Medical AIHEART score chest pain calculator
A five-domain score (0 to 10) for adults presenting to the emergency department with chest pain, estimating the 6-week risk of major adverse cardiac events (MACE: death, MI, or coronary revascularisation). Low scorers can often be discharged early; high scorers warrant an early invasive strategy.
How to measure each input
- History
- A gestalt of how typical the chest pain is for ischaemia. Highly suspicious features (pressure, exertional, radiation, diaphoresis, relief with nitrates) score 2; vague or clearly atypical histories score 0.
- ECG
- Score the initial 12-lead. Significant ST-segment depression or transient elevation not attributable to LBBB, LVH, or digoxin scores 2; non-specific repolarisation changes score 1; a normal ECG scores 0.
- Age
- Three bands: under 45 scores 0, 45 to 64 scores 1, and 65 or older scores 2.
- Risk factors
- Count hypertension, hypercholesterolaemia, diabetes, current or recent smoking, a positive family history, and obesity. Three or more, or any established atherosclerotic disease (prior MI, PCI/CABG, stroke, or peripheral arterial disease), scores 2.
- Troponin
- Use the initial troponin against your assay's upper reference limit: at or below the limit scores 0, 1 to 3 times scores 1, and above 3 times scores 2. Pathways then add serial sampling.
Interpretation
| Band | Meaning |
|---|---|
| 0 to 3, low risk | Low short-term MACE risk (roughly 1.7% at 6 weeks). Early discharge is reasonable in many pathways, ideally with serial troponins per local protocol before disposition. |
| 4 to 6, moderate risk | Intermediate MACE risk (around 12 to 17%). Admit or observe with serial troponins and further non-invasive testing; do not discharge on the initial assessment alone. |
| 7 to 10, high risk | High MACE risk (around 50% or more in the derivation cohort). Treat as a likely acute coronary syndrome and pursue an early invasive strategy with cardiology involvement. |
Pitfalls, exclusions and caveats
- The original HEART score uses the initial troponin. Accelerated pathways (for example HEART Pathway) add a second troponin, often with high-sensitivity assays, before safely discharging low-risk patients: do not discharge on a single value alone.
- It is for undifferentiated chest pain. It does not apply to a confirmed STEMI, ongoing unstable angina, or an obvious non-cardiac cause, where management follows its own pathway.
- The History domain is subjective and the largest source of inter-rater variability; calibrate it carefully and lean toward caution when uncertain.
- A low score reduces but does not eliminate short-term risk. Combine it with clinical judgement, the trajectory of symptoms, and local protocols rather than treating it as a sole discharge rule.
- Reported MACE rates vary by cohort, assay, and follow-up window; the percentages here are approximate.
Sum 0 to 2 points each for: History (suspicion), ECG, Age, Risk factors, and initial Troponin. Total 0 to 10. 0 to 3 low risk, 4 to 6 moderate, 7 to 10 high.The HEART score was described by Six, Backus, and Kelder (2008) and validated further by Backus, Mahler, and colleagues. This implementation is an educational tool and is not affiliated with the original authors or any guideline body.
Frequently asked
What HEART score is safe for discharge?
A score of 0 to 3 carries a low 6-week MACE risk (around 1.7%) and supports early discharge in many pathways. Most accelerated protocols still require at least serial troponins, often with a high-sensitivity assay, before the patient goes home.
Does HEART use one troponin or two?
The original score uses the initial troponin. Real-world accelerated pathways such as the HEART Pathway add a repeat troponin (commonly at 3 hours, or a 0/1-hour high-sensitivity protocol) to improve safety before discharging low-risk patients.
How is the HEART score different from a TIMI or GRACE score?
TIMI and GRACE were derived in confirmed acute coronary syndrome to estimate prognosis. HEART was built specifically for undifferentiated emergency-department chest pain to triage who can be discharged early, and it performs well in that setting.
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.