Key result
The myocardial-ischaemic-injury-index algorithm predicted 1-year myocardial infarction or cardiovascular death, occurring in 17.6% of high-probability vs 1.5% of low-probability patients (p<0.0001).
Why the study?
Diagnostic pathways for myocardial infarction rely on fixed troponin thresholds that do not account for variation by age, sex, and time. The authors aimed to evaluate whether a machine learning algorithm predicting myocardial infarction likelihood performs well in clinical practice and predicts subsequent events.
Does the myocardial-ischaemic-injury-index machine learning algorithm predict subsequent myocardial infarction or cardiovascular death in patients with suspected acute coronary syndrome?
Cohort (n=15,944)
Does the myocardial-ischaemic-injury-index machine learning algorithm predict subsequent myocardial infarction or cardiovascular death in patients with suspected acute coronary syndrome?
Absolute Event Rate: 17.6% vs 1.5%
p-value: p=<0.0001
The myocardial-ischaemic-injury-index machine learning algorithm effectively identifies patients at high risk for myocardial infarction and subsequent cardiovascular events at 1 year.
May enhance risk stratification; leaves open prospective validation before clinical adoption.
BACKGROUND: Diagnostic pathways for myocardial infarction rely on fixed troponin thresholds, which do not recognise that troponin varies by age, sex, and time within individuals. To overcome this limitation, we recently introduced a machine learning algorithm that predicts the likelihood of myocardial infarction. Our aim was to evaluate whether this algorithm performs well in routine clinical practice and predicts subsequent events. METHODS: threshold (49·7). The trial is registered with ClinicalTrials.gov, NCT01852123. FINDINGS: score ≥49·7; specificity 95·0% [94·6-95·3], positive predictive value 70·4% [68·7-72·0]). At 1 year, subsequent myocardial infarction or cardiovascular death occurred more often in high-probability patients than low-probability patients (520 [17·6%] of 2961 vs 197 [1·5%] of 12 983], p<0·0001). INTERPRETATION: algorithm could improve the diagnosis and assessment of risk in patients with suspected acute coronary syndrome. FUNDING: Medical Research Council, British Heart Foundation, National Institute for Health Research, and NHSX.
No takes yet. Share an insight, caveat, or question.
Doudesis et al. (2022) conducted a cohort in suspected acute coronary syndrome (n=15,944). myocardial-ischaemic-injury-index machine learning algorithm vs. low-probability patients was evaluated on subsequent myocardial infarction or cardiovascular death at 1 year (p=<0.0001). The myocardial-ischaemic-injury-index algorithm predicted 1-year myocardial infarction or cardiovascular death, occurring in 17.6% of high-probability vs 1.5% of low-probability patients (p<0.0001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: