Designing Screening Models for Mild Cognitive Impairment in Atrial Fibrillation

Aiming to improve screening of cognitive function in patients with atrial fibrillation (AF), researchers evaluated a computerized screening strategy that utilized a subset of tests from the Cambridge Neuropsychological Test Automated Batter (CANTAB). According to the study’s lead author Jia Wang, the CANTAB subtests were a “feasible and effective” strategy for screening patients with AF for mild cognitive impairment (MCI). Their experience was published in Computational and Mathematical Methods in Medicine.

The randomized trial included 105 patients who performed the Multitasking Test (MTT), Rapid Visual Information Processing (RVP), and Paired Associates Learning (PAL) tests from the CANTAB. Traditional neuropsychological tests were also performed for reference data. Logistic regression was used to establish various screening models with different CANTAB subtests, which were then further developed using the Akaike Information Criterion (AIC).

During the study, 58 (55%) of the patients were diagnosed with MCI. The investigators calculated the sensitivity and specificity of the various tests and found that “MTT alone had reasonable sensitivity (82.8%) and specificity (74.5%) for MCI screening, while RVP (sensitivity 72.4%, specificity 70.2%) and PAL (sensitivity 70.7%, specificity 57.4%) were less effective.” The authors’ additional analysis suggested that combining the MTT and RVP tests—and excluding the PAL test—increased specificity to 85.8%. Lastly, adding education modules to the models did improve MCI screening results.