lacking.

Longitudinal study of informed consent in innovative therapy research: experience and provisional recommendations from a multicenter trial of intracerebral grafting.

BACKGROUND: There is an urgent need to assess and improve the consent process in clinical trials of innovative therapies for neurodegenerative disorders. METHODS: We performed a longitudinal study of the consent of Huntington's disease patients during the Multicenter Fetal Cell Intracerebral Grafting Trial in Huntington's Disease (MIG-HD) in France and Belgium. Patients and their proxies completed a consent questionnaire at inclusion, before signing the consent form and after one year of follow-up, before randomization and transplantation. The questionnaire explored understanding of the protocol, satisfaction with the information delivered, reasons for participating in the trial and expectations regarding the transplant. Forty-six Huntington's disease patients and 27 proxies completed the questionnaire at inclusion, and 27 Huntington's disease patients and 16 proxies one year later. RESULTS: The comprehension score was high and similar for Huntington's disease patients and proxies at inclusion (72.6% vs 77.8%; P > 0.1) but only decreased in HD patients after one year. The information satisfaction score was high (73.5% vs 66.5%; P > 0.1) and correlated with understanding in both patients and proxies. The motivation and expectation profiles were similar in patients and proxies and remained unchanged after one year. CONCLUSIONS: Cognitively impaired patients with Huntington's disease were capable of consenting to participation in this trial. This consent procedure has presumably strengthened their understanding and should be proposed before signing the consent form in future gene or cell therapy trials for neurodegenerative disorders. Because of the potential cognitive decline, proxies should be designated as provisional surrogate decision-makers, even in competent patients.