Key result
The artificial neural network could theoretically reduce the number of ambulance ECGs transmitted by 64% without missing any case of STEMI or a need for immediate PCI.
Why the study?
Does an artificial neural network accurately predict STEMI and the need for acute PCI in prehospital patients with suspected acute coronary syndrome?
Cohort (n=560)
No
Does an artificial neural network accurately predict STEMI and the need for acute PCI in prehospital patients with suspected acute coronary syndrome?
Effect estimate: AUROC 0.93 (95% CI 0.89-0.96)
An artificial neural network can accurately predict STEMI and the need for acute PCI from prehospital ECGs, potentially reducing unnecessary ECG transmissions to the CCU by 64%.
May support ANN triage to cut prehospital ECG volume; hypothesis-generating and should not yet change practice.
Our ANN had an excellent ability to predict STEMI and the need of acute PCI in ambulance ECGs, and has a potential to safely reduce the number of ECG transmitted to the CCU by almost two thirds.
No takes yet. Share an insight, caveat, or question.
Forberg et al. (2012) conducted a cohort in ST elevation myocardial infarction (n=560). Artificial neural network (ANN) vs. CCU physician's ECG interpretation was evaluated on Detecting STEMI and predicting the need for acute PCI (AUROC 0.93, 95% CI 0.89-0.96). The artificial neural network could theoretically reduce the number of ambulance ECGs transmitted by 64% without missing any case of STEMI or a need for immediate PCI.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: