Related Experiment Video
Updated: May 11, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Detection of mild cognitive impairment and early stage dementia with an audio-recorded cognitive scale
Margaret C Sewell1, Xiaodong Luo, Judith Neugroschl
1The Alzheimer's Disease Research Center, Icahn School of Medicine at Mount Sinai, New York, New York 10029, USA. margaret.sewell@mssm.edu
Background:
Physicians often miss diagnosis of mild cognitive impairment (MCI) or early dementia and screening measures can be insensitive to very mild impairments. Other cognitive assessments may take too much time or be frustrating to seniors. This study examined the ability of an audio-recorded scale, developed in Australia, to detect MCI or mild Alzheimer's disease (AD) and compared cognitive domain-specific performance on the audio-recorded scale to in-person battery and common cognitive screens.
Method:
Seventy-six patients from the Mount Sinai Alzheimer's Disease Research Center were recruited. Patients were aged 75 years or older, with clinical diagnosis of AD or MCI (n = 51) or normal control (n = 25). Participants underwent in-person neuropsychological testing followed by testing with the audio-recorded cognitive screen (ARCS).
Results:
ARCS provided better discrimination between normal and impaired elderly individuals than either the Mini-Mental State Examination or the clock drawing test. The in-person battery and ARCS analogous variables were significantly correlated, most in the 0.4 to 0.7 range, including verbal memory, executive function/attention, naming, and verbal fluency. The area under the curve generated from the receiver operating characteristic curves indicated high and equivalent discrimination for ARCS and the in-person battery (0.972 vs. 0.988; p = 0.23).
Conclusion:
The ARCS demonstrated better discrimination between normal controls and those with mild deficits than typical screening measures. Performance on cognitive domains within the ARCS was well correlated with the in-person battery. Completion of the ARCS was accomplished despite mild difficulty hearing the instructions even in very elderly participants, indicating that it may be a useful measure in primary care settings.
Insights
The audio-recorded cognitive screen (ARCS) effectively identifies mild cognitive impairment and early Alzheimer's disease, outperforming standard tests. This accessible tool shows promise for primary care settings.
Area of Science:
- Gerontology
- Neuroscience
- Cognitive Assessment
Background:
- Physicians frequently miss diagnoses of mild cognitive impairment (MCI) or early dementia.
- Existing screening measures can be insensitive to very mild cognitive impairments.
- Current cognitive assessments may be time-consuming or frustrating for seniors.
Purpose of the Study:
- To evaluate an audio-recorded cognitive screen (ARCS) for detecting MCI or mild Alzheimer's disease (AD).
- To compare ARCS performance across cognitive domains with in-person testing and common cognitive screens.
Main Methods:
- Seventy-six participants aged 75+ were recruited from Mount Sinai Alzheimer's Disease Research Center.
- Participants included individuals with MCI or AD (n=51) and normal controls (n=25).
- Testing involved an in-person neuropsychological battery followed by the audio-recorded cognitive screen (ARCS).
Main Results:
- ARCS demonstrated superior discrimination between normal and impaired elderly individuals compared to the Mini-Mental State Examination and clock drawing test.
- Significant correlations (0.4-0.7) were found between ARCS and in-person battery variables for verbal memory, executive function/attention, naming, and verbal fluency.
- Receiver operating characteristic curves showed high and equivalent discrimination for ARCS and the in-person battery (AUCs 0.972 vs. 0.988).
Conclusions:
- ARCS effectively discriminates between normal controls and individuals with mild cognitive deficits, surpassing typical screening measures.
- Cognitive domain performance on ARCS strongly correlates with results from comprehensive in-person assessments.
- ARCS is a potentially valuable primary care tool, usable even by very elderly participants with mild hearing difficulties.
More Related Videos
Related Concept Videos
Dementia
The progression of dementia is generally gradual.
Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ and tau...

