Medical AIPERC rule pulmonary embolism calculator
Eight clinical criteria for patients in whom PE is being considered but gestalt pretest probability is already low. If none of the eight are present, PE can be excluded without D-dimer or imaging. Any single positive criterion means PERC cannot exclude PE and further work-up is required.
How to measure each input
- Gestalt pretest probability first
- PERC is only valid in patients you have already judged to be low risk on clinical gestalt (or low on a structured score). Confirm low probability before applying the eight criteria.
- Oxygen saturation
- Measure SaO2 on room air at rest. Supplemental oxygen invalidates this criterion as written.
- Heart rate
- Use the highest recorded heart rate during the encounter; transient tachycardia counts.
- Oestrogen use
- Includes combined oral contraceptives, hormone replacement therapy, and other oestrogenic hormone preparations.
- Surgery or trauma
- Surgery requiring general anaesthesia, or significant trauma, within the previous 4 weeks.
Interpretation
| Band | Meaning |
|---|---|
| 0 positive, PERC negative | In a patient whose gestalt pretest probability is already low, all eight criteria being negative excludes PE without D-dimer or imaging (the residual probability falls below the testing threshold, roughly 1 to 2%). PERC must not be applied when pretest probability is moderate or high. |
| 1 to 8 positive, PERC positive | PERC cannot exclude PE. Continue the diagnostic pathway: D-dimer if probability is low to moderate, or imaging (CT pulmonary angiography) if probability is high. A positive PERC does not diagnose PE, it simply means rule-out by PERC is not possible. |
Pitfalls, exclusions and caveats
- PERC is a rule-out tool for low-probability patients only. Applying it to moderate or high pretest probability patients can falsely reassure and miss PE.
- All eight criteria must be negative. Even one positive item means PERC fails and you proceed to D-dimer or imaging.
- PERC is not a probability score; the count of positives does not grade PE risk, it only distinguishes rule-out-eligible (0) from not (1 or more).
- It is not validated in pregnancy, and oestrogen use plus pregnancy physiology limit its use in many women of reproductive age.
- Local oxygen saturation thresholds and altitude can affect the SaO2 criterion; the rule was derived near sea level.
Count the positives among: age >= 50, heart rate >= 100, oxygen saturation < 95% on room air, unilateral leg swelling, haemoptysis, surgery or trauma within 4 weeks, prior DVT or PE, and oestrogen use. 0 positives = PERC negative (only valid when pretest probability is already low). 1 or more positives = PERC positive.The PERC rule was derived by Kline et al. (2004). This implementation is an educational tool and is not affiliated with the original authors or any guideline body.
Frequently asked
When can I use the PERC rule?
Only in a patient you have already judged to be low risk for PE on clinical gestalt. PERC then asks whether you can skip even the D-dimer. It is not a tool for moderate or high probability patients.
What does a PERC score of zero mean?
Zero positive criteria in an already low-risk patient means PE can be excluded without D-dimer or imaging, because the residual probability is below the threshold at which testing helps.
Does one positive criterion mean the patient has a PE?
No. A positive PERC only means PE cannot be ruled out by PERC alone. You continue the pathway with D-dimer or imaging, which often turns out negative.
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.