A Rapid, Mobile Neurocognitive Screening Test to Aid in Identifying Cognitive Impairment and Dementia (BrainCheck): Cohort Study

Abstract

Background The US population over the age of 65 is expected to double by the year 2050. Concordantly, the incidence of dementia is projected to increase. The subclinical stage of dementia begins years before signs and symptoms appear. Early detection of cognitive impairment and/or cognitive decline may allow for interventions to slow its progression. Furthermore, early detection may allow for implementation of care plans that may affect the quality of life of those affected and their caregivers. Objective We sought to determine the accuracy and validity of BrainCheck Memory as a diagnostic aid for age-related cognitive impairment, as compared against physician diagnosis and other commonly used neurocognitive screening tests, including the Saint Louis University Mental Status (SLUMS) exam, the Mini-Mental State Examination (MMSE), and the Montreal Cognitive Assessment (MoCA). Methods We tested 583 volunteers over the age of 49 from various community centers and living facilities in Houston, Texas. The volunteers were divided into five cohorts: a normative population and four comparison groups for the SLUMS exam, the MMSE, the MoCA, and physician diagnosis. Each comparison group completed their respective assessment and BrainCheck Memory. Results A total of 398 subjects were included in the normative population. A total of 84 participants were in the SLUMS exam cohort, 51 in the MMSE cohort, 35 in the MoCA cohort, and 18 in the physician cohort. BrainCheck Memory assessments were significantly correlated to the SLUMS exam, with coefficients ranging from .5 to .7. Correlation coefficients for the MMSE and BrainCheck and the MoCA and BrainCheck were also significant. Of the 18 subjects evaluated by a physician, 9 (50%) were healthy, 6 (33%) were moderately impaired, and 3 (17%) were severely impaired. A significant difference was found between the severely and moderately impaired subjects and the healthy subjects ( P =.02). We derived a BrainCheck Memory composite score that showed stronger correlations with the standard assessments as compared to the individual BrainCheck assessments. Receiver operating characteristic (ROC) curve analysis of this composite score found a sensitivity of 81% and a specificity of 94%. Conclusions BrainCheck Memory provides a sensitive and specific metric for age-related cognitive impairment in older adults, with the advantages of a mobile, digital, and easy-to-use test. Trial Registration ClinicalTrials.gov NCT03608722; https://clinicaltrials.gov/ct2/show/NCT03608722 (Archived by WebCite at http://www.webcitation.org/76JLoYUGf)

Risk Score Stratification of Alzheimer’s Disease and Mild Cognitive Impairment using Deep Learning

“…Many studies have previously examined neurocognitive tests and identified a few top neurocognitive classifiers using non-machine learning methods, but they are not discussed here [9,[11][12][13] (see reviews by Abd Razak In sum, our results are comparable or compared favorably with previous studies although comparisons were not made on the same datasets. Our study is novel in that we employed a nonsupervised learning (as opposed to supervised learning) method, applied to a large and multi-center ADNI dataset with commonly used measures.…”

“…A large array of neurocognitive tests are currently used to detect cognitive impairment and classify amongst normal controls (CN), EMCI, LMCI and AD [7][8]. Many studies have identified a few top classifiers using logistic regression and machine learning methods [9][10][11][12][13][14][15][16][17][18]. Some studies have also used MRI and genetic data in conjunction with neurocognitive measures for classification [19][20].…”

Validation of a Computerized Cognitive Test Battery for Detection of Dementia and Mild Cognitive Impairment

“…Prior studies have shown that some computerized cognitive tests demonstrate high accuracy in differentiating dementia patients from healthy participants, but do not have adequate psychometrics to distinguish MCI from dementia [19][20][21][22] . Ideally, computerized cognitive tests would aim to be more rapid and maximize accessibility to This study evaluated BrainCheck, a computerized cognitive test battery previously validated for its diagnostic accuracy for the detection of concussion [24] and dementia-related cognitive decline [25] . BrainCheck is portable, allows for self and remote administration, and can be reimbursed by insurance plans in the US.…”

“…p-values are adjusted with the Benjamini-Hochberg method. The BrainCheck Overall Score is a composite of all individual assessments within the BrainCheck battery, representing overall performance (See details in Method 2.4).Using an existing normative population database, partly compiled from controls in previous studies[24,25] , the Overall Score was adjusted for age and the device used to generate the normalized BrainCheck Overall Scores. The normalized BrainCheck Overall Scores differed significantly among these three groups ( p <0.05).…”

Implementing Remote Memory Clinics to Enhance Clinical Care During and After COVID-19

“…BrainCheck Memory ( ) is available on any Apple device and has been modified to detect age-related cognitive decline by measuring immediate and delayed recall, Trail Making Tests A and B, Stroop Test and Digit Symbol Substitution Task. In a recent large cohort study ( 54 ) in participants aged >49 years, BrainCheck Memory was administered by research staff, with scores significantly correlating with Saint Louis University Mental Status exam scores, Mini-Mental State Examination (MMSE) scores and MoCA scores. BrainCheck Memory was able to differentiate healthy controls from cognitively impaired participants ( p =.02) and BrainCheck Memory composite scores were found to have a sensitivity of 81% and specificity of 94%.…”