Purpose. To present data on testing the program, which allows optimizing audiological monitoring in children with risk factors for the development of hearing loss and deafness.Characteristics of children and research methods. 217 children who underwent audiological monitoring at the consultative аnd diagnostic center in Morozov Children’s City Clinical Hospital were examined. The research was a prospective longitudinal study with cross-sectional elements. The children were divided into 2 groups. The first group (main) consisted of 136 children who underwent audiological monitoring based on the developed program, and the second (comparison) included 81 children (the program was not applied). Statistical software packages SPSS and Epi info were used to process the obtained data.Results. In the main group, the most common age of children with primary treatment was (3.0 ± 0.5) months, and in the comparison group — (6.0 ± 0.5) months. In the main group, in the period of (3.0 ± 0.5) months of life, out of 129 children, neurosensory hearing loss was detected in 27 (21.0%), in the period of (6.0 ± 0.5) in 19 of 134 (14.0%), and in the periods of (9.0 ± 0.5) and (12.0 ± 0.5) in 19 (13.4%) and 5 of 136 children, respectively. In 22 children out of 136, hearing decline was transient. In the comparison group at the age of (3.0 ± 0.5) months, neurosensory hearing loss was detected in 2 children, at (6.0 ± 0.5) months in 4 out of 15, at (9.0 ± 0.5) in 1 child out of 25, and at (12.0 ± 0.5) in 9 patients out of 35 children.Conclusion. The application of the developed program will allow neonatologists and primary care physicians to fully comply with the deadlines for audiological monitoring.

The application of artificial neural networks (ANNs) to mathematical modelling in microbiology and biotechnology has been a promising and convenient tool for over 30 years because ANNs make it possible to predict complex multiparametric dependencies. This article is devoted to the investigation and justification of ANN choice for modelling the growth of a probiotic strain of Bifidobacterium adolescentis in a continuous monoculture, at low flow rates, under different oligofructose (OF) concentrations, as a preliminary study for a predictive model of the behaviour of intestinal microbiota. We considered the possibility and effectiveness of various classes of ANN. Taking into account the specifics of the experimental data, we proposed two-layer perceptrons as a mathematical modelling tool trained on the basis of the error backpropagation algorithm. We proposed and tested the mechanisms for training, testing and tuning the perceptron on the basis of both the standard ratio between the training and test sample volumes and under the condition of limited training data, due to the high cost, duration and the complexity of the experiments. We developed and tested the specific ANN models (class, structure, training settings, weight coefficients) with new data. The validity of the model was confirmed using RMSE, which was from 4.24 to 980% for different concentrations. The results showed the high efficiency of ANNs in general and bilayer perceptrons in particular in solving modelling tasks in microbiology and biotechnology, making it possible to recommend this tool for further wider applications.

A group of Russian specialists dealing with the problems of auditory function in premature babies touches upon important issues of early detection of hearing loss and deafness in this contingent of children born before the date of physiological birth. The purpose of the article was to argue the need for a personalized approach to the diagnosis of auditory function in premature and full-term babies depending on the timing of gestation and their somatic state at the time of birth, as well as the comprehensive rehabilitation of children with hearing loss and deafness. The article describes the advantages of the previously developed computer program Multiplicity of audiological monitoring in children of the first year of life with risk factors for hearing loss and deafness.

The advantages and disadvantages of using clustering methods using the Kohonen neural network and the density-based spatial clustering of applications with noise (DBSCAN) algorithm for solving problems of analyzing multidimensional medical data are presented. An example of using clustering methods to identify the relationship between the development of sensorineural hearing loss in newborns and the disease caused by the COVID-19 virus in the children themselves or in their mothers during pregnancy is analyzed. The considered methods are also used to prepare recommendations for monitoring newborns depending on the results of clustering data on their examination and anamnesis using various methods. The use of clustering methods in medicine expands the arsenal of tools for researchers and practicing doctors who use them for the purpose of diagnosing, predicting the course of diseases, the development of pathologies, and forming a treatment plan.