Related Experiment Video
Updated: Aug 9, 2025
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.6K
Using Machine Learning to Predict Cognitive Impairment Among Middle-Aged and Older Chinese: A Longitudinal Study
Haihong Liu1,2, Xiaolei Zhang3,4, Haining Liu2,5,6
1Centre for Research in Psychology and Human Well-being, Faculty of Social Sciences and Humanities, Universiti Kebangsaan Malaysia, Bangi, Malaysia.
International Journal of Public Health
|February 17, 2023
Summary
Machine learning accurately predicts cognitive impairment in older adults, identifying key risk factors like BMI, blood pressure, and depression. This approach offers a 4-year predictive window for early intervention.
Area of Science:
- Gerontology
- Artificial Intelligence
- Neuroscience
Background:
- Cognitive impairment poses a significant public health challenge for aging populations worldwide.
- Early identification and prediction of cognitive decline are crucial for timely interventions.
Purpose of the Study:
- To evaluate the predictive capability of machine learning (ML) models for cognitive impairment in middle-aged and older adults.
- To identify key predictors associated with cognitive impairment over a 4-year period.
Main Methods:
- A longitudinal study involving 2,326 participants with baseline, 2-year, and 4-year follow-ups.
- Development and validation of a random forest ML model to predict cognitive impairment.
- Comparison of ML model performance against traditional logistic regression.
Main Results:
- Random forest models demonstrated high predictive accuracy (AUC = 0.81 at Year 2, 0.79 at Year 4) compared to logistic regression (AUC = 0.61, 0.62).
- Key predictors identified include baseline physical examination data (BMI, blood pressure), biomarkers (cholesterol), functional status, demographics (age), and emotional state (depression).
Conclusions:
- Machine learning algorithms significantly enhance the prediction of cognitive impairment in Chinese middle-aged and older adults.
- The study successfully identified critical risk markers for cognitive decline, aiding in early detection and prevention strategies.
