Iranian Journal of

---

Background: Few studies have investigated maternal leptin concentrations in women with pregnancies complicated by gestational diabetes mellitus (GDM), and these published results are conflicting. We examined the association between plasma leptin concentration and GDM risk.
Methods: As a cross-sectional study 741 pregnant women that referred to five university hospital clinics were recruited. The universal screening was performed with a GCT-50g and those with plasma glucose level ≥130mg/dl, were diagnosed as GDM if they had an impaired GTT-100g based on Carpenter and Coustan criteria. The level of insulin was measured during OGTT-100g. Also maternal plasma leptin concentrations were measured.
Results: GDM patients had higher age, parity, BMI, and serum leptin concentration as compare with normal pregnancies. In logistic regression model serum leptin levels were independent factor for GDM.
Conclusion: Serum leptin concentrations can predict GDM.

---

Background: Diabetes is such diseases that need high quality beside prevention such as correctly predict fluctuations in blood glucose levels. The main complications of the disease can be anesthesia, coma and even death. Today, in these patients, the correct dose of insulin determined based on experience or doctors knowledge, and interact between the patients and physician, although there is an inevitable human errors.

Methods: In this study based on applied method, 124 patients and 188 healthy subjects based on 12 features by Random Selection, Who had been referred to Research Center for Diabetic in Sabzevar university of Medical Science since 2006 to 2011 were studied. The proposed system has several subsystems, such as evolutionary algorithms (BPS 1) to select the most effective features, Data Mining Algorithms (SVM 2) to detect and classify the features from the non-effective features. Adaptive Neuro fuzzy systems (ANFIS 3) to estimate learn and adaptation in order to correctly predict have been used.

Results: In this study, we try to use artificial intelligence systems to determine the correct dose of insulin for diabetics. The proposed system combines the best attributes in the database in the form the interaction was able to achieve high accuracy with the lowest error. The proposed system based on best features in the database in the interaction form was able to achieve high accuracy with the lowest error. The proposed system in the form of composition and interaction with the subsystem was able to achieve carefully 84.1% in specificity, 91% in sensitivity and 92.9% in accuracy.

Conclusion: In this research, due to the importance of correct and timely determination of insulin for diabetics, a new method based on the combination of intelligent systems is presented. Thus, the results obtained in previous articles and studies provide significantly improved.

---

Background: On time diabetes diagnosis dramatically reduces the many injuries and damage in the community. Diabetes is a disease that requires a lot of care in addition to prevention, such as prediction the correct level of blood sugar fluctuations. The most important complications of such disease are anesthesia, coma and even death at final. Today, in these patients, determining the correct dose of insulin is based on the experience and knowledge of physicians along with the interaction of patients with them, although human error is inevitable.
Methods: This study includes 124 patients and 188 healthy suspects were examined based on 21 features which hold by 7 features for diagnosis and 14 features for predicting insulin dose. The proposed system was presented to identify or diagnose the disease at first, and finally the correct doses of insulin for patients have been determine. The proposed system has two stages (which include diagnosis and prediction) and several subsystems. In the diagnosis phase, some sub systems such as the Fuzzy system for the purpose of accurately estimating the disease progression in patients and the decision tree (DT) for the preparation of rules in the fuzzy system (the process of mapping the attribute space (individuals) to the output (the diagnostic result)) have used. Also, in the prediction phase of insulin dose, the BPSO algorithms are used to select the best features. Classification algorithms (SVMs) are used to categorize effective to non-effective and adaptive artificial neuropsychological (ANFIS) systems for ultimate patient prediction have used.
Results: The proposed system, based on the best features in the provided data base in the form of the combination and interaction, succeeded to achieve a 95.1% precision, of course due to comparing by other commonly used methods and its performance the proposed method have high precision.
Conclusion: The results were significantly improved compared to previous studies. Also, in comparison with the results of physicians, it is indicative of good performance in predicting the accuracy of the time series of glucose concentration because the proposed system succeeded in predicting blood sugar levels for up to 48 hours.

---

Background: Diabetes is one of the most dangerous and common diseases of the modern world. Since medical research usually has limited data available and medical data is very ambiguous, it seems appropriate to use the fuzzy model to find out the relationship between input and output in medical data. None of the previous articles of fuzzy regression have been used to predict complications of diabetes, including nephropathy. Therefore, in this study, a fuzzy regression model was used to predict nephropathy in a diabetic patient.
Methods: In the present study, GFR results of previous patient experiments were used to predict a deeper horizons of GFR and ultimately to predict renal disease. Chronic kidney disease has been stratified based on the amount of GFR, that fuzzy data has been constructed based on these levels. The GFR prediction was performed in the following steps. Step 1: Define fuzzy sets based on the GFR level, which is considered for each level of a fuzzy set. Step 2: Fuzzify patient data Based on fuzzy sets. Step 3: GFR prediction with fuzzy regression model. Step 4: Defuzzifying the predictions. Step 5: Evaluating the model efficiency. The RMSE error is used to compare the performance of the model.
Results: The results of GFR prediction showed that comparison RMSE was 10.09 with using simple linear regression model and 4.24 in fuzzy model.
Conclusions: fuzzy regression model can predict nephropathy in diabetic patients.

---

Background: Today, in most hospitals in Iran, there is an extensive database of patient characteristics that includes a large amount of information related to medical, family and medical records. Finding a knowledge model of this information can help to predict the performance of the medical system and improve educational processes.
Methods: Data mining techniques are analytical tools that are used to extract meaningful knowledge from a large data set. In this study, the information of 500 people referred to Shahid Bolandian Health Center in Qazvin has been used. In this research, a predicted model has been performed using decision tree data mining methods and neural network and Bayesian network.
Results: The decision tree model has the highest accuracy and the Bayesian network has the lowest accuracy in diagnosing diabetic patients, and consequently the decision tree has the least error and the Bayesian network has the highest error. The decision tree model with 95.68% had the highest accuracy in prediction.
Conclusion: Fat has the greatest effect in predicting diabetes and gender has the least effect in predicting diabetes. Based on the decision tree analysis, the rules obtained among the stated characteristics of age and sugar variables have the greatest effect in predicting the occurrence of diabetes (according to software analysis) and by creating a proper diet can prevent this disease Prevented.

---

Background: Diabetes entails a great quantity of deaths each year and a great quantity of people living with the disease do not find out their health status early sufficient. In this paper, we advance a data mining-based model for prematurely diagnosis and prediction of diabetes.
Methods: Although K-means is simple and can be utilized for a vast diversity of data kinds, it is wholly sensitive to initial locations of cluster centers which specify the final cluster result, which either enables an efficiently and adequate clustered dataset for the logistic regression model, or presents a lesser amount of data as a result of wrong clustering of the main dataset, thereby restricting the proficiency of the logistic regression model. The main purpose of this study is was to specify procedures of ameliorating the k-means clustering and logistic regression accuracy consequence. Therefore, our algorithm comprises of principal component analysis technique, k-means technique and logistic regression model.
Results: The results obtained from this study show that the ability to obtain the result of K-means clustering accuracy is much higher than what other researchers have obtained in similar studies. Also, compared to the results obtained from other algorithms, the logistic regression model was implemented at an improved level in predicting the onset of diabetes. Another real advantage is that the proposed algorithm was able to successfully model a new dataset.
Conclusion: In general, the proposed approach can be effectively used in predicting and early diagnosis of diabetes.