Tehran University Medical Journal

Background: Regarding the increased risk of developing type 2 diabetes in pre-diabetic people, identifying pre-diabetes and determining of its risk factors seems so necessary. In this study, it is aimed to compare ordinary logistic regression and robust logistic regression models in modeling pre-diabetes risk factors.
Methods: This is a cross-sectional study and conducted on 6460 people, over 30 years old, who have participated in the screening of diabetes plan in Mashhad city that it was done by Mashhad University of Medical Sciences from October to December 2010. According to the fasting blood sugar criteria, 5414 individuals were identified as healthy and 1046 individuals were identified as pre-diabetic. Age, gender, body mass index, systolic blood pressure, diastolic blood pressure and waist-to-hip ratio were measured for every participant. The data was entered into the Microsoft Excel 2013 (Microsoft Corp., Redmond, WA, USA) and then analysis of the data was done in R Project for Statistical Computing, Version R 3.1.2 (www.r-project.org). Ordinary logistic regression model was fitted on the data. The outliers were identified. Then Mallow, WBY and BY robust logistic regression models were fitted on the data. And then, the robust models were compared with each other and with ordinary logistic regression model according to goodness of fit and prediction ability using Pearson's chi-square and area under the receiver operating characteristic (ROC) curve respectively.
Results: Among the variables that were included in the ordinary logistic regression model and three robust logistic models, age, body mass index and systolic blood pressure were statistically significant (P< 0.01) but waist-to-hip ratio was not statistically significant (P> 0.1). There were 552 outliers with misclassification error in the ordinary logistic regression model. Pearson's chi-square value and area under the ROC curve value in the Mallow model were almost the same as for ordinary logistic regression model. But it was relatively higher in BY and WBY models.
Conclusion: Based on results of this study age, overweight and hypertension are risk factors of prediabetes. Also, WBY and BY models were better than ordinary logistic regression model, according to goodness of fit criteria and prediction ability.

Background: Diabetes mellitus has several complications. The Late diagnosis of diabetes in people leads to the spread of complications. Therefore, this study has been done to determine the possibility of predicting diabetes type 2 by using data mining techniques.
Methods: This is a descriptive-analytic study that was conducted as a cross-sectional study. The study population included people referring to health centers in Mohammadieh City in Qazvin Province, Iran, from April to June 2015 for screening for diabetes. The 5-step CRISP method was used to implement this study. Data were collected from March 2015 to June 2015. In this study, 1055 persons with complete information were included in the study. Of these, 159 were healthy and 896 were diabetic. A total of 11 characteristics and risk factors were examined, including the age, sex, systolic and diastolic blood pressure, family history of diabetes, BMI, height, weight, waistline, hip circumference and diagnosis. The results obtained by support vector machine (SVM), decision tree (DT) and the k-nearest neighbors algorithm (k-NN) were compared with each other. Data was analyzed using MATLAB® software, version 3.2 (Mathworks Inc., Natick, MA, USA).
Results: Data analysis showed that in all criteria, the best results were obtained by decision tree with accuracy (0.96) and precision (0.89). The k-NN methods were followed by accuracy (0.96) and precision (0.83) and support vector machine with accuracy (0.94) and precision (0.85). Also, in this study, decision tree model obtained the highest degree of class accuracy for both diabetes classes and healthy in the analysis of confusion matrix.
Conclusion: Based on the results, the decision tree represents the best results in the class of test samples which can be recommended as a model for predicting diabetes type 2 using risk factor data.

Background: Diabetes mellitus as a chronic disease is the most common disease caused by metabolic disorders and it is one of the most important health issues all around the world. Nowadays, data mining methods are applied in different fields of sciences due to data mining methods capability. Therefore, in this study, we compared the efficiency of data mining methods in predicting type 2 diabetes.
Methods: In this cross-sectional study, the data of 7,000 participants in the Diabetes Screening Project in Samen, Mashhad City, Iran, were considered in 2016. There were 540 untreated diabetic patients. The Samen Project was included in the routine examinations of diabetes patients like blood glucose, eyes health, nephropathy, and legs health. So, in order to maintain balance, 600 healthy individuals were selected in a proportional volume sampling in this study. Therefore, the total sample size was 1140 people. In this study, people with diabetes aged over 30 years old were enrolled and participants with the previous history of type 2 diabetes, with normal blood glucose due to drug use or other issues at the time of the study, were excluded.
Results: All three models (Logistic regression, simple Bayesian and support vector machine models) had the same test accuracy (86%), however, in terms of area under the receiver operating characteristic (ROC) curve (AUC), logistic regression and simple Bayesian models had better performance (AUC=90% against AUC=88%). In the simple Bayesian model and logistic regression, body mass index (BMI) and age variables were the most important variables, while BMI and blood pressure variables were the most important factors in the support vector machine model.
Conclusion: According to the results, all three models had the same accuracy. In terms of area under the curve (AUC), logistic and simple Bayes models had better performance than the support vector machine model. Totally all three models had almost the same performance. Based on all three models, BMI was the most important variable.

Background: Gestational diabetes mellitus (GDM) is one of the most common metabolic disorders in pregnancy, which is associated with serious complications. In the event of early diagnosis of this disease, some of the maternal and fetal complications can be prevented. The aim of this study was to early predict gestational diabetes mellitus by two statistical models including artificial neural network (ANN) and decision tree and also comparing these models in the diagnosis of GDM.
Methods: In this modeling study, among the cases of pregnant women who were monitored by health care centers of Kermanshah City, Iran, from 2010 to 2012, four hundred cases were selected, therefore the information in these cases was analyzed in this study. Demographic information, mother's maternal pregnancy rating, having diabetes at the beginning of pregnancy, fertility parameters and biochemical test results of mothers was collected from their records. Perceptron ANN and decision tree with CART algorithm models were fitted to the data and those performances were compared. According to the accuracy, sensitivity, specificity criteria and surface under the receiver operating characteristic (ROC) curve (AUC), the superior model was introduced.
Results: Following the fitting of an artificial neural network and decision tree models to data set, the following results were obtained. The accuracy, sensitivity, specificity and area under the ROC curve were calculated for both models. All of these values were more in the neural network model than the decision tree model. The accuracy criterion for these models was 0.83, 0.77, the sensitivity 0.62, 0.56 and specificity 0.95, 0.87, respectively. The surface under the ROC curve in ANN model was significantly higher than decision tree (0.79, 0.74, P=0.03).
Conclusion: In predicting and categorizing the presence and absence of gestational diabetes mellitus, the artificial neural network model had a higher accuracy, sensitivity, specificity, and surface under the receiver operating characteristic curve than the decision tree model. It can be concluded that the perceptron artificial neural network model has better predictions and closer to reality than the decision tree model.

Background: Celiac disease is a chronic inflammation of small intestine which is caused by an increased permanent sensitivity to a protein named gluten. This protein is present in some cereals such as wheat, barley, and rye. The immunologic response to this protein can cause clinical symptoms in people with specific human leukocyte antigens (HLAs) (including HLADQ2 or HLADQ8). Most studies have reported an increased incidence of celiac disease in patients with diabetes mellitus type I. This study aimed to determine the prevalence of the celiac disease in patients with diabetes mellitus type I under the age of 18 years old.
Methods: This cross-sectional, analytic descriptive study was performed on forty children with diabetes mellitus type I in Sanandaj Diabetes Association (Kurdistan University of Medical Sciences), Iran, from September 2012 to September 2013. After obtaining consent from their parents, demographic data, including gender, age, family history of diabetes, duration of illness, symptoms of celiac disease, were recorded in the questionnaire. The measurement of the tissue transglutaminase (tTG) antibody and total immunoglobulin type A in the serum was necessary for the screening of celiac disease. Therefore in the laboratory, 5 ml of the venous blood sample was taken and then the serum levels of tTG antibody (from immunoglobulin type A) and total serum levels of this immunoglobulin were measured by the enzyme-linked immunosorbent assay (ELISA) method. Upper endoscopy with multiple biopsies from small intestine was performed in patients with positive serological screening. Finally, the disease was evaluated by histological finding.
Results: Forty children with diabetes mellitus type I included 19 boys (47.5%) and 21 girls (52.5%) were enrolled in the study. The mean age of these patients was 10.53±4.05. The prevalence of celiac disease was 7.5% in these individuals. In the subjects, there was no significant relationship between gastrointestinal symptoms and celiac disease.
Conclusion: In the present study, the prevalence of the celiac disease in type 1 diabetic patients was 7.5% which is higher than the normal population.

Background: Coronary artery ectasia (CAE) is dilatation of an arterial segment to a diameter at least 1.5 times that of the adjacent normal coronary artery. The incidence of coronary artery ectasia is distinct in different countries that can be found in 1.2% to 5% of angiographic examinations.
Methods: This is a retrospective study that was conducted from September 2019 to February 2020 in Kermanshah University of Medical Sciences and the results were reported briefly. To obtain the desired articles, electronic searches were conducted in databases including the Scopus, PubMed, and Science Direct databases without time limited until October 2019. The keywords used were Coronary Artery Ectasia AND (Diabetes OR "Diabetes Mellitus"). This was done by two individuals separately and the final results were confirmed by a third person. Mixed method appraisal tool (MMAT) was used to evaluate the quality of studies. The structure of writing and the process of performing and reporting the study are based on the PRISMA checklist.

Results: After treatment in placebo group the level of LDL-C (median 0.90 mg/dl to 0.82, P=0.008) and HDL-C (median 0.40 mg/dl to 0.35, P=0.090) were decreased, while in the empagliflozin group the levels of LDL-C (median 0.87 mg/dl to 0.96, P=0.875) and HDL-C (median 0.38 mg/dl to 0.48), P=0.007) increased. Treatment with Empagliflozin and placebo had no significant effect on changing the levels of total cholesterol, TG and eGFR (P>0.05). The weight loss and FBS reduction in the empagliflozin group were significantly higher than placebo (P=0.001 and P=0.048, respectively).

Background: Vitamin B12 deficiency is one of the most well-known disorders due to long-term use of metformin due to interference with its absorption.
Methods: This double-blind randomized trial was conducted from June to October 2016 at Shahid Beheshti Hospital in Qom on 60 patients in the age group of 30 to 60 years with a history of type 2 diabetes for one to two years and taking metformin in the amount of one to two grams. Patients were divided into two groups of 30 people. The intervention group received metformin with 1 gram of calcium carbonate daily, and the control group received metformin without calcium. Each of the patients in the intervention group was given 200 calcium carbonate tablets. Vitamin B12 levels of the patients in both groups were measured before the start of the intervention, and they were evaluated in terms of neuropathy according to the Michigan questionnaire. Vitamin B12 of patients and neuropathy in two groups were measured before the intervention and after three months.
Results: There was a difference between the two groups in terms of gender, and no significant difference was observed between the mean ages in the two groups. The mean level of vitamin B12 before receiving calcium in group A (intervention) was lower than group B (control) (P=0.036) and after receiving calcium, the level of vitamin B12 in the intervention group increased (P=0.002). In the control group, the level of vitamin B12 decreased (P=0.030). (P=0.006), and in the control group there was no significant difference in the examination of neuropathy (P=0.2).

Conclusion: Oral calcium daily intake increases vitamin B12 levels in patients with type 2 diabetes and calcium may be able to moderate the decrease in serum vitamin B12 levels induced by metformin in patients with type 2 diabetes.

Background: Maternal diseases such as diabetes, hypertension, preeclampsia, hypothyroidism and epilepsy in pregnancy are associated with fetal and neonatal complications. The aim of this study was to compare the prognosis of neonates in maternal diseases.
Methods: This study was a cross-sectional study. The present study was performed on 600 preterm infants with mothers with diabetes, hypertension, preeclampsia, hypothyroidism and epilepsy. This study was done in Ghaem Hospital of Mashhad from March 2015 to April 2021 with available sampling. The data collection tool was a researcher-made checklist including infant (gestational age, Apgar score of the first minute, Apgar score of the fifth minute) and maternal (mode of delivery, prenatal care, premature rupture of the membranes) characteristics. Neonatal prognosis was compared at birth. All clinical and diagnostic examinations of newborns were performed by a neonatologist. Neonatal and maternal data in the group of newborns with normal mothers and newborns with maternal diseases were analyzed by Kolmogorov-Smirnov and Chi-square tests. The significance level was considered p≤0.05 in all cases.

Results: The results show that 161 newborns (28.90%) had normal mothers, 89 newborns (15.98%) had diabetic mothers, 117 newborns (21.01%) had hypertensive mothers, and 50 newborns (8.98%) had hypothyroid mothers. One hundred tweny newborns (21.72%) had mothers with preeclampsia, 19 newborns (3.41%) had mothers with epilepsy. Newborns with mothers with epilepsy had the lowest Apgar score of the first minute and the lowest gestational age and newborns with mothers with diabetes had the lowest Apgar score of the fifth minute. Mothers with hypothyroidism had the highest rate of premature rupture of the membranes and mothers with hypertension and preeclampsia had the highest incidence of cesarean section. Conclusion: Maternal diseases including diabetes, hypertension, preeclampsia, hypothyroidism and epilepsy affect the prognosis of neonates in terms of the severity of prematurity, premature rupture of the membranes, type of delivery, Apgar scores of the first and fifth minutes. Therefore, proper control and treatment of these diseases may improve neonatal prognosis.