Accuracy of a Self-Administered Online Cognitive Assessment in Detecting Amnestic Mild Cognitive Impairment

Abstract

Objectives: Our aim was to validate the online Brain Health Assessment (BHA) for detection of amnestic mild cognitive impairment (aMCI) compared to gold-standard neuropsychological assessment. We compared the diagnostic accuracy of the BHA to the Montreal Cognitive Assessment (MoCA).

Methods: Using a cross-sectional design, community-dwelling older adults completed a neuropsychological assessment, were diagnosed as normal cognition (NC) or aMCI, and completed the BHA and MoCA. Both logistic regression (LR) and penalized logistic regression (PLR) analyses determined BHA and demographic variables predicting aMCI; MoCA variables were similarly modeled. Diagnostic accuracy was compared using area under the receiver operating characteristic curve (ROC AUC) analyses.

Results: Ninety-one participants met inclusion criteria (51 aMCI, 40 NC). PLR modeling for the BHA indicated Face-Name Association, Spatial Working Memory, and age-predicted aMCI (ROC AUC = 0.76; 95% confidence interval [CI]: 0.66-0.86). Optimal cut-points resulted in 21% classified as aMCI (positive), 23% negative, and 56% inconclusive. For the MoCA, digits, abstraction, delayed recall, orientation, and age predicted aMCI (ROC AUC = 0.71; 95% CI: 0.61-0.82). Optimal cut-points resulted in 22% classified positive, 8% negative, and 70% inconclusive (LR results presented within). The BHA model classified fewer participants into the inconclusive category and more as negative for aMCI, compared to the MoCA model (Stuart-Maxwell p = .004).

Discussion: The self-administered BHA provides similar detection of aMCI as a clinician-administered screener (MoCA), with fewer participants classified inconclusively. The BHA has the potential to save practitioners time and decrease unnecessary referrals for a comprehensive assessment to determine the presence of aMCI.

Keywords: Cognitive screening; Diagnostic accuracy; Logistic regression; Validity; eHealth.

Figure 1.

Flow diagram of participant classification by the Brain Health Assessment (index) and Neuropsychological Assessment (reference). MCI = mild cognitive impairment; aMCI = amnestic mild cognitive impairment.

Figure 2.

ROC curves for final BHA and MoCA PLR models. The ROC curves for the BHA (solid line) and MoCA (dashed line) PLR models with the single cut-point (solid triangle for BHA; open triangle for MoCA) and two cut-points (solid circles for BHA; open circles for MoCA). MoCA = Montreal Cognitive Assessment; BHA = Brain Health Assessment; PLR = penalized logistic regression; ROC = receiver operating characteristic.