Localization of Myocardial Infarction Based on Learning Vector Quantization Networks Applied to ST Elevations of the 12‐Lead ECG

Abstract

Background: During recent years artificial neural networks have been proposed as a diagnostic tool in different fields of cardiology. Most of the studies have utilized the multilayer perceptron with backpropagation learning rule for the design of the network. As a new approach, Learning Vector Quantization (LVQ) which belongs to the class of competitive learning networks, was developed particularly for classification problems. So far there are no data available on the application of LVQ for classification tasks in cardiology. The present study aims at investigating the performance of LVQ for localization of myocardial infarction (MI) based on ST elevations in the standard 12-lead ECC.Methods: Altogether, 769 male patients (age 53 ? 7 years) with an acute MI were included into the study. Three hundred fifty-three patients (46%) presented with anterior and 41 6 patients (54%) with inferior MI based on typical changes in the standard 12-lead ECG. Standardized ST elevations in all 12 leads were used as input structure for the network. The performance of the network was studied using two different learning and test sets. The influence of the number of reference vectors and training steps on the classification accuracy for infarct location was investigated. Results:The highest classification accuracy of 88.6% for infarct location was achieved using the learning set with 66% of all patients. This setup was based on five reference vectors and 200 training steps. The best accuracies for anterior MI were higher as compared to inferior infarctions in both the test and training set. Using more than 50 reference vectors resulted in a decrease of classification accuracy due to overtraining of the network. Conclusion: Appropriately initialized and trained artificial neural networks based on LVQ give a high accuracy for localization of MI using only ST elevations of the standard 12-lead ECG. A.N.E. 1997;2(4):331-337 artificial neural networks; Learning Vector Quantization; myocardial infarctionDuring recent years the automatic interpretation of electrocardiographic data has been shown to be useful for classification tasks in cardiology.' Artifi-cia1 neural networks have been applied in different fields of cardiology, such as detection of atrial fib r i l l a t i~n ,~'~ classification of electrocardiographic

Artificial Neural Networks in Medicine and Biology

“…Another approach to providing interpretability is to use a hybrid neurofuzzy system [59]. These are feed-forward networks built from if-then rules containing linguistic terms based on domain knowledge, and the membership functions associated with the fuzzy rules can be tuned to data by means of a training algorithm.…”

“…From medical signal analysis the following applications can be mentioned: electroencephalography [27], [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], magnetoencephalography [49], [50], [51], electrocardiography [52], [53], [54], [55], [56], [57], [58], [59], electromyography [60], [61], [62], [63], [64], [65], [66], classification of motor cortical discharge patterns [67], [68], [69], sleep cycle recognition [70], [71], analysis of blood pressure time series [72], [73], [74], classification oflung sounds …”