We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
پیشبینی میزان بروز بیماري سل با استفاده از سريهاي زمانی مبتنی بر شبکههاي عصبی در ایران
- Authors
عاطفه صدیقنیا; شراره رستم نیاکان کلهري; مهشید ناصحی; احمد علی حنفی بجد
- Abstract
Background: Tuberculosis (TB) is an important infectious disease with high mortality in the world. None of the countries stay safe from TB. Nowadays, different factors such as co-morbidities, increase TB incidence. World Health Organization (WHO) last report about Iran's TB status shows rising trend of multidrug-resistant tuberculosis (MDR-TB) and HIV/TB. More than 95% illness and death of TB cases are in developing countries. The most infections are in South East Asia and West Pacific that 56% of them are new cases in the world. The incidence is actually new cases of each year. Incidence prediction is affecting TB prevention, management and control. The purpose of this study was to designing and creating a system to predict TB incidence by time series artificial neural networks (ANN) in Iran. Methods: This study was a retrospective analytic. 10651 TB cases that registered on Iran’s Stop TB System from March 2014 to March 2016, were analyzed. Most of reliable data used directly, some of them merged together and create new indicators and two columns used to compute a new indicator. At first, effective variables were evaluating with correlation coefficient tests then extracting by linear regression on SPSS statistical software, version 20 (IBM, Armonk, NY, USA). We used different algorithms and number of neurons in hidden layer and delay in time series neural network. R, MSE (mean squared error) and regression graph were used for compare and select the best network. Incidence prediction neural network were designed on MATLAB® software, version R2014a (Mathworks Inc., Natick, MA, USA). Results: At first, 23 independent variables entered to study. After correlation coefficient and regression, 12 variables with P≤0.01 in Spearman and P≤0.05 in Pearson were selected. We had the best value of R, MSE and also regression graph in train, validation and tested by Bayesian regularization algorithm with 10 neuron in hidden layer and two delay. Conclusion: This study showed that artificial neural network (ANN) had acceptable function to extract knowledge from TB raw data; ANN is beneficial to TB incidence prediction.
- Publication
Tehran University Medical Journal, 2019, Vol 77, Issue 4, p216
- ISSN
1683-1764
- Publication type
Article