The problem of maximizing the performance of the detection of ischemia episodes is a difficult pattern classification problem. The state space for this problem is consisted of regions that lie near class separation boundaries and require the construction of complex discriminants while for the rest regions the classification task is significantly simpler. The motivation for developing the Network Self-Organizing Map (NetSOM) model is to exploit this

Problema maximizarii performantelor in recunoasterea automata a modificarilor segmentului ST-T in detectia ischemiei ramine o problema dificila de "pattern clasification". Autorii propun o model nou (de tip ierarhizat) de mapa Kohonen, numit NetSOM. Sensitivitatea respectiv predictivitatea recunoasterii modificarilor de segment ST-T au fost de 78% si respectiv 74.1%. The problem of maximizing the performance of ST-T segment automatic recognition