North American Stroke Triage Score Evaluation Data

Daria S. Nicke's research evaluates the Japan Urgent Stroke Triage (JUST) score for differentiating ischemic and hemorrhagic strokes in a North American population. The dataset contains variables used in logistic regression models, including neurological symptoms and patient demographics. The study was published on figshare in April 2026.

Use Cases

• Validate the JUST-7 score's predictive power (AUC 0.68) for stroke type classification using its core variables.
• Build a logistic regression model to predict hemorrhagic stroke using features like altered mental status (OR 1.88) and systolic blood pressure ≥165mmHg (OR 2.32).
• Analyze the impact of added covariates like sex, numbness, comorbidities, and AHA guidelines on model AUC (improved to 0.72).
• Investigate the association between nausea and vomiting (OR 2.90) and the likelihood of hemorrhagic stroke diagnosis.

Strengths

• Data is derived from a two-state cohort of acute stroke patients transported by EMS, providing real-world clinical context.
• Model performance is quantified with specific AUC metrics (0.68 to 0.72) and odds ratios with confidence intervals.

Limitations

• The dataset is very small at 14.8 KB, indicating it likely contains summary results or a single table, not raw patient records.
• Specific row count, column names, and individual patient data are unknown, limiting direct analytical use.
• Geographic coverage is limited to a North American population from two unspecified states, which may not generalize globally.

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

Last updated April 2026, indicating recent analysis.

Geography

North American population (two-state cohort).