Mattias Ohlsson, Holger Holst and Lars Edenbrandt
Acute myocardial infarction: analysis of the ECG using artificial neural networks
In Proceedings of the Artificial Neural Networks in Medicine and Biology Conference, 209-214 (2000)
This paper presents a neural network classifier for the diagnosis of acute myocardial infarction, using the 12-lead ECG. Features from the ECGs were extracted using principal component analysis, which allows for a small number of effective indicators. A total of 4724 pairs of ECGs, recorded at the emergency department, was used in this study. It was found (empirically) that a previous ECG, recorded on the same patient, has no or very little effect on the performance for the neural network classifier.
LU TP 99-34