In this work, we consider the flexible neuro-fuzzy systems of the Mamdani-type. When designing such systems to solve approximation problem, we should choose triangular norms used in inference and aggregation operators. This can be done by trial and error. In this work, we propose an algorithm that allows in an automatic way to choose the types of triangular norms in the learning process. The task of this algorithm is also an automatic selection of parameters of all functions describing the system. The algorithm uses an evolutionary strategy for its action and has been tested using well-known approximation benchmarks.

OBJECTIVES: Atopic dermatitis (AD) is an increasingly common, chronic, relapsing, inflammatory skin disease characterized by impaired epidermal barrier function and cutaneous inflammation. The prev...

The aim of this study was to assess the correlations of clinical features of patients with moderate and severe courses of COVID-19, comorbidity (endocrine, autoimmune, cardiovascular, oncological, and pulmonary diseases), and alleles of the HLA class II system genes. One hundred COVID-19 patients hospitalized in the Endocrinology Research Centre, Moscow, Russia, were analyzed for age, gender, smoking, comorbidity, and invasive mechanical ventilation. Computer tomography was used to assess the severity of the disease. HLA-DRB1, HLA-DQA1, and HLA-DQB1 alleles were identified in samples from 100 patients and samples from 327 randomly selected individuals collected in the prepandemic period (control group). There was no association of gender, age, weight, body mass index, smoking, and comorbidity with the severity of COVID-19. Allele DQB1*06:02-8 was more common in patients (p < 0.00005), and DQB1*06:01 and DQB1*05:03 were more common in the control group (p < 0.00005, and p = 0.0011, respectively). DQB1*06:02-8 can probably be considered as predisposing to moderate and severe COVID-19, and DQB1*06:01 can be considered as protective. No association of these alleles with comorbidity was found. Our results suggest that carriers of predisposing alleles, with cardiovascular and non-autoimmune endocrine diseases, should take more stringent preventive measures, and if infected, a more aggressive COVID-19 treatment strategy should be used.

BACKGROUND:Over the past decades, the growth of overweight and obesity among the population, especially significant in children, is registered everywhere. To assess the dynamics of the obesity epidemic and to monitor the effectiveness of preventive interventions in the regions, it is recommended that monitoring be carried out in the regions to ensure regular measurement of body weight. AIMS:to assess the dynamics of the frequency of overweight and obesity in children of primary school age in the Tyumen region. METHODS:a survey of children aged 811 years old residing in the Tyumen region in 2008 (n=390) and in 2017 (n=468) was conducted. The choice of territories in 2008 was carried out by the cluster method in 2008 and in 2017. The studies were conducted by expeditionary method with the departure of a team of doctors in the territory with the measurement of height and body weight and determination of the body mass index (BMI). The results were evaluated according to the SDS BMI guidelines. To compare the frequency of occurrence of qualitative features, the chi-square test () was used, to compare samples by quantitative characteristics, Student's t-criterion was used. The critical level of significance (p) was checked for statistical hypotheses to be 0.05. RESULTS:In 2017, in the Tyumen region, an increase in the frequency of obesity in children of primary school age is 2.4 times higher than in 2008 (6.7% in 2008, 15.8% in 2017), in boys as in girls. Overweight and obesity are more often diagnosed in boys in 2017 (40.0%). Girls 811 years in 2017 compared with 2008 increased the frequency of both obesity and overweight. CONCLUSION:In 2017, in the Tyumen region, an increase in the frequency of obesity in children of primary school age is 2.4 times higher than in 2008 (6.7% in 2008, 15.8% in 2017), as in boys, and for girls. Overweight and obesity are more often diagnosed in boys in 2017 (40.0%). Girls 811 years in 2017 compared with 2008 increased the frequency of both obesity and overweight.

SUMMARY The index used in Russia to predict mortality in patients with burns, the Frank index, needs to be revised because it has a low prognostic value.TARGET Modify the Frank index to increase its predictive value for mortality.MATERIAL AND METHODS A retrospective study included 307 patients with skin burns. We added the age of the patient to the Frank index (FI) formula and changed the score for inhalation trauma (IT). We compared the discriminatory power and predictive value of FI and the Revised Frank Index (RFI) using statistical analysis methods.RESULTS Adding the absolute number of years of the patient and 30 points for IT to the FI formula improved the discriminatory power and predictive value of RFI, which is calculated by the formula ∑ = S_{surface burns} (% b.s. ) + 3*S_{surface burns} (% b.s. ) + age (full years) + 30 (points for IT).CONCLUSION The predictive power of the revised Frank index is higher than the Frank index currently used. The threshold value of the revised Frank index, dividing the forecast into favorable and unfavorable, is score 130.