Related Experiment Video
Updated: Aug 10, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Improving the screening power of the cognitive abilities screening instrument, Chinese version
Rung-Ching Tsai1, Ker-Neng Lin, Kuan-Ying Wu
1Department of Mathematics, National Taiwan Normal University, Taipei, Taiwan, ROC. rtsai@math.ntnu.edu.tw
Abstract:
The purpose of this study was to find means to increase the power of the Cognitive Abilities Screening Instrument, Chinese version (CASI C-2.0) in the screening of dementia. In assessing the performance of the CASI in dementia screening, it is a common practice to determine a cutoff score for the total CASI score and report the respective sensitivity and specificity. In this paper, we showed that an alternative scoring system, i.e., a weighted sum of the scores from the 9 domains in the CASI C-2.0, may improve its effectiveness in screening. In particular, short-term memory and orientation appeared to be the 2 most relevant domains and their combined score was shown to be more effective than the total score in screening dementia. We also showed that such a scoring system could be kept the same across examinees with different demographic backgrounds. With the weighted scoring system of the 9 domains for patients from the targeted population, we hope to make the CASI a clinically more powerful tool in screening dementia.

