Medical AIPadua Prediction Score for VTE risk in medical inpatients
A weighted score that stratifies hospitalised medical (non-surgical) patients by venous thromboembolism risk. A total of 4 or more identifies high risk: in the derivation cohort these patients had a markedly higher VTE rate, and pharmacological thromboprophylaxis is recommended unless contraindicated. A score below 4 is low risk.
How to measure each input
- Reduced mobility
- Counts as bedrest with bathroom privileges, due to patient limitation or physician order, for at least 3 days. This 3-point item is one of the commonest drivers of a high score.
- Active cancer
- Local or distant metastases, or chemotherapy or radiotherapy within the previous 6 months.
- Previous VTE
- A prior deep vein thrombosis or pulmonary embolism. Superficial vein thrombosis does not count.
- Recent trauma or surgery
- Trauma or surgery within the previous month scores 2 points.
Interpretation
| Band | Meaning |
|---|---|
| < 4, low risk | Low risk of venous thromboembolism (about 0.3% over 90 days in the derivation cohort). Routine pharmacological thromboprophylaxis is generally not indicated; reassess if the clinical picture changes. |
| >= 4, high risk | High risk of venous thromboembolism (about 11% over 90 days without prophylaxis in the derivation cohort, versus 2.2% with prophylaxis). Pharmacological thromboprophylaxis is recommended unless contraindicated by active bleeding or high bleeding risk. |
Pitfalls, exclusions and caveats
- Designed and validated for hospitalised medical (non-surgical) patients. Use a surgical model such as Caprini for surgical patients.
- A high score indicates VTE risk only. It does not weigh bleeding risk: always balance prophylaxis against active bleeding or a high bleeding risk before prescribing.
- The threshold is a binary at 4. A score of 3 with a strong clinical concern still warrants individual judgement.
- External validations have shown variable predictive performance, so use it as a structured prompt rather than an infallible cutoff.
Add the points for each item present. Active cancer 3, previous VTE (excluding superficial vein thrombosis) 3, reduced mobility 3, known thrombophilic condition 3, recent (<= 1 month) trauma or surgery 2, age >= 70 years 1, heart and/or respiratory failure 1, acute MI or ischaemic stroke 1, acute infection or rheumatological disorder 1, obesity (BMI >= 30) 1, ongoing hormonal treatment 1. High risk if total >= 4.The Padua Prediction Score was described by Barbar et al. (2010). This implementation is an educational tool and is not affiliated with the original authors or any guideline body.
Frequently asked
What does a Padua score of 4 or more mean?
It marks high risk of venous thromboembolism in a hospitalised medical patient. In the derivation cohort, high-risk patients without prophylaxis had about an 11% VTE rate over 90 days. Pharmacological thromboprophylaxis is recommended unless bleeding risk makes it unsafe.
Is the Padua score for surgical patients?
No. It was developed and validated for hospitalised medical (non-surgical) patients. For surgical patients, use a model designed for that population, such as the Caprini score.
Does a high Padua score mean I should always start an anticoagulant?
Not automatically. The score only estimates clot risk. You must weigh it against bleeding risk: active bleeding or a high bleeding risk can outweigh the benefit, in which case mechanical prophylaxis may be preferred.
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.