This article presents a study on the approach to the development of a medical decision support system (DSS) for the selection of formulas for calculating the optical strength of intraocular lenses (IOLs) used in the surgical treatment of cataracts. The system is based on the methods of building recommendation systems, which allows you to automate the process of choosing an IOL and minimize the risk of human error. The implementation of the system in the practice of medical organizations is expected to be highly accurate and efficient, significantly reduce the time allowed for decision-making, as well as improve the results of surgical interventions.

Keywords: intraocular lens, ophthalmology, formulas for calculating optical strength, web application, machine learning, eye parameters, prognostic model, recommendation system, prediction accuracy, medical decision

Eye tracking (oculography) is a technology that allows recording the direction of human gaze on a visual stimulus. It’s application can provide researchers with valuable data on which elements of the environment are most attractive in various contexts, in areas such as marketing, psychology, etc. The aim of this work is to identify the pattern of human attention distribution on visual stimulus objects of different sizes using eye tracking technology. A webcam was used to record the subjects’ gaze movements while they were studying experimental images. The results of the experiments showed that larger objects in visual stimuli receive higher attention priority than smaller objects. This observation is true for both human-created works and images created by artificial intelligence (Kandinsky 3.1 is used in this study). The obtained results of the study will improve our understanding of how people perceive visual information, which can contribute to the creation of more effective approaches to interface development.

Keywords: eye tracking technology, attention priority, region of interest, number of eye gaze registrations, artificial intelligence, Vincent Van Gogh

The article discusses the methods and approaches developed by the authors for the recommendation system, which are aimed at improving the quality of rehabilitation of the patient during respiratory training. To describe the training, we developed our own language for a specific subject area, as well as its grammar and syntax analyzer. Thanks to this language, it is possible to build a devereve describing a specific patient's training. Two main methods considered in the article are applied to the resulting tree: "A method for analyzing problem areas during training by patients" and "A method for fuzzy search of similar areas in training". With the help of these methods, it is proposed to analyze the problem areas of patients' training during rehabilitation and look for similar difficult areas of the patient to select similar exercises in order to maintain the level of diversity of tasks and involve the patient in the process.

Keywords: Recommendation system, learning management system, rehabilitation, medicine, respiratory training, marker system, domain-specific language, Levenshtein distance

This paper considers the modern classification methods of breast cancer histopathology. The main purpose of the study is to conduct an extended test of the trained model on data that fundamentally differs from the training dataset. We chose a large Russian dataset with different types of classification as the training dataset. The dataset contains images with different resolutions and magnifications. As testing data, the same dataset was used, but the resolution, color balance, brightness, and contrast of the images were changed. The classes in the dataset were unbalanced, so we applied augmentation methods (flipping and rotation). The models ResNet 152, DenseNet 121, Inception_resnet_v2 were selected for training. The transfer learning approach was used for training. The preprocessing of images consisted of normalizing the values of all image channels in the range from 0 to 1. The models had good results with standard testing methods. The resolution change slightly reduced metrics. The change in color balance, brightness, and contrast significantly reduced all metrics. The test results show that elementary normalization is not enough for high-quality training of models resistant to changes in input data.

Keywords: neural network, model, machine learning, breast cancer, cancer classification, artificial intelligence, transfer learning, histopathology

The results of clinical trials are the main source of information in the implementation of medical activities in accordance with the principles of evidence-based medicine. At the moment, there are no information systems that would allow a doctor to select clinical studies within the framework of nosology that best match the profile of a particular patient, in order to further analyze their results and select therapy. The aim of the study was to improve the existing process of searching for clinical trials by using the prioritization method according to the inclusion criteria set by the doctor during the selection. To achieve this goal, the following tasks were implemented, namely, the process of selecting and searching for clinical trials by doctors was studied and the method of searching for clinical trials by doctors and the allocation of the necessary criteria was worked out. The team of authors proposed an algorithm for searching for clinical trials according to inclusion criteria, which in turn will significantly increase the effectiveness and reduce the time for searching and choosing therapy.

Keywords: clinical studies, criteria search algorithms, criteria search methods, including factors, search for the nearest class, services

The question of creating an automated accompaniment is still an undisclosed part within the current automation of the musical field. The construction of accompaniment is used not only in the musical field, but also in related ones. Automatically generated accompaniment is used in audio and video studios for advertising, by people with and without musical education. In this paper, the existing methods for constructing automated accompaniment, audio file formats will be considered, and the developed algorithm and method for automatic accompaniment generation will be described.

Keywords: accompaniment, auto generated accompaniment, auto accompaniment, melody, MIDI