Journal of North Khorasan

Abstract Background & Objectives: Logistic regression is a general model to determine the relationship between covariates and binary response variables. Artificial neural network model is an alternative flexible model which can be used in these cases, too. This study aimed to make a comparison between the predictions of ANN and logistic regression model for binary outcome of medical data. Material &Methods: Data gathered from 639 registered gastric cancer patients between January 2002 and October 2007 at the Research Center for Gastroenterology and Liver Diseases of Shahid Beheshti University of Medical Sciences, Tehran, Iran. Stage of disease was considered as the dependent variable. Network performance was assessed by using of least square error of prediction and then concordance indexes and area under receiver operative characteristic curves (AUROC) were used to comparison of neural network and logistic regression models. Data analysis was performed by R 2.12 software. Results: Results showed that the concordance index of ANN and LR for drug treatment was calculated as 0.771 and 0.710 respectively. In addition AUROC for ANN and LR models were 0.725 and 0.699, respectively. The difference between the values of observed and predicted of the dependent variable by two models was significant (P=0.002). Conclusion: As a result, the total accuracy prediction of the ANN model is better than LR model, so this model is suggested to predict the stage of gastric cancer disease and also diagnostic goals.

Background & Objectives: Seizures can be noted to the main symptom of epilepsy. Seizures prediction or early diagnosis for people reduces significantly injuries of epilepsy. The main problem that related to neurological disorders is an inability to timely prediction or the occurrence of seizures. Material and Method: EEG signals are Stochastic Process that can be treated as a sequence in time or in other words can be stated time series. In this study 300 epileptic patients categorized in three groups: normal, before and during the convulsive seizures were studied. Accordingly, after receiving data, they were preprocessed, then for Prediction time occurrence extracted special features by propose Algorithm. Eventually In order to final validate the cross-evaluation method (k-fold) has been used. Result: Firstly by wavelet transforms (WT), removed possible artifacts. In the next step by Binary Particle Swarm Optimization (BPSO) the characteristics (delay) are obtained. Then SVM algorithm (SVM) was performed to dimension reduction and manage the data (delay) so final Prediction that applied by Adaptive Nero Fuzzy Inference System Based on Optimal Delay. The final evaluation and final validation were done and the algorithm accurately in predicts by 2 units in delay approved. Conclusion: The Proposed System achieved a high accurate by interaction in introduced method. Despite the high accuracy, the present methods have a little ability in predicting seizure. Comparing the current methods indicate accuracy and high efficiency of the present approach.