Metacognition in functional cognitive disorder

Abstract

Functional cognitive disorder is common but underlying mechanisms remain poorly understood. Metacognition, an individual's ability to reflect on and monitor cognitive processes, is likely to be relevant. Local metacognition refers to an ability to estimate confidence in cognitive performance on a moment-to-moment basis, whereas global metacognition refers to long-run self-evaluations of overall performance. Using a novel protocol comprising task-based measures and hierarchical Bayesian modelling, we compared local and global metacognitive performance in individuals with functional cognitive disorder. Eighteen participants with functional cognitive disorder (mean age = 49.2 years, 10 males) were recruited to this cross-sectional study. Participants completed computerized tasks that enabled local metacognitive efficiency for perception and memory to be measured using the hierarchical meta-d' model within a signal detection theory framework. Participants also completed the Multifactorial Memory Questionnaire measuring global metacognition, and questionnaires measuring anxiety and depression. Estimates of local metacognitive efficiency were compared with those estimated from two control groups who had undergone comparable metacognitive tasks. Global metacognition scores were compared with the existing normative data. A hierarchical regression model was used to evaluate associations between global metacognition, depression and anxiety and local metacognitive efficiency, whilst simple linear regressions were used to evaluate whether affective symptomatology and local metacognitive confidence were associated with global metacognition. Participants with functional cognitive disorder had intact local metacognition for perception and memory when compared with controls, with the 95% highest density intervals for metacognitive efficiency overlapping with the two control groups in both cognitive domains. Functional cognitive disorder participants had significantly lower global metacognition scores compared with normative data; Multifactorial Memory Questionnaire-Ability subscale (t = 6.54, P < 0.0001) and Multifactorial Memory Questionnaire-Satisfaction subscale (t = 5.04, P < 0.0001). Mood scores, global metacognitive measures and metacognitive bias were not significantly associated with local metacognitive efficiency. Local metacognitive bias [β = -0.20 (SE = 0.09), q = 0.01] and higher depression scores as measured by the Patient Health Questionnaire-9 [β = -1.40 (SE = 2.56), q = 0.01] were associated with the lower global metacognition scores. We show that local metacognition is intact, whilst global metacognition is impaired, in functional cognitive disorder, suggesting a decoupling between the two metacognitive processes. In a Bayesian model, an aberrant prior (impaired global metacognition), may override bottom-up sensory input (intact local metacognition), giving rise to the subjective experience of abnormal cognitive processing. Future work should further investigate the interplay between local and global metacognition in functional cognitive disorder.

Keywords: Bayesian model; depression; functional cognitive disorder; metacognition; signal detection theory.

Graphical Abstract

Figure 1

Task structure. Participants were tested on both recognition memory (left) and perceptual discrimination (right) tasks. In both tasks, participants are: (i) presented stimuli (for 2000 ms in the recognition memory task; 3000 ms in the perceptual discrimination task); (ii) asked to make an unspeeded two-alternative forced-choice based on presented stimuli and (iii) asked to make an unspeeded metacognitive judgement on a sliding scale.

Figure 2

Local metacognition is intact in FCD. Posterior densities of the estimates of group mean metacognitive efficiency (M-ratio) are shown for perception and memory, in FCD, Control Group 1 [healthy (web)] and Control Group 2 [healthy (NYU)]. Vertical bars show the 95% highest density interval for each M-ratio and dotted vertical bars the mean. Overlap between the HDIs across panels indicates that the FCD group has a similar level of local metacognitive efficiency compared with the controls in both domains.

Figure 3

Relationship of age, affective symptomatology and metacognitive measures with global metacognition. Regression plots for FCD participants with MMQ-Ability score as the dependent variable (y-axis) and the following independent variables: (A) age; (B) GAD-7; (C) PHQ-9; (D) MMQ-Satisfaction score; (E) MMQ-Strategies score; (F) local metacognitive bias in the memory task. β coefficient values are presented along with q values that were calculated following FDR correction using the Benjamini–Hochberg method. GAD-7, Generalised Anxiety Disorder-7; PHQ-9, Patient Health Questionnaire-9; MMQ, Multifactorial Memory Questionnaire. n = 17 as one participant did not complete the MMQ questionnaire.