Related Experiment Video
Updated: Jun 10, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
A preliminary study of the Six-Item Screener in detecting cognitive impairment
Mei-Rong Chen1, Qi-Hao Guo, Xin-Yi Cao
1Department of Neurology, People's Hospital of Putuo District, Shanghai, China.
Objective:
The present retrospective study was to explore the clinical value of Six-Item Screener (SIS), which is constituted by 6 items from mini-mental status examination (MMSE), to identify cognitive impairment.
Methods:
A total number of 1976 patients aged over 50 years, from the Memory Clinic of Huashan Hospital were employed in a battery of neuropsychological tests including MMSE. Subjects with severe conditions, unable to cooperate, or having been previously enrolled, were excluded from this study. The employed subjects were divided into 3 groups: subjective memory complaints (SMCs) (475 cases), patients with mild cognitive impairment (MCI) (440 cases), and patients with Alzheimer's disease (AD) (1061 cases, including 555 mild, 339 moderate, and 167 severe). A total score of MMSE and a score of SIS composed of date, month, year, three-word delayed recall from MMSE were calculated. Data were analyzed based on educational background.
Results:
The cut-off of SIS score was <2 for illiterate, <3 for elementary, and <4 for junior high school or above. The sensitivity and specificity of SIS for detecting mild AD were 88.5% and 78.3%, respectively, with an overall accuracy of 83.8%, while for detecting MCI, the sensitivity and specificity were 34.3% and 90.1%, respectively, with an overall accuracy of 63.2%.
Conclusion:
SIS is an effective and reliable instrument for dementia detection in outpatient department. However, it has limited value for MCI identification.
