Acute myocardial infarction detected in the 12-lead ECG by artificial neural networks

Authors: 
Heden B, Ohlin H, Rittner R, Edenbrandt L
Journal: 
Circulation
Publication Date: 
1997 Sep 16
Volume: 
96
Issue: 
6
Pages: 
1798-802
  • HIT Description: Decision support with artificial intelligence. More info...
  • Purpose of Study: Evaluate the detection of acute myocardial infarction in the 12-lead ECG with artificial neural networks.
  • Years of study: 1990-1995
  • Study Design: Case-control
  • Outcomes: Impact on health care effectivness/quality
Summary:
  • Settings: The study was conducted at the emergency department of the University Hospital in Lund, Sweden.
  • Intervention: The performance of the neural networks, together with the correct diagnosis was compared with that of a widely used ECG interpretation program and the classification of an experienced cardiologist.
  • Evaluation Method: Measures of neural networks performance.
  • Description: The computerized electrocardiogram used was the ÒSiemens-Elema ABÓ. Artificial neural networks with multilayered perceptron architecture were used, and they detected acute myocardial infarction by use of measurements from the 12 ST-T segments of each ECG, together with the correct diagnosis.
  • Quality of Care and Patient Safety Outcome: The neural networks showed higher sensitivities and discriminant power than both the interpretation program and cardiologist. The sensitivity of the neural networks was 15.5% (95% confidence interval [CI], 12.4 to 18.6) higher than that of the interpretation program compared at a specificity of 95.4% (P<.00001) and 10.5% (95% CI, 7.2 to 13.6) higher than the cardiologist at a specificity of 86.3% (P<.00001).