Abstract TP308: Predictive model for Stroke Mimics during Code Stroke Evaluation

Abstract

Introduction: A common approach at differentiating acute ischemic stroke (AIS) from stroke mimics (SM) is medical history and clinical presentation. However, combination of certain clinical symptoms and signs are more associated with SM than with AIS. Identifying these clinical features during “Code Stroke “would help clinicians to raise high suspicion to identify SM and thus prevent futile IV thrombolysis. Hypothesis: A predictive model will identify a combination of signs and symptoms associated with SM. Methods: A retrospective cohort over a 4-year period was used to construct a predictive model with recursive partitioning. Results: During the study period, out of 1467 “Code Stroke” activations, 508 patients were eligible for IV thrombolysis. After initial analysis of 43 “Code Stroke” clinical features, we identified 11 signs and symptoms that were significantly different in AIS and SM patients: age, systolic blood pressure, atrial fibrillation (AF), being on antithrombotic at presentation, similar admissions in the past, seizure at onset, headache at presentation, encephalopathy, focal neurological symptoms, NIHSS and old stroke on head CT. Using a predictive model analysis, headache at presentation, absence of focal symptoms, and seizure at onset significantly predicted of SM. A high predictive value of 92%, (CI: 88-95%) for SM included: i) headache at presentation, ii) no headache without focal symptoms, iii) no headache with at least one focal symptom and seizure at onset. While a low SM predictive value of 29% (CI: 23-35%) included no headache at presentation with at least one focal symptom and no seizure at onset. Conclusion: Our study found that among other symptoms, headache, absence of focal symptoms, and seizure at onset have strongest association with SM during “Code Stroke”. Study results further need to be validated in prospective cohort.