Study objective: We seek to evaluate how accurately the emergency physician initiates percutaneous coronary intervention for patients presenting to the emergency department (ED) with ST-segment-elevation myocardial infarction (STEMI) and the impact of emergency physician-initiated percutaneous coronary intervention on mean door-to-balloon time. Methods: We conducted a before-and-after cohort study of consecutive STEMI patients presenting to a 608-bed tertiary care hospital during a 32-month period. During the first 19 months, percutaneous coronary intervention was available only by consultation with an on-call interventionist. In the subsequent 13 months, percutaneous coronary intervention was initiated by the emergency physician independent of cardiology consultation. All patients presenting during the study period with an appropriate clinical history and characteristic ECG findings of STEMI were eligible. Patients with greater than 12 hours of symptoms, contraindications to percutaneous coronary intervention, a valid do-not-resuscitate order, who died before percutaneous coronary intervention was attempted, who initially refused, or whose door-to-balloon time was greater than 6 hours were excluded. The accuracy of emergency physician identification of STEMI was confirmed by an independent cardiologist. All hospital medical records with a discharge diagnosis of acute myocardial infarction (International Classification of Diseases, Ninth Revision code 410.xx) were reviewed to confirm that no STEMI patients went unidentified. A t test was used to compare mean door-to-balloon time in each cohort. Results: A total of 172 patients were enrolled in this investigation, 95 STEMI patients in the initial 19-month period and 77 patients in the subsequent 13 months, when percutaneous coronary intervention was initiated solely at the discretion of the emergency physician. Percutaneous coronary intervention was inappropriately initiated by the emergency physician only once, and no ED patients with STEMI were overlooked, resulting in 100% sensitivity (95% confidence interval [CI] 97.3% to 100%) and 99.6% specificity (95% CI 97.7% to 99.9%). Mean door-to-balloon time in the emergency physician-initiated percutaneous coronary intervention cohort improved by 40 minutes (95% CI 26 to 54 minutes) from 131 to 91 minutes. Conclusion: The emergency physician is able to accurately initiate percutaneous coronary intervention for ED patients presenting with STEMI independent of cardiology consultation. Emergency physician-initiated percutaneous coronary intervention significantly reduces mean door-to-balloon time for these patients. © 2007 American College of Emergency Physicians.