North American Stroke Patient Data for Triage Score Evaluation

A research paper evaluates the Japan Urgent Stroke Triage (JUST) score for differentiating ischemic from hemorrhagic strokes in a North American cohort. The study uses logistic regression on patient variables transported by emergency medical services. The work was authored by Daria S. Nicke and published in April 2026.

Use Cases

• Validate the JUST-7 score's predictive power (AUC 0.68) for stroke type classification in a new geographic population.
• Analyze odds ratios for specific symptoms like altered mental status (OR 1.88) or systolic blood pressure ≥165mmHg (OR 2.32) as hemorrhagic stroke indicators.
• Compare model performance between the original JUST variables (AUC 0.70) and an expanded model including sex, numbness, and comorbidities (AUC 0.72).
• Identify key clinical features from the study's logistic regression for building a simplified North American stroke differentiation tool.

Strengths

• Provides specific model performance metrics, including AUC scores of 0.68, 0.70, and 0.72 for different variable sets.
• Reports concrete odds ratios with 95% confidence intervals for significant predictors like nausea and vomiting (OR 2.90).

Limitations

• Dataset scope is limited to the analysis presented in a single 143 KB PDF file, containing no raw patient records.
• The underlying patient cohort size and specific row count for the logistic regression are not disclosed.

Provenance

Source

figshare, authored by Daria S. Nicke.

Collection Method

Analysis of a two-state cohort of adult acute stroke patients transported by emergency medical services.

Time Range

null

Freshness

null

Geography

North American population (specific two-state cohort within the United States).