Artificial Intelligence Enabled Rapid Identification of ST-Elevation Myocardial Infarction With Electrocardiogram - ARISE

Contribution To Literature:

The ARISE trial showed that AI-ECG interpretation shortens the time from ECG acquisition to arriving in the cath lab.


The goal of the trial was to evaluate artificial intelligence (AI)-interpreted electrocardiogram (ECG) (AI-ECG) compared with usual care among patients in the emergency department who received an ECG.

Study Design

  • Randomized
  • Parallel
  • Blinded

Patients presenting to the emergency department were randomized to AI-ECG (n = 21,989) vs. usual care (n = 22,005).

  • Total number of enrollees: 43,994
  • Duration of follow-up: hospitalization
  • Mean patient age: 60 years
  • Percentage female: 50%

Inclusion criteria:

  • Patients ≥18 years of age who presented to emergency department or inpatient department
  • Patients who received ≥1 ECG without history of coronary angiography within 3 days

Principal Findings:

The primary outcome, time from ECG to the cath lab, was 43.3 minutes in the AI-ECG group vs. 52.3 minutes in the usual care group (p = 0.003).

Secondary outcomes:

  • Ejection fraction: 45.0% in the AI-ECG group vs. 47.5% in the usual care group (p = 0.49)
  • Length of hospitalization: 5.0 days in the AI-ECG group vs. 5 days in the usual care group (p = 0.85)
  • Positive predictive value: 88.0%
  • Negative predictive value: 99.9%


Among patients who received an ECG in the emergency department, AI-ECG shortens the time from ECG acquisition to arrival in the cath lab. Ejection fraction and length of hospitalization was similar between treatment groups.


Presented by Dr. Chin-Sheng Lin at the American Heart Association Scientific Sessions, Philadelphia, PA, November 13, 2023.

Clinical Topics: Arrhythmias and Clinical EP, Acute Coronary Syndromes

Keywords: AHA23, Artificial Intelligence, Electrocardiography

< Back to Listings