Scientific Journal of

  Abstract

 Background and Objectives

 Cox regression model is one of the most common methods of survival analysis for whose application an assumption of proportional hazards needs to be established. Recently, neural network models without having certain assumptions have been shown to be suitable alternatives in predicting survival. This study aims to compare Cox regression and Artificial Neural Network ( ANN ) models to predict survival in acute leukemia patients.

 Materials and Methods

 In the present retrospective study, the information on 197 patients with acute leukemia in Sayyed-O-Shohada Hospital was collected using a checklist. Firstly, the assumption of proportional hazards was tested Cox regression model was fitted to the observations. To select an efficient ANN to compare with Cox regression model, the number of hidden layer neurons was changed. The prediction accuracy of the two models was compared using receiver operating characteristic (ROC) curve and kappa. Data analysis was performed using SPSS 19, Splus2000, and MatlabR 2009 software packages.

 Results

 Out of 9 ANN models with one hidden layer and 4 to 12 neurons, an ANN with 5 neurons in hidden layer was a superior model compared with Cox regression model. The areas under ROC curve for ANN model and Cox model were estimated to be 0.0709 and 0.458, respectively. The accuracies of prediction of survival for ANN model and Cox model were estimated as 78.9% and 50.3%, respectively.

 Conclusions

 Due to the high predicting accuracy of ANN models, the use of different models of ANN and their development in various fields of medical science are recommended.

  Abstract

 Background and Objectives

 Thalassemia is one of the most common chronic genetic diseases whose psychological issues can affect quality of life in patients. Research has shown that regular physical activity can increase well-being in a person. This study compared the quality of life in patients with thalassemia major based on their participation in group activities in Bandar Abbas in 2011.

 Materials and Methods

 In this descriptive analytical study, 35 patients with thalassemia major having participated in group activities were selected as the case group and 75 patients not participating as the control. Data were collected with quality of life questionnaire SF-36 and were analyzed by using SPSS13 statistical software , Mann-Whitney and Kruskal Wallis tests.

 Results

 The difference between the quality of life scores in the case and control groups for dimensions of general understanding of health, role limitation due to physical health problems, energy and vitality, physical functioning, emotionally related role limitations, body pain, mental health, and overall quality of life score was significant. The mean values of overall quality of life score in the case and control groups were 81.40 ± 3.64 and 58.35 ± 6.14, respectively. The relationship between the overall quality of life score and participation in group activities, starting age for desferal medication, and the number of desferal injections per month was significant in the case group.

 Conclusions

 Patients should be encouraged to participate in group activities and rehabilitative centers should be constructed to improve the level of life skills so as to lead to greater patients independence.

 Key words: Thalassemia Major , Physical Activity , Quality of Life