Objective:

To create and internally validate a multivariable model for predicting clinically detected strokes among patients experiencing acute persistent vertigo.

Approach:

• Study Design: Retrospective analysis of 689 patients with acute persistent vertigo, including 165 clinically diagnosed strokes.
• Model Development: Candidate predictors were selected using LASSO-regularized logistic regression, followed by multivariable logistic modeling.
• Validation: Internal validation using 5-fold cross-validation and bootstrap resampling for confidence intervals.
• Performance Comparison: Model performance assessed against ABCD2, CNS, and Triage-Plus scores.

Key Findings:

• Mean age of the cohort was 60.3 years; stroke subcohort mean age was 65.0 years.
• Significant predictors of stroke included older age (OR 1.050 per 1-year increase), smoking (OR 2.147), hypertension (OR 5.452), hyperlipidemia (OR 2.621), diabetes mellitus (OR 3.918), coronary heart disease (OR 4.361), history of atrial fibrillation (OR 10.376), higher CNS score (OR 1.679 per point), and nausea/vomiting (OR 2.020).
• The model showed excellent discrimination (AUC 0.902) and good calibration.
• Performance of the model exceeded that of ABCD2 (AUC 0.642) and Triage-Plus (AUC 0.514).

Interpretation:

The multivariable prediction model may assist in risk stratification and diagnostic decision-making for acute persistent vertigo.

Limitations:

• The study was conducted at a single center, which may limit generalizability.
• Retrospective design may introduce biases in data collection.

Conclusion:

The multivariable prediction model could provide tailored stroke risk assessment for acute persistent vertigo.