Hyperinsulinemia is a condition characterized by excessively high levels of insulin in the bloodstream. It can exist for many years without any symptomatology. The research presented in this paper was conducted from 2019 to 2022 in cooperation with a health center in Serbia as a large cross-sectional observational study of adolescents of both genders using datasets collected from the field. Previously used analytical approaches of integrated and relevant clinical, hematological, biochemical, and other variables could not identify potential risk factors for developing hyperinsulinemia. This paper aims to present several different models using machine learning (ML) algorithms such as naive Bayes, decision tree, and random forest and compare them with a new methodology constructed based on artificial neural networks using Taguchi’s orthogonal vector plans (ANN-L), a special extraction of Latin squares. Furthermore, the experimental part of this study showed that ANN-L models achieved an accuracy of 99.5% with less than seven iterations performed. Furthermore, the study provides valuable insights into the share of each risk factor contributing to the occurrence of hyperinsulinemia in adolescents, which is crucial for more precise and straightforward medical diagnoses. Preventing the risk of hyperinsulinemia in this age group is crucial for the well-being of the adolescents and society as a whole.

Hyperinsulinemia is a condition with extremely high levels of insulin in the blood. Various factors can lead to hyperinsulinemia in children and adolescents. Puberty is a period of significant change in children and adolescents. They do not have to have explicit symptoms for prediabetes, and certain health indicators may indicate a risk of developing this problem. The scientific study is designed as a cross-sectional study. In total, 674 children and adolescents of school age from 12 to 17 years old participated in the research. They received a recommendation from a pediatrician to do an OGTT (Oral Glucose Tolerance test) with insulinemia at a regular systematic examination. In addition to factor analysis, the study of the influence of individual factors was tested using RBF (Radial Basis Function) and SVM (Support Vector Machine) algorithm. The obtained results indicated statistically significant differences in the values of the monitored variables between the experimental and control groups. The obtained results showed that the number of adolescents at risk is increasing, and, in the presented research, it was 17.4%. Factor analysis and verification of the SVM algorithm changed the percentage of each risk factor. In addition, unlike previous research, three groups of children and adolescents at low, medium, and high risk were identified. The degree of risk can be of great diagnostic value for adopting corrective measures to prevent this problem and developing potential complications, primarily type 2 diabetes mellitus, cardiovascular disease, and other mass non-communicable diseases. The SVM algorithm is expected to determine the most accurate and reliable influence of risk factors. Using factor analysis and verification using the SVM algorithm, they significantly indicate an accurate, precise, and timely identification of children and adolescents at risk of hyperinsulinemia, which is of great importance for improving their health potential, and the health of society as a whole.

In previous years, significant attempts have been made to enhance computer-aided diagnosis and prediction applications. This paper presents the results obtained using different machine learning (ML) algorithms and a special type of a neural network map to uncover previously unknown comorbidities associated with chronic diseases, allowing for fast, accurate, and precise predictions. Furthermore, we are presenting a comparative study on different artificial intelligence (AI) tools like the Kohonen self-organizing map (SOM) neural network, random forest, and decision tree for predicting 17 different chronic non-communicable diseases such as asthma, chronic lung diseases, myocardial infarction, coronary heart disease, hypertension, stroke, arthrosis, lower back diseases, cervical spine diseases, diabetes mellitus, allergies, liver cirrhosis, urinary tract diseases, kidney diseases, depression, high cholesterol, and cancer. The research was developed as an observational cross-sectional study through the support of the European Union project, with the data collected from the largest Institute of Public Health “Dr. Milan Jovanovic Batut” in Serbia. The study found that hypertension is the most prevalent disease in Sumadija and western Serbia region, affecting 9.8% of the population, and it is particularly prominent in the age group of 65 to 74 years, with a prevalence rate of 33.2%. The use of Random Forest algorithms can also aid in identifying comorbidities associated with hypertension, with the highest number of comorbidities established as 11. These findings highlight the potential for ML algorithms to provide accurate and personalized diagnoses, identify risk factors and interventions, and ultimately improve patient outcomes while reducing healthcare costs. Moreover, they will be utilized to develop targeted public health interventions and policies for future healthcare frameworks to reduce the burden of chronic diseases in Serbia.

This paper will present the results of a study on dietary habits in adolescents. The high school or adolescent era is a time of great physical and psychological changes, which cause instability and oscillations in the mood and behavior of high school students. Results obtained by interviewing secondary school students about eating habits and results obtained using a standardized questionnaire for the risk of type 2 diabetes were analyzed using a reliable statistical tool IBM SPSS Statistical, which offers a range of reliable analyzes and statistical tests. Previous research has shown that for each person with type 2 diabetes, one person finds out who does not know it. Discovery of pre-diabetes, in new potential patients, is necessary at the earliest age, when a number of factors affect lifestyles, such as irregular nutrition and obesity, physical inactivity, stress, and others become important for the development of this disease. Detection of risk levels in potential patients is important for both the individual and public health, and everyday clinical practice. After determining the degree of risk for a particular sample, a set of measures for a particular adolescent population will be recommended, so that the disease does not occur, or its onset will move for a later period of life.

Objective. Diabetes mellitus is a chronic disease in which the body either does not produce or inadequately uses the hormone of the pancreas, insulin. Health education work with this population of patients is an important aspect of treatment and health care, it aims to change harmful health behavior and prevent complications. The aim of the research is to examine the information and health habits of patients with diabetes mellitus, to determine the presence of factors that can affect the worsening of the condition and lead to complications of the disease. Methods. The research was conducted according to the type of cross-sectional study. To collect data, a questionnaire for patients with diabetes mellitus was used, which the authors constructed for this research. The research was conducted in the population of patients with diabetes, in the period June-August 2018. at the General Hospital in Valjevo. The sample consisted of 110 respondents. Results. In the observed sample, almost 2/3 (63%) of the respondents are overweight, and almost 3/4 (74%) of the respondents regularly control their blood sugar values. More than 1/2 (56%) were educated for glycemic self-control, 70% were informed about signs of hyperglycemia, 87% were signs of hypoglycemia. More than 1/3 of respondents are exclusively on insulin therapy, 87% adhere to the therapeutic regimen, 87% of the subjects are trained for insulin self-application. 90% of respondents go to check-ups regularly, and 97% think that the information they receive from health workers is useful. Conclusion. Healthcare professionals of all profiles, primarily doctors and nurses, should continuously conduct health education work with people with diabetes. The largest number of patients in the observed sample were informed about their disease and hygienic dietary regime. In order to make the results even more encouraging, it is necessary to intensify health education work at all levels of health care.