Related Experiment Video
Updated: Nov 7, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Development and Validation of a Nomogram Based on Motoric Cognitive Risk Syndrome for Cognitive Impairment
Yong Liu1, Kai Wei1, Xinyi Cao1,2
1Shanghai Key Laboratory of Psychotic Disorders, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Objective:
To develop and validate a prediction nomogram based on motoric cognitive risk syndrome for cognitive impairment in healthy older adults.
Methods:
Using two longitudinal cohorts of participants (aged ≥ 60 years) with 4-year follow-up, we developed (n = 1,177) and validated (n = 2,076) a prediction nomogram. LASSO (least absolute shrinkage and selection operator) regression model and multivariable Cox regression analysis were used for variable selection and for developing the prediction model, respectively. The performance of the nomogram was assessed with respect to its calibration, discrimination, and clinical usefulness.
Results:
The individualized prediction nomogram was assessed based on the following: motoric cognitive risk syndrome, education, gender, baseline cognition, and age. The model showed good discrimination [Harrell's concordance index (C-index) of 0.814; 95% confidence interval, 0.782-0.835] and good calibration. Comparable results were also seen in the validation cohort, which includes good discrimination (C-index, 0.772; 95% confidence interval, 0.776-0.818) and good calibration. Decision curve analysis demonstrated that the prediction nomogram was clinically useful.
Conclusion:
This prediction nomogram provides a practical tool with all necessary predictors, which are accessible to practitioners. It can be used to estimate the risk of cognitive impairment in healthy older adults.
