Comparison of the predictive accuracy of multiple definitions of cognitive impairment for incident dementia: a 20-year follow-up of the Whitehall II cohort study

Background: Studies generally use cognitive assessment done at one timepoint to define cognitive impairment in order to examine conversion to dementia. Our objective was to examine the predictive accuracy and conversion rate of seven alternate definitions of cognitive impairment for dementia. Methods: In this prospective study, we included participants from the Whitehall II cohort study who were assessed for cognitive impairment in 2007–09 and were followed up for clinically diagnosed dementia. Algorithms based on poor cognitive performance (defined using age-specific and sex-specific thresholds, and subsequently thresholds by education or occupation levels) and objective cognitive decline (using data from cognitive assessments in 1997–99, 2002–04, and 2007–09) were used to generate seven alternate definitions of cognitive impairment. We compared predictive accuracy using Royston's R2, the Akaike information criterion (AIC), sensitivity, specificity, and Harrell's C-statistic. Findings: 5687 participants, with a mean age of 65·7 years (SD 5·9) in 2007–09, were included and followed up for a median of 10·5 years (IQR 10·1–10·9). Over follow-up, 270 (4·7%) participants were clinically diagnosed with dementia. Cognitive impairment defined using both cognitive performance and decline had higher hazard ratios (from 5·08 [95% CI 3·82–6·76] to 5·48 [4·13–7·26]) for dementia than did definitions based on cognitive performance alone (from 3·25 [2·52–4·17] to 3·39 [2·64–4·36]) and cognitive decline alone (3·01 [2·37–3·82]). However, all definitions had poor predictive performance (C-statistic ranged from 0·591 [0·565–0·616] to 0·631 [0·601–0·660]), primarily due to low sensitivity (21·6–48·4%). A predictive model containing age, sex, and education without measures of cognitive impairment had better predictive performance (C-statistic 0·783 [0·758–0·809], sensitivity 74·2%, specificity 72·2%) than all seven definitions of cognitive impairment (all p<0·0001). Interpretation: These findings suggest that cognitive impairment in early old age might not be useful for dementia prediction, even when it is defined using longitudinal data on cognitive decline and thresholds of poor cognitive performance additionally defined by education or occupation. Funding: National Institutes of Health, UK Medical Research Council.