Medical diagnostic accuracies can be improved when the pattern is simplified through representation by important features. Features are used to represent patterns with minimal loss of important information. The feature vector, which is comprised of the set of all features used for describing a pattern, is a reduced-dimensional representation of that pattern. By identifying a set of salient features, the noise in a classification model can be reduced, resulting in more accurate classification. In this study, a signal-to-noise ratio (SNR) saliency measure was employed to determine saliency of input features of recurrent neural networks (RNNs) used in the classification of electrocardiogram (ECG) signals. In order to extract features representing four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database, eigenvector methods were used. The RNNs used in the ECG beats classification were trained for the SNR screening method. The results of the application of the SNR screening method to the ECG signals demonstrated that classification accuracies of the RNNs with salient input features are higher than those of the RNNs with salient and non-salient input features.
The Internet has become an important source of information for physicians seeking immediate data for the management of patients and for those developing decision-making methodologies and guidelines for clinical practice. In this study, components and subsystems of a medical decision support system are presented. An artificial neural network model, which is one of the subsystems of the differential diagnosis component, has been proposed as a reasoning tool to support medical diagnosis. The input data of artificial neural network models used in different medical diagnosis can be obtained via the Internet. The present study is concerned with the application of artificial neural network model to diabetes prediction. Demographic and medical data of diabetics and non-diabetics obtained via the Internet were used as the artificial neural network inputs. The accuracy of the neural network's results has shown that the diabetes prediction is feasible by the neural network described in this study.
A new approach based on the implementation of probabilistic neural network (PNN) is presented for classification of electrocardiogram (ECG) beats. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were analyzed. The ECG signals were decomposed into time-frequency representations using discrete wavelet transform (DWT) and wavelet coefficients were calculated to represent the signals. The aim of the study is classification of the ECG beats by the combination of wavelet coefficients and PNN. The purpose is to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. The present research demonstrated that the wavelet coefficients are the features which well represent the ECG signals and the PNN trained on these features achieved high classification accuracies.