Machine learning-based prediction model for cognitive frailty in elderly patients with ischaemic stroke: a prospective cohort study - Summary - MDSpire
Advertisement
Machine learning-based prediction model for cognitive frailty in elderly patients with ischaemic stroke: a prospective cohort study
To develop and internally validate a machine learning-based model for predicting 3-month cognitive frailty risk in older patients with ischaemic stroke.
Key Findings:
SHAP analysis revealed that the discharge National Institutes of Health Stroke Scale score, age, and white matter hyperintensity burden were major contributors to model prediction.
Interpretation:
The model developed provides an interpretable method for estimating early cognitive frailty risk in older patients post-stroke.
Limitations:
The model requires external validation before clinical application.
The held-out internal test set contained only 44 cognitive frailty events, which may lead to uncertainty in classification metrics.
Conclusion:
An interpretable machine learning model was developed to estimate cognitive frailty risk using routinely available clinical variables, highlighting the need for further validation.
