Comparing three data mining algorithms for Identifying the associated risk factors of type 2 diabetes

Background: Increasing the prevalence of type 2 diabetes has given rise to a global health burden and a concern among health service providers and health administrators. The current study aimed at developing and comparing some statistical models to identify the risk factors associated with type 2 diabetes. In this light, artificial neural network [ANN], support vector machines [SVMs], and multiple logistic regression [MLR] models were applied, using demographic, anthropometric, and biochemical characteristics, on a sample of 9528 individuals from Mashhad City in Iran

Methods: This study has randomly selected 6654 [70%] cases for training and reserved the remaining 2874 [30%] cases for testing. The three methods were compared with the help of ROC curve

Results: The prevalence rate of type 2 diabetes was 14% in our population. The ANN model had 78.7% accuracy, 63.1% sensitivity, and 81.2% specificity. Also, the values of these three parameters were 76.8%, 64.5%, and 78.9%, for SVM and 77.7%, 60.1%, and 80.5% for MLR. The area under the ROC curve was 0.71 for ANN, 0.73 for SVM, and 0.70 for MLR

Conclusion: Our findings showed that ANN performs better than the two models [SVM and MLR] and can be used effectively to identify the associated risk factors of type 2 diabetes

[ effects of massage on intra ventricular hemorrhage in preterm infants in the neonatal intensive care unit]

Background and Aim: Massage can produce sense of security, enhanced physical growth, improved circulation and function of nervous system. It also can decrease sleep disorders and behavior disturbances. This study investigated the effect of massage on intra ventricular hemorrhage in premature infants in the neonatal intensive care unit [NICU] of Ghaem Hospital in Mashhad, Iran

Material and Methods: In this random clinical trial 60 stable preterm newborns were divided into intervention [n=30] and control [n=30] groups. The intervention group performed passive massage movements for three short periods [each period= fifteen minutes] in 3 consecutive hours for 5 days. The intervention and control groups were compared with each other in regard to the incidence of intra ventricular hemorrhage. Our tools for data collection included forms for sample selection and demographic characteristics, check lists to record data and pulse oximetry device. Using SPSS.16 software, data were analyzed by independent t-test, chi square test and odds ratio

Results: In our study experimental group showed a lower incidence rate of intra ventricular hemorrhage in comparison to the control group [P= 0.058]; however, it was not statically significant

Conclusion: According to the results of this study massage along with other methods can be an effective method for reducing the incidence of intra ventricular hemorrhage in stable premature infants

structural equation model to predict the social-cognitive determinants related to physical activity in Iranian women with diabetes mellitus

Lifestyle-modification programs including physical activity are essential for both treatment and prevention of Type 2 Diabetes Mellitus [T2DM]. However, factors associated with physical activity among patients are poorly understood. This study applied Social-Cognitive Theory [SCT] for predicting determinants of physical activity among women with T2DM in Iran, 2013. In this cross-sectional study, partial least square path modeling [PLS-PM] was used as an estimation technique for structural equation model. This model specified hypotheses between components of Social-cognitive Theory on physical activity behavior. A random sample of 300 women with T2DM was selected, and completed SCT constructs instrument. Data were analyzed using statistical software WarpPLS Ver. 4.0. The model explained 26% of the variance in physical activity. Self-regulation, task self-efficacy and barrier self-efficacy were significantly direct predictors of physical activity among women with T2DM. Task self-efficacy, social support and modeling had significantly indirect effects on physical activity behavior [P<0.001]. Our findings showed evidence for adequacy of a theoretical framework that could be used to predict physical activity behavior among women with T2DM

Views of users towards the quality of hospital information system in training hospitals

Users of hospital information system [HIS] use these systems during working day and know its problems better than others know. Studying their views is very important and can be especially effective in the development of the information system. The aim of this study was to investigate the users' view towards the quality of hospital information system in the training hospitals in Mashhad University of medical sciences. The current study was an applied research in Training Hospitals of Mashhad [East of Iran], which was conducted with descriptive cross-sectional method. A four-section questionnaire was designed for data collection consisting of: characteristics of information quality, reasons of low quality of information, accessibility of information and decision support. Validity and reliability were tested and SPSS was used for data analysis. 62.8% of users explained that one of reasons of low quality information was a problem related to obtaining information. 47.7% of them were unsatisfied with hospital information system ability for decision-making support. In general, 53.2% of users were slightly satisfied with the overall quality information of the system. There are some problems concerning information quality of HIS in Mashhad training hospitals. These problems include inappropriate information quality of the system and incompatibility with user needs which leads to decreased satisfaction of users towards the system