Medical AIBISAP score for acute pancreatitis severity
A simple 5-point score (0 to 5) for early risk stratification in acute pancreatitis, predicting in-hospital mortality within the first 24 hours. Each criterion scores 1 point. A score of 3 or more identifies substantially higher mortality and organ-failure risk.
How to measure each input
- BUN
- Blood urea nitrogen greater than 25 mg/dL scores 1. If your laboratory reports serum urea in mmol/L, BUN 25 mg/dL corresponds to about 8.9 mmol/L of urea (urea mmol/L = BUN mg/dL x 0.357).
- Impaired mental status
- Any new reduction in conscious level, conventionally a Glasgow Coma Scale below 15, including disorientation, lethargy, somnolence, stupor, or coma.
- SIRS
- Present when two or more of the four SIRS criteria are met (temperature, heart rate, respiratory rate or PaCO2, white cell count). Reassess across the first 24 hours, as SIRS can evolve.
- Pleural effusion
- Detected on chest radiograph or CT. Combined with age over 60 and the other variables, it reflects more severe, systemic disease.
Interpretation
| Band | Meaning |
|---|---|
| 0 to 2, lower risk | In the derivation cohort, in-hospital mortality was below 1% for patients with a BISAP score under 2 and remained low through a score of 2. Most patients in this band have mild, self-limiting disease, though clinical reassessment over the first 48 hours is still needed. |
| 3 to 5, higher risk | A score of 3 or more is associated with substantially higher in-hospital mortality (in the order of 5 to 20%, rising to roughly 22% at a score of 5) and a higher rate of organ failure. Consider high-dependency or intensive monitoring, aggressive supportive care, and senior review. |
Pitfalls, exclusions and caveats
- BISAP predicts mortality and severity but is not a substitute for serial clinical assessment; deterioration can occur despite an initially low score.
- It uses BUN in mg/dL. Confusing BUN with serum urea in mmol/L will misclassify the first criterion.
- Sensitivity at the score >= 3 cutoff is modest (around 38% in validation), so a low score does not exclude severe disease; specificity is high (over 90%).
- The score does not include haematocrit, CRP, or contrast-enhanced CT findings used by other systems, and it does not replace the revised Atlanta classification for defining severity.
- Derived and validated in adult acute pancreatitis; do not extrapolate to chronic pancreatitis or paediatric patients.
1 point each: BUN > 25 mg/dL + Impaired mental status (GCS < 15) + SIRS present (>= 2 SIRS criteria) + Age > 60 years + Pleural effusion on imaging. Total 0 to 5.The BISAP score was derived by Wu et al. (2008). This implementation is an educational tool and is not affiliated with the original authors or any guideline body.
Frequently asked
What BISAP score indicates severe acute pancreatitis?
A score of 3 or more identifies patients at substantially higher risk of in-hospital mortality (roughly 5 to 20%, up to about 22% at a score of 5) and organ failure. Scores under 2 carry mortality below 1% in the derivation cohort.
Is BUN entered in mg/dL or mmol/L?
The BISAP criterion is BUN greater than 25 mg/dL. If your laboratory reports serum urea in mmol/L, that threshold is about 8.9 mmol/L of urea (urea mmol/L = BUN mg/dL x 0.357).
How does BISAP compare with Ranson's and APACHE-II?
In Papachristou et al's validation, BISAP performed comparably to Ranson's, APACHE-II, and CTSI for predicting severity and mortality, with the advantage that all five variables are simple bedside measures available within 24 hours.
A score is a start. The product is asked.
Calculators give a number. When the patient in front of you needs the reasoning behind it, with the sources, the product is what does the looking-up.
Medical AI returns evidence-grounded answers backed by real citations. It is a reference tool, and these terms describe how it should and should not be used.
01 Educational purpose
Medical AI is an information and reference tool intended for educational use only. The answers it returns are not medical advice, diagnosis, or treatment. Always consult a qualified doctor or healthcare professional with any question concerning a medical condition.
02 Professional use
Medical AI is designed for use by practicing clinicians. It is not intended for direct patient use and is not a substitute for professional clinical judgment. Apply your own training and current guidelines to every decision an answer informs.
03 Privacy and data
We do not collect, store, or process personally identifiable patient information (PHI or PII). Do not enter names, dates of birth, medical record numbers, or any other patient identifiers into the composer.
04 Information currency
Medical knowledge evolves rapidly. Citations carry their publication date, so consult the primary source and the most recent clinical guideline before acting on anything material.