A Comparison of Cross-Sectional and Longitudinal Methods of Defining Objective Subtle Cognitive Decline in Preclinical Alzheimer's Disease Based on Cogstate One Card Learning Accuracy Performance

Abstract

Background: Longitudinal, but not cross-sectional, cognitive testing is one option proposed to define transitional cognitive decline for individuals on the Alzheimer's disease continuum.

Objective: Compare diagnostic accuracy of cross-sectional subtle objective cognitive impairment (sOBJ) and longitudinal objective decline (ΔOBJ) over 30 months for identifying 1) cognitively unimpaired participants with preclinical Alzheimer's disease defined by elevated brain amyloid and tau (A+T+) and 2) incident mild cognitive impairment (MCI) based on Cogstate One Card Learning (OCL) accuracy performance.

Methods: Mayo Clinic Study of Aging cognitively unimpaired participants aged 50 + with amyloid and tau PET scans (n = 311) comprised the biomarker-defined sample. A case-control sample of participants aged 65 + remaining cognitively unimpaired for at least 30 months included 64 who subsequently developed MCI (incident MCI cases) and 184 controls, risk-set matched by age, sex, education, and visit number. sOBJ was assessed by OCL z-scores. ΔOBJ was assessed using within subjects' standard deviation and annualized change from linear regression or linear mixed effects (LME) models. Concordance measures Area Under the ROC Curve (AUC) or C-statistic and odds ratios (OR) from conditional logistic regression models were derived. sOBJ and ΔOBJ were modeled jointly to compare methods.

Results: sOBJ and ΔOBJ-LME methods differentiated A+T+ from A-T- (AUC = 0.64, 0.69) and controls from incident MCI (C-statistic = 0.59, 0.69) better than chance; other ΔOBJ methods did not. ΔOBJ-LME improved prediction of future MCI over baseline sOBJ (p = 0.003) but not over 30-month sOBJ (p = 0.09).

Conclusion: Longitudinal decline did not offer substantial benefit over cross-sectional assessment in detecting preclinical Alzheimer's disease or incident MCI.

Keywords: Amyloid; biomarker; cognigram; memory; neuropsychology; reliable change index; sensitivity and specificity; tau; transitional cognitive decline; validity.

Figure 1.

Study definitions: Methods of defining subtle cognitive decline.

Figure 2.. Sample timeline and matching for cognitively unimpaired, incident MCI cases and stable controls.

Note: Visualize the timing of events in a risk-set matched design with a run-in period. Eligible subjects had a run-in period of 30 months of CBB assessments (see ‘a’) which was used to derive the metrics of interest sOBJ and ΔOBJ. Incident MCI cases were those who went on to receive a diagnosis of MCI (yellow dot) after the run in period and were matched to controls (blue X) by age, sex, education, and year of initial CBB to account for potential temporal effects. To ensure equitable opportunity for development of MCI, cases were also matched to controls having at least as much time in study subsequent to the run-in period, i.e. risk-set matching (see ‘b’). We used a 3-to-1 control-to-case matching ratio. To compare the relationship between each metric of interest and incidence of MCI while accounting for a matched-design, conditional logistic regression (CLR) models were fit and stratified by matched-sets.

Figure 3.. Boxplots of One Card Learning accuracy performance across methods of defining subtle cognitive decline and biomarker groups.

Note: Box plots representing performances on OCL accuracy separately by biomarker defined groups show the interquartile range (box), median (horizontal solid line within each box) and the extent of outlier performances (vertical lines extending above and below each box) in each of the sOBJ and ∆OBJ methods. Dashed line (---) denotes the conventional cut-off used (≤ −1 z score for sOBJ and ∆OBJ-WSD; <10^th percentile slope for ∆OBJ-LR and ∆OBJ-LME methods). Individuals in all biomarker based groups with performances below this line are identified as decliners based on these cut-offs. A = amyloid, T = tau, sOBJ = subtle objective cognitive impairment at baseline based on OCL accuracy age-corrected z-score derived from Cogstate norms. ∆OBJ = subtle objective cognitive decline since baseline assessment. WSD = within subjects standard deviation z-score based on Cogstate norms. LR = Linear regression model; <10%ile slope is equivalent to a < −0.0199 annualized change on OCL accuracy raw score (arcsine transformed). LME = linear mixed effects model; <10%ile slope is equivalent to a < 0.0162 annualized change on OCL accuracy raw score (arcsine transformed). <10%ile slope cutoffs were derived from the cognitively unimpaired reference sample.