Volume 10,Issue 7
Objective: To evaluate the predictive value of Modified Early Warning Score (MEWS) for neurological disease prognosis and identify prognostic factors. Methods: This retrospective study analyzed 768 neurological patients with MEWS ≥ 4 (June 2022–June 2024). Patients were stratified by outcomes (favorable/unfavorable). Multivariable logistic regression and ROC analysis were performed. Results: 108 cases (13.1%) had unfavorable outcomes. Significant prognostic factors included: age, TBI history, onset-to-admission time, PT, MEWS score, and MEWS ≥ 4 frequency (all P < 0.05). MEWS showed AUC = 0.749 (sensitivity 62.0%, specificity 77.4%). Conclusion: MEWS demonstrates moderate predictive value (AUC = 0.749) for neurological outcomes. Consciousness assessment limitations (56.5% impaired cases) may affect sensitivity. A specialized model incorporating pupillary reflexes and GCS is recommended for improved early warning.