Related Experiment Video
Updated: Mar 15, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Utility of the Montreal Cognitive Assessment as a Screening Test for Neurocognitive Dysfunction in Adults with Sickle
Cody Cichowitz1, Patrick C Carroll1, John J Strouse1
1From the Departments of Psychiatry and Behavioral Medicine, Pediatrics, and Medicine, Johns Hopkins School of Medicine, Baltimore, Maryland, and the Division of Hematology, Duke University School of Medicine, Durham, North Carolina.
Objectives:
Neurocognitive dysfunction is an important complication of sickle cell disease (SCD), but little is published on the utility of screening tests for cognitive impairment in people with the disease. The purpose of this study was to evaluate the Montreal Cognitive Assessment (MoCA) as a screening tool and identify predictors of MoCA performance in adults with sickle cell disease.
Methods:
We conducted a retrospective, cross-sectional study of the first 100 adult patients with SCD who completed the MoCA as part of routine clinical care at the Johns Hopkins Sickle Cell Center for Adults. We abstracted demographic, laboratory, and clinical data from each participant's electronic medical record up to the date that the MoCA was administered. The factorial validity of each MoCA domain was analyzed using standard psychometric statistics. We evaluated the abstracted data for associations with the composite MoCA score and looked for independent predictors of performance using multivariable regressions.
Results:
Components of the MoCA performed well in psychometric analyses and identified deficits in executive function that were described in other studies. Forty-six percent of participants fell below the cutoff for mild cognitive impairment. Increased education was an independent predictor of increased MoCA score (3.1, 95% confidence interval [CI] 1.5-4.7), whereas cerebrovascular accidents and chronic kidney disease were independent predictors of decreased score (-3.3, 95% CI -5.7 to -0.97 and -3.2, 95% CI -6.2 to -0.11, respectively). When analysis was restricted to patients with SCA, increased education (3.7, 95% CI 2.2-5.2) and a history of hydroxyurea therapy (2.0, 95% CI -0.022 to 4.0) were independent predictors of a higher score, whereas chronic kidney disease (-3.3, 95% CI -6.4 to -0.24) and increased aspartate transaminase (-0.045, 95% CI -0.089 to -0.0010) were independent predictors of a decreased score.
Conclusions:
The MoCA showed promise by identifying important cognitive deficits and associations with chronic complications and therapy.
