A machine learning algorithm to predict acute myocardial infarction over 30 minutes.

Document Type

Conference Proceeding

Publication Date


Publication Title

J Am Coll Cardiol


Background Chest pain is a common presentation in the emergency department (ED). Variation in high sensitivity cardiac troponin I (hs-cTnI) by age and gender make diagnosis of AMI more challenging. Machine learning integrates these variables to allow more accurate and rapid evaluation of possible AMI. Methods We applied a machine learning algorithm (myocardial-ischemic-injury-index [MI3]) that incorporates age, gender, and hs-cTnI levels at time 0 and 30 minutes in 529 patients evaluated for possible AMI in a single urban ED. MI3 calculates a value from 0-100 reflecting the likelihood of AMI. Diagnosis of AMI was adjudicated by 2 independent physicians in accordance with the universal definition of AMI and required at least 1 hs-cTnI >99th% (Abbott Architect; 26 ng/L). Patients were followed at 30 days for major adverse cardiac events (MACE): death or AMI. Results There were 42 (7.9%) patients that had an AMI. Patients were divided into 3 groups by the MI3 score: low-risk (≤3.13), intermediate-risk (>3.13-51.0), and high-risk (>51.0) (Table). The sensitivity for AMI was 100% with a MI3 value ≤3.13 and 353 (67%) ruled-out for AMI at 30 minutes. At 30 days there were 2 (0.6%) MACEs (0 AMI, 2 non-cardiac deaths) in the low-risk group, in the intermediate-risk group 4 (3.0%) MACEs (3 AMIs, 1 cardiac death), and in the high-risk group 4 (9.1%) MACEs (4 AMIs, 2 cardiac deaths). Conclusion The MI3 algorithm had 100% sensitivity for AMI at 30 minutes and identified a low-risk cohort who may be considered for early discharge.





First Page


This document is currently not available here.