FACEmemory®, an innovative online platform for episodic memory pre-screening: findings from the first 3,000 participants

Background: The FACEmemory® online platform comprises a novel, self-administered memory test with embedded voice recognition technology and a questionnaire with relevant sociodemographic and medical/family history data. This is the first study about a completely self-administered memory test with voice recognition, pre-tested in a memory clinic, offered freely worldwide on a website platform. The aims of this study are to investigate the demographic and clinical variables associated with FACEmemory total score, and to identify differentiable patterns of memory performance among the first 3,000 individuals who completed the FACEmemory. Methods: A marketing campaign was carried out to make FACEmemory accessible worldwide to individuals whose native language was Spanish or Catalan. Data from the first 3,000 subjects over 18 years old who completed the FACEmemory were analysed. Descriptive analyses were applied to demographic, FACEmemory scores, and medical/family history variables reported in a questionnaire; t-test and chi-square analyses were used to compare participants with preserved (>31 points) versus impaired performance (<32) on total FACEmemory; and multiple linear regression was used to identify variables that modulate FACEmemory performance. Finally, Machine Learning techniques were applied to identify differentiable patterns of memory performance. Results: The study sample had a mean age of 50.57 years and 13.65 years of schooling. 64.1% were women and most (82.1%) participants reported memory complaints that worried them. The group with impaired FACEmemory performance (20.4%) was older, had fewer years of formal education and a higher prevalence of hypertension, diabetes mellitus, dyslipidemia, and family history of a neurodegenerative disease compared with the group with preserved FACEmemory performance. Multiple regression analysis showed that age, schooling, sex, country and completion of the questionnaire were statistically associated with FACEmemory total score. Finally, Machine Learning techniques identified 4 patterns of FACEmemory performance: normal, dysexecutive, storage and completely impaired. Conclusions: FACEmemory is a promising tool for the pre-screening of people with subjective memory complaints in the community in order to identify those with objective memory deficits and raise awareness about cognitive decline. The FACEmemory website platform is an opportunity to facilitate a free, online and self-administered episodic memory assessment to Spanish or Catalan speaking individuals worldwide, and potentially extensible to other languages.