Machine learning as new promising technique for selection of significant features in obese women with type 2 diabetes.

Background The global trend of obesity and diabetes is considerable. Recently, the early diagnosis and accurate prediction of type 2 diabetes mellitus (T2DM) patients have been planned to be estimated according to precise and reliable methods, artificial networks and machine learning (ML). Materials and methods In this study, an experimental data set of relevant features (adipocytokines and anthropometric levels) obtained from obese women (diabetic and non-diabetic) was analyzed. Machine learning was used to select significant features [by the separability-correlation measure (SCM) algorithm] for classification of women with the best accuracy and the results were evaluated using an artificial neural network (ANN). Results According to the experimental data analysis, a significant difference (p < 0.05) was found between fasting blood sugar (FBS), hemoglobin A1c (HbA1c) and visfatin level in two groups. Moreover, significant correlations were determined between HbA1c and FBS, homeostatic model assessment (HOMA) and insulin, total cholesterol (TC) level and body mass index (BMI) in non-diabetic women and insulin and HOMA, FBS and HbA1c, insulin and HOMA, systolic blood pressure (SBP) and diastolic blood pressure (DBP), BMI and TC and HbA1c and TC in the diabetic group. Furthermore, there were significant positive correlations between adipocytokines except for the resistin and leptin levels for both groups. The excellent (FBS and HbA1c), good (HOMA) and fair (visfatin, adiponectin and insulin) discriminators of diabetic women were determined based on specificities and sensitivities level. The more selected features in the ML method were FBS, apelin, visfatin, TC, HbA1c and adiponectin. Conclusions Thus, the subset of features involving FBS, apelin, visfatin and HbA1c are significant features and make the best discrimination between groups. In this study, based on statistical and ML results, the useful biomarkers for discrimination of diabetic women were FBS, HbA1c, HOMA, insulin, visfatin, adiponectin and apelin. Eventually, we designed useful software for identification of T2DM and the healthy population to be utilized in clinical diagnosis.

Polymorphism rs9939609 of Fat Mass and Obesity-associated Gene Correlation with Leptin Level of Obese Women Suffered from Type 2 Diabetes.

BACKGROUND: Recent studies reported that Fat Mass and Obesity-associated gene (FTO) single nucleotides polymorphisms (SNPs), especially rs9939609, have association with obesity and type 2 diabetes mellitus. On the other hand, many researches confirmed that leptin, an adipocytokine, is related to the obesity and Body Mass Index (BMI) in patients who suffered from Type 2 Diabetes (T2DM). OBJECTIVE: In this study, the correlation of FTO rs9939609 polymorphism and leptin level was investigated in the obese women who suffered from T2DM. METHODS: In case-control study, metabolic and anthropometric parameters, and leptin level of 38 obese diabetic and 38 non-diabetic women were investigated. Genotyping of rs9939609 FTO gene was completed by sequencing of PCR amplicons for all cases. RESULTS: According to the results, FBS, age, HbA1c, insulin level, HOMA index and leptin level showed statistically significant difference between diabetic and non-diabetic women (P < 0.05). Based on the adjusting of FTO rs9939609 SNP with anthropometric and metabolic parameters, no significant difference was found between the three genotypes (AA, TA and TT) in non-diabetic women (P > 0.05). But, in the diabetic group, only TC had significant difference and mean of TC was higher in mutant genotypes (AA and TA) than wild genotype (TT). Also, BMI, insulin, LDL and HDL showed negative correlation with leptin level in both groups but these correlations were not statistically significant. CONCLUSION: The results of our study (with little sample size) showed that the mean of leptin level in diabetic women was lower than non-diabetic women (significant difference). However, the level of leptin was not statistically significant between three genotypes, and odds ratio of rs9939609 was higher in diabetic women in comparison with non-diabetic women.

Correlation of Resistin Serum Level with Fat Mass and Obesity-Associated Gene (FTO) rs9939609 Polymorphism in Obese Women with Type 2 Diabetes.

AIMS: The aim of this study was to detect any association of fat mass and obesity-associated (FTO) rs9939609 variant to metabolic and anthropometric parameters and resistin level as adipokines in Iranian obese women with type 2 diabetes mellitus. MATERIAL AND METHODS: Totally, 42 diabetic and 36 non-diabetic women were selected. The PCR amplicons of FTO gene were sequenced and metabolic, anthropometric parameters and resistin level were measured. RESULTS: Serum resistin concentrations were not different between diabetic and non-diabetic subjects (p>0.05), while resistin level in diabetic group with AA genotype was lower than that with other genotypes in the same group. In rs9939609 SNP adjusted analysis, insulin and HOMA levels were high in AA genotype. While levels of FBS and HbA1c were higher in AA and AT genotypes. In diabetic group, only TG showed significant difference among three genotypes and mean of TG was higher in TA genotype. No significant correlation between resistin and anthropometric and metabolic parameters was found except for DBP in diabetic patients. CONCLUSION: There was no significant association between rs9939609 and resistin serum level in type 2 obese diabetic women while percentile ranges (25th, 50th and 75th) of resistin concentrations was high in diabetic group.

The Effect of Thickness on the Sealing Ability of CEM Cement as a Root-end Filling Material.

Background and aims. Different materials have been used for root-end filling during surgical endodontic treatment. The aim of this in vitro study was to evaluate the dye penetration in different thicknesses of calcium enriched mixture (CEM) cement as root-end filling material. Materials and methods. Following root canal filling in 70 extracted human single-rooted premolar teeth, the apical 3 mm of their root-ends was resected; the root-end cavities with depths of 1, 2 and 3 mm were prepared by ultrasonic retrotips and filled with CEM cement. After setting of cement, the roots were immersed in 2% Rhodamine B and the dye leakage was measured under stereomicroscope (×16) using Image J software. The data were analyzed by one-way ANOVA and Bonferroni post hoc tests at 5% significance level. Results. The means and standard deviations of dye penetration in the 1, 2, and 3 mm groups were 3395.5±1893.4, 3410.4±1440.5, and 2581.6±1852.9 µm, respectively. The one-way ANOVA analysis indicated significant differences (P < 0.001); however, the Bonferroni post hoc test revealed that only the positive control group differed significantly from the experimental groups (P < 0.001). Conclusion. The findings demonstrated CEM cement to have an adequate root-end sealing ability in 3-mm thickness.