Related Experiment Video
Updated: Sep 15, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Blood Biomarker-Based Machine Learning Model for Predicting Cognitive Impairment in Stroke Patients
Yue Zhao1, Daojun Zeng2, Hong Yu2
1Department of Anesthesiology, The Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan Province, China; Anesthesiology and Critical Care Medicine Key Laboratory of Luzhou, Southwest Medical University, Luzhou, Sichuan Province, China; Department of Thoracic Surgery, The Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan Province, China.
Machine learning models accurately predict cognitive impairment (CI) risk in stroke patients. Logistic regression showed the best performance, identifying key factors for early intervention and improved outcomes.
Area of Science:
- Neurology
- Data Science
- Biostatistics
Background:
- Cognitive impairment (CI) is a frequent complication in stroke survivors, negatively impacting prognosis.
- Early and precise identification of stroke patients at high risk for CI is essential for timely management.
- This study developed machine learning (ML) models to predict CI risk in stroke patients.
Purpose of the Study:
- To develop and evaluate ML models for predicting cognitive impairment risk in stroke patients.
- To identify key clinical and demographic factors associated with CI post-stroke.
- To enable early intervention strategies by accurately assessing CI risk.
Main Methods:
- Utilized data from the China Health and Retirement Longitudinal Study (2011-2018) for 2505 stroke patients.
- Employed Lasso regression and Boruta algorithm for feature selection, identifying ten key variables.
- Developed and compared ten ML algorithms, including logistic regression, XGBoost, SVM, and Random Forest, assessing performance via AUC and decision curve analysis.
Main Results:
- The logistic regression model achieved the highest predictive accuracy with an Area Under the Curve (AUC) of 0.824 (95% CI: 0.794-0.854).
- Decision curve analysis confirmed the logistic regression model's superior clinical utility and net benefit.
- SHapley Additive exPlanations identified education, age, pain, depression, HbA1c, and BUN as significant predictors of CI.
Conclusions:
- ML-based prediction models offer high accuracy for assessing CI risk in stroke patients.
- The developed models facilitate early identification of at-risk individuals, paving the way for timely interventions.
- Accurate CI risk prediction can significantly improve patient outcomes following a stroke.
