Introducing a quantitative method to calculate the rate of primary infertility

In the previous studies, the rate of primary infertility was reported differently. It seems the main reasons are related to the different methods of data collection and information analysis. Therefore, introducing a precise method to determine the infertile couples and the population exposed to the risk of infertility is an important issue to study primary infertility. The proposed methodology for assessing primary infertility rate has been designed and applied by Avicenna Research Institute in a national survey. Sampling was conducted based on probability proportional to size cluster method. In this survey, after reviewing the former studies, the reproductive history was used as a basis for data collection. Every reproductive event was recorded with a code and a date in the questionnaire. To introduce a precise method, all possible events were considered thoroughly and for each situation, it was determined whether these cases should be considered in numerator, denominator or it should be eliminated from the study. Also in some situations where the correct diagnosis of infertility was not possible, a sensitivity analysis was recommended to see the variability of results under different scenarios. The proposed methodology can precisely define the infertile women and the population exposed to the risk of infertility. So, this method is more accurate than other available data collection strategies. To avoid bias and make a consistent methodology, using this method is recommended in future prevalence studies

Comparison of logistic regression and artificial neural network in low back pain prediction: second national health survey

The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. The area under the ROC curve [SE], root mean square and -2Loglikelihood of the logistic regression was 0.752 [0.004], 0.3832 and 14769.2, respectively. The area under the ROC curve [SE], root mean square and -2Loglikelihood of the artificial neural network was 0.754 [0.004], 0.3770 and 14757.6, respectively. Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant