Related Experiment Video
Updated: Aug 14, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
AMES: An Automated Self-Administered Scale to Detect Incipient Cognitive Decline in Primary Care Settings
Lin Huang1, Zihan Mei2, Jianfeng Ye2
1Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Abstract:
Early identification and intervention of cognitive decline could be effective to prevent progression to dementia. We developed a self-delivered cognitive screening tool, Automated Memory and Executive Screening (AMES), to assess cognitive domains including memory, language, and executive function. 189 participants with diagnoses of mild cognitive impairment (MCI, n = 43), subjective cognitive decline (SCD, n = 29), objectively-defined subtle cognitive decline (obj-SCD, n = 18), and normal controls (NC, n = 99) completed the study. AMES had good convergent validity with conventional scales, and was good to discriminate patients with MCI (area under the curve [AUC] = 0.88; sensitivity = 86%; specificity = 80%) and obj-SCD (AUC = 0.78; sensitivity = 89%; specificity = 63%) from NC. These findings support that AMES is an easy to administer and effective instrument to screen for early cognitive impairment in community-based settings.

