Why the study?
Hospital readmission among stroke survivors is frequent, especially in contexts of social vulnerability, compromising recovery and overburdening health services.
Population
Socially vulnerable stroke survivors
Design
Predictive modeling study using machine learning algorithms
Key result
A decision tree model predicted hospital readmission among socially vulnerable stroke survivors with up to 92.45% accuracy, identifying falls, time since stroke, caregiver presence, and sleep difficulty as key predictors.
Authors
Loading...
May inform targeted interventions in vulnerable stroke survivors; leaves open prospective validation before clinical use.
Cross-Sectional (n=267)
Yes
Machine learning models, particularly decision trees, can accurately predict hospital readmission in socially vulnerable stroke survivors, identifying key risk factors such as falls and time since stroke to guide preventive strategies.
Silva et al. (2025) conducted a cross-sectional in Stroke survivors in social vulnerability (n=267). Risk factors for hospital readmission (e.g., falls, complications, lack of caregiver) vs. Patients without these risk factors was evaluated on Hospital readmission within one year after stroke. A decision tree model predicted hospital readmission among socially vulnerable stroke survivors with up to 92.45% accuracy, identifying falls, time since stroke, caregiver presence, and sleep difficulty as key predictors.