Ischemia detection with a self-organizing map supplemented by supervised learning

Abstract

The problem of maximizing the performance of the detection of ischemia episodes is a difficult pattern classification problem. The motivation for developing the supervising network self-organizing map (sNet-SOM) model is to exploit this fact for designing computationally effective solutions both for the particular ischemic detection problem and for other applications that share similar characteristics. Specifically, the sNet-SOM utilizes unsupervised learning for the "simple" regions and supervised for the "difficult" ones in a two stage learning process. The unsupervised learning approach extends and adapts the self-organizing map (SOM) algorithm of Kohonen. The basic SOM is modified with a dynamic expansion process controlled with an entropy based criterion that allows the adaptive formation of the proper SOM structure. This extension proceeds until the total number of training patterns that are mapped to neurons with high entropy reduces to a size manageable numerically with a capable supervised model. The second learning phase has the objective of constructing better decision boundaries at the ambiguous regions. At this phase, a special supervised network is trained for the computationally reduced task of performing the classification at the ambiguous regions only. The utilization of sNet-SOM with supervised learning based on the radial basis functions and support vector machines has resulted in an improved accuracy of ischemia detection especially in the last case. The highly disciplined design of the generalization performance of the support vector machine allows designing the proper model for the number of patterns transferred to the supervised expert.

HySMID: an ischemia diagnosis system using genetic algorithms and multicriteria decision analysis

“…The obtained results are better than those of other similar approaches [1,[3][4][5][6][7][8][11][12] when tested using the data from the ESC ST-T database. Furthermore, the multicriteria approach has the ability to provide interpretations for the decisions made following postprocessing (identification of the closest prototype(s)).…”

“…In Table 1 the results of the proposed hybrid system are compared to those of other approaches of automated ischemic episode detection, such as ANNs [1,[4][5][6], ANNs combined with principal component analysis (PCA) [4,7], set of rules [3], fuzzy logic [8], PCA [11] or other signal processing techniques [12]. It should be mentioned that other beat classification systems have also been proposed but their performance cannot be judged against the above mentioned methods, since either they have been evaluated with other test sets or they employed different performance measures [9,10].…”

“…It should be mentioned that other beat classification systems have also been proposed but their performance cannot be judged against the above mentioned methods, since either they have been evaluated with other test sets or they employed different performance measures [9,10]. [4] 77 86 Recurrent ANN [4] 77 85 Knowledge-learning ANN [4] 71 66 ANN [5] 84 79 CP-SOM & SVM [6] 83 82 ANN & PCA [7] 90 89 Fuzzy Logic [8] 81 68 PCA [11] 85 86 Geometric method [12] 82 …”

“…Several techniques have been proposed for this purpose, which evaluate the ST segment changes and the T wave alterations with different methodologies. Their evaluation process is based upon medical knowledge expressed by a set of rules [3], artificial neural networks (ANNs) [1,[4][5][6][7], fuzzy logic [8], wavelet analysis [9] or other signal processing techniques [10][11][12].…”

Ischemia detection using supervised learning for hierarchical neural networks based on kohonen-maps

“…The training set is extracted from 110 fifteen minutes ECG records, consisting of representative normal and abnormal ST-T waveforms. After R-peak detection (inside the QRS complex) using the amplitude and the first derivative of the signal, [9] and baseline wander rejection (based on cubic splines) we could precisely extract the ST-T patterns for PCA feature extraction [7], [8].…”