Related Experiment Video
Updated: Jul 16, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Identifying the most efficient items from the Mini-Mental State Examination for cognitive function assessment in
Meei-Fang Lou1, Yu-Tzu Dai, Guey-Shiun Huang
1School of Nursing, College of Medicine, National Taiwan University, Taipei, Taiwan. mfalou@ha.mc.ntu.edu.tw
Aims:
The purpose of the study was to identify the most efficient items from the Mini-Mental State Examination for assessment of cognitive function.
Background:
The Mini-Mental State Examination is the most frequently used cognitive screening instrument. However, the Mini-Mental State Examination has been criticized for insensitivity to mild cognitive dysfunction, limited memory assessment and variability in level of difficulty of the individual items.
Method:
This study used secondary data analysis. Item response theory two-parameter model was used to analyse the data from the admission assessment of mental status by the Mini-Mental State Examination for 801 patients.
Results:
By using item response analysis, 16 items were selected from the original 30-item Mini-Mental State Examination. The 16 items included mainly the measures of orientation, recall and attention and calculation. The internal consistency of the 16-item Mini-Mental State Examination was 0.84. The proposed new cut-off point for the 16-item Mini-Mental State Examination was 11. The correct classification rate was 0.94, the sensitivity was 100% and the specificity was 97.4%, when compared with the original 30-item Mini-Mental State Examination from the cut-off point of 24. This new cut-off point was determined for the purpose of over-identifying patients at risk so as to ensure early detection of and prevention from the onset of cognitive disturbance.
Conclusion:
Only a few items are needed to describe the subject's cognitive status. Using item response theory analysis, the study found that the Mini-Mental State Examination could be simplified.
Relevance To Clinical Practice:
Deleting the items with less variation makes this assessment tool not only shorter, easier to administer and less strenuous for respondents, but also enables one to maintain validity as a cognitive function test for clinical setting.
