Iranian Journal of

  Background and Objectives : recent years, considerable attention has been paid to statistical models for classification of medical data according to various diseases and their outcomes. Artificial neural networks have been successfully used for pattern recognition and prediction since they are not based on prior assumptions in clinical studies. This study compared two statistical models, artificial neural network and logistic regression, to predict the survival of patients with breast cancer.

  Methods: Two models were applied on cancer registry data, Kerman, southeast of Iran, to predict survival. The data of 712 breast cancer patients in the age group 15 to 85 years was used in this study. The logistic regression and three-layer perceptron neural network models were compared in terms of predicting the survival. Sensitivity, specificity, prediction accuracy, and the area under ROC curve were used for comparing the two models.

  Results : In this study, the sensitivity and specificity of logistic regression and artificial neural network models were (0.594, 0.70) and (0.621, 0.723), respectively. Prediction accuracy and the area under ROC curve for two models were (0.688, 0.725) and (0.70, 0.725), respectively.

  Conclusion: Although there were insignificant differences in the performance of the two models for predicting the survival of the patients with breast cancer, the corresponding results of artificial neural network were more appropriate for predicting survival in such data.

Background and Objectives: Diabetes is a chronic and common metabolic disease which has no curative treatment. Logistic regression (LR) is a statistical model for the analysis and prediction in multivariate statistical techniques. Discriminant analysis is a method for separating observations in terms of dependent variable levels which can allocate any new observation after making discriminating functions. The aim of this study was to compare and determine the effective variables in type 2 diabetes.

Methods: The data included 5357 persons obtained through a cohort study in Kerman, southeastern Iran, in 2009-11. Diabetes was considered the response variable. The independent variables after deleting colinearity and correlated variables included height, waist circumference, age, gender, occupation, education, drugs, systolic blood pressure, HDL, LDL, drug abuse, activities, and triglyceride. Sensitivity, specificity, accuracy, and ROC curve were applied for determining and comparing the prediction power of the models.

Results: The results in the reduced model with extracted significant variables from the full model, the sensitivity of the LR model and DA was 74% and 22.4%, the specificity of the LR model and DA was 71.1 % and 95.4 %, the prediction accuracy of the LR model and DA was 71.5% and 85.3%, and the ROC curve of the LR model and DA was 80.3% and 80.1%, respectively.Simulation showed the sensitivity, specificity, accuracy, and ROC curve was 99.18%, 98.49%, 98.59%, and 99.9% for the LR model and 92.62%, 99.19%, 98.26%, and 99.56% for DA, respectively.

Conclusion: The results showed that the risk factors of diabetes in the logistic regression reduced model were waist circumference, age, gender, LDL level, systolic pressure, and drugs. Also, the sensitivity of the LR model was more than DA while DA had a higher specificity and prediction accuracy. Comparison of the ROC curve showed that the prediction estimated values were rather similar in both models, but the two models were the same asymptotically.

Background and Objectives: One of the fair financial protection indexes in monitoring health systems is estimating impoverishment due to health care expenditure. The aim of this study was to measure the percentage of households impoverished due to out-of-pocket(OOP) payments in Iran provinces during2008-2014.

Methods: The present retrospective descriptive study was conducted based on data from Household Income and Expenditure Survey in both rural and urban households. The proportion of households that moved below the poverty line after deducting health care costs was calculated. The poverty line for urban and rural areas was calculated based on household food expenditure. To show the provincial dispersion of the index during this period, the coefficient of variation(CV) was used. Mann-WhitneyU test and descriptive statistics were used to analyze the data.

Results: Golestan, North Khorasan, and Kerman had the highest impoverishment rate due to OOP Moreover, Alborz, Tehran, and Bushehr had the lowest impoverishment rate due to OOP. In all the study years, the average impoverishment due to OOP was significantly higher in rural areas compared to urban areas. Provincial dispersion CV for this index did not have a constant trend.

Conclusion: The results of this study provide valuable evidence for policy-makers to estimate the impact of OOPs on household impoverishment. In order to reduce impoverishment due to OOP, supportive targeted interventions for vulnerable and low-income households, especially rural households, in addition to decreasing the share of OOP, are essential, such as developing health subsidies and improving insurance service packages.

Background and Objectives: Catastrophic health expenditure (CHE) is a key indicator for measuring  households' financial protection in the health system. This study was conducted to measure the incidence and intensity of CHE in Iranian provinces 2008-2014.

Methods: When the out-of-pocket (OOP) spending of each household amounts to at least 40% of the household's capacity to pay, it is called a catastrophe. The incidence of CHE in Iranian provinces was estimated using the data obtained from household-expenditure-and-income-surveys. The intensity was calculated as the average extent to which OOPs exceeded the 40% threshold. Descriptive statistics and Mann-WhitneyU test were used for data analysis. The index of disparity(ID) was also calculated for geographical disparities across the provinces.

Results: On average, the lowest and highest CHE incidence and intensity were seen in Fars and South Khorasan provinces respectively. However, the highest and lowest rate for CHE households that actually experienced catastrophe at the 40% threshold belonged to Fars and Kurdistan provinces. The incidence of CHE in rural was more than urban areas. ID of CHE incidence for targeted amount was high and had no constant trend.

Conclusion: CHE incidence had a remarkable difference in different provinces and in the rural area compared to the urban area. Due to the importance of this index in promoting health financial protection, like indexes such as OOP, its distribution in rural and urban areas as well as in different provinces is considerable. It requires a structured format to identify the disadvantaged and low-income groups and provide financial-support and insurance for them.