Biomedical domains are characterized by the presence of large amounts of high dimensional data and a lack of general theories to understand structural and functional components. Artificial Neural Networks (ANN) are computer-based expert systems that have proved to be useful in pattern recognition tasks. ANN can be used in different phases of the decisionmaking process, from classification to diagnostic procedures. In this work, we develop a method based on a hybrid ANN. This method uses three different feed forward type multilayer neural networks, with the ability to classify ECGs as normal or carrying atrioventricular block (AVB). A single output unit encodes the probability of AVB occurrences. A value between 0 and 0.05 being the desired output for a normal ECG, a value between 0.05 and 1 would infer an occurrence of an AVB. The results show that, this hybrid network has a good performance to detect AVBs. They show a sensibility of 98% and a specificity of 92%.

Biomedical domains are characterized by the presence of large amounts of high dimensional data and a lack of general theories to understand structural and functional components. Artificial Neural Networks (ANN) are computer-based expert systems that have proved to be useful in pattern recognition tasks. ANN can be used in different phases of the decisionmaking process, from classification to diagnostic procedures. In this work, we develop a method based on a hybrid ANN. This method uses three different feed forward type multilayer neural networks, with the ability to classify ECGs as normal or carrying atrioventricular block (AVB). A single output unit encodes the probability of AVB occurrences. A value between 0 and 0.05 being the desired output for a normal ECG, a value between 0.05 and 1 would infer an occurrence of an AVB. The results show that, this hybrid network has a good performance to detect AVBs. They show a sensibility of 98% and a specificity of 92%.

Biomedical domains are characterized by the presence of large amounts of high dimensional data and a lack of general theories to understand structural and functional components. Artificial Neural Networks (ANN) are computer-based expert systems that have proved to be useful in pattern recognition tasks. ANN can be used in different phases of the decisionmaking process, from classification to diagnostic procedures. In this work, we develop a method based on a hybrid ANN. This method uses three different feed forward type multilayer neural networks, with the ability to classify ECGs as normal or carrying atrioventricular block (AVB). A single output unit encodes the probability of AVB occurrences. A value between 0 and 0.05 being the desired output for a normal ECG, a value between 0.05 and 1 would infer an occurrence of an AVB. The results show that, this hybrid network has a good performance to detect AVBs. They show a sensibility of 98% and a specificity of 92%.