Computerized interpretation of the prehospital electrocardiogram (ECG) is increasingly being used in the basic life support (BLS) ambulance setting to reduce delays to treatment for patients suspected of ST segment elevation myocardial infarction (STEMI).

To estimate 1) predictive values of computerized prehospital 12-lead ECG interpretation for STEMI and 2) additional on-scene time for 12-lead ECG acquisition.

Over a 2-year period, 1,247 ECGs acquired by primary care paramedics for suspected STEMI were collected. ECGs were interpreted in real time by the GEMarquette 12SL ECG analysis program. Predictive values were estimated with a bayesian latent class model incorporating the computerized ECG interpretations, consensus ECG interpretations by study cardiologists, and hospital diagnosis. On-scene time was compared for ambulance-transported patients with (n 5 985) and without (n 5 5,056) prehospital ECGs who received prehospital aspirin and/or nitroglycerin.

The computer's positive and negative predictive values for STEMI were 74.0% (95% credible interval [CrI] 69.6–75.6) and 98.1% (95% CrI 97.8–98.4), respectively. The sensitivity and specificity were 69.2% (95% CrI 59.0–78.5) and 98.9% (95% CrI 98.1–99.4), respectively. Prehospital ECGs were associated with a mean increase in on-scene time of 5.9 minutes (95% confidence interval 5.5–6.3).

The predictive values of the computerized prehospital ECG interpretation appear to be adequate for diversion programs that direct patients with a positive result to hospitals with angioplasty facilities. The estimated 26.0% chance that a positive interpretation is false is likely too high for activation of a catheterization laboratory from the field. Acquiring prehospital ECGs does not substantially increase on-scene time in the BLS setting.