Related Experiment Video
Updated: Oct 16, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Performance characteristics of a two-stage dementia screen in a population sample
A S Khachaturian1, J J Gallo, J C Breitner
1Department of Mental Hygiene, School of Hygiene and Public Health, The Johns Hopkins University, 624 North Broadway, 8th Floor, Baltimore, MD 21205, USA.
Abstract:
We analyzed the performance of a two-stage screening protocol [the Modified Mini-Mental State Exam (3MS) or the Informant Questionnaire for Cognitive Decline (IQCODE), and the Dementia Questionnaire (DQ)] in a weighted stratified sample of 839 subjects from a population survey of dementia in Cache County, UT. The subjects were subsequently examined using a standardized diagnostic assessment protocol. Using the method of receiver operating characteristic (ROC) analysis, the main outcome measure was area under the ROC curve (AUC). The overall AUC estimates were 0.956 (95% confidence interval 0.943-0.968) for the 3MS/IQCODE and 0.945 (0.931-0.960) for the DQ. After adjustment for age, the efficiency of the both 3MS/IQCODE and the DQ was better for subjects with genotype epsilon4/epsilon4 at APOE, better among women, and better in those with two or more years duration of dementia. The optimal threshold for this two-stage screen yielded sensitivity and specificity estimates of 91.0% and 92.0%, respectively.
More Related Videos
06:58Highlighting and Reducing the Impact of Negative Aging Stereotypes During Older Adults' Cognitive Testing
Published on: January 24, 2020
06:23The 4 Mountains Test: A Short Test of Spatial Memory with High Sensitivity for the Diagnosis of Pre-dementia Alzheimer's Disease
Published on: October 13, 2016
Related Concept Videos
Dementia
The progression of dementia is generally gradual.
Dementia l: Introduction