The formation of films of valve metal oxides of the aluminum, zirconium, titanium, tantalum, niobium series with a thickness of about 100 nm by electrochemical anodization in an electrolyte based on a 1 % aqueous solution of citric acid is considered. The effect of films of anodic oxides of valve metals with a built-in electret charge on the process of blood hemostasis when it contacts the surface of oxide films is studied. It is found that films of oxides with a negative electric charge (oxides of aluminum and zirconium) slow down the process of blood hemostasis, and films of anodic oxides with a positive electric charge (oxides of niobium and tantalum) accelerate it. Recommendations are given for the use of coatings with a negative electric charge as implant coatings to ensure a thromboresistant effect. Positively charged valve metal oxides can be used in wound treatment to stop bleeding.

The article presents the calculation of the structural and electronic characteristics of a conjugate consisting of the drug carboplatin (C₆H₁₂N₂O₄Pt) and a fullerenol (C₆₀(OH)₂₄) nanocarrier by the HF-3c method. Optimization of the geometric structure of the conjugate in an aqueous medium was carried out using the same level of theory and the polarizable continuum model. To clarify the nature of the intermolecular bond and assess the strength of the interaction between the carboplatin molecule and fullerenol, a topological analysis of the mechanisms of non-covalent interaction was performed based on the quantum theory of atoms in molecules. Individual paired atomic non-covalent interactions in the conjugate were analyzed and their energies were estimated using the correlation between the interaction energy and the characteristics of the electron density at the critical points of the bonds. It is shown that the conjugate is formed due to weak interaction forces between carboplatin and fullerenol, ensuring the release of the drug when delivering it to the corresponding DNA region without significant energy costs. The studied conjugates can be used for targeted drug delivery.

Since loss of working capacity and disability associated with respiratory diseases are caused by bronchial asthma and chronic obstructive pulmonary disease in 2/3 of cases, there is a need for technical support for early detection of these diseases. The developed diagnostic complex is based on an evolutionary mathematical model of the human respiratory system, describing the processes of gas exchange between the atmosphere and the lungs and between the lungs and blood. The complex allows analyzing such respiratory system parameters as arterial blood hemoglobin oxygen saturation, heart rate and respiratory rate. The complex is suitable for onetime (screening) measurements, as well as long-term (night/daily) monitoring. The corresponding software has been developed that allows analyzing the desaturation index, apnea-hypopnea index, photoplethysmogram, and visualizing the breathing process. The complex implements a standardized six-minute walk load test. This allows identifying respiratory failure, assessing its severity and conditions of occurrence. During the testing at a health resort, it was possible to diagnose obstructive apnea-hypopnea syndrome at an early stage in people who were unaware of the disease. The choice of a health resort was due to the comfortable conditions for conducting night monitoring, the availability of time and the desire of people to take care of their health and undergo diagnostics. 

Electrocardiography is an important diagnostic method that allows assessing the electrical activity of the heart. Its use allows diagnosing cardiovascular diseases at early stages, preventing their progression and development of complications. However, not all pathologies can be detected during a short-term study. If the presence of such dis eases is suspected, a method of long-term recording of the electrocardiogram is used. The quality of its recording during long-term recording largely depends on the electrodes used. Today, the most common are electrodes with silver chloride coating, showing good results for a short time. However, their use for more than 24 hours leads to signal distortion and irritation of the patient’s skin due to dehydration and surface degradation. The article pre sents the results of studies of materials intended for the manufacture of dry electrodes, their properties and influence on the indicators obtained during the examination.

It is possible to improve the quality of treatment of patients using dental implants by strengthening the bone–dental implant connection with a weak direct current. Titanium electrodes simulating dental implants were used in the in vitro experiment. The electrodes were placed in collected human venous blood. In the experimental group, physiotherapy procedures were performed for 10 minutes using the developed device at a current of 15–20 μA. In the control group, titanium plates were placed in blood without electric current for 10 minutes. In the studied samples, the adhesion density of blood clots to the titanium plates, the thickness of blood clots, the number of platelets and erythrocytes were studied. It was found that the effect of an electric current of 15–20 μA on a blood clot through titanium plates contributes to thickening and compaction of blood clots on the surface of the electrodes. The number of red blood cells and platelets in the blood clot increases, which can have a positive effect on the process of osseointegration.

To improve the results of diagnostics of anatomical structures in dentistry, a method such as cone-beam computed tomography is used, which provides extended visualization of the anatomical structures of the dental system and adjacent areas, including the cervical region, upper respiratory tract, etc. To improve the results of diagnostics of patients with diseases of the temporomandibular joints, an algorithm for analyzing a computer image of the cervicocranial region is proposed, which has diagnostic reproducibility, allows determining the asymmetry of the mutual arrangement of anatomical structures, detecting degenerative-dystrophic and other changes in the articulating surfaces. This method helps to identify the etiological factors in the development of diseases of the temporomandibular joints, increases the effectiveness of treating other diseases of the cervicocranial region.

Generative diffusion models are a well-established method for generating high-quality images. However, there are studies that show that diffusion models are less privacy-friendly than generative models, such as generative adversarial networks and a growing family of their modifications. The discovered vulnerabilities require in-depth study of various security aspects. This is especially important for sensitive areas such as medical image analysis tasks and their practical applications. The paper describes a method for detecting image patterns presented in generated images that can potentially be identified in real CT images of patients with pulmonary tuberculosis. The method includes the following main procedures: correlation of pairs of generated and real images to pre-select pairs that involve further analysis; calculation of correlation statistics using direct and inverse Fisher transforms; performing affine image registration and calculating pairwise similarity scores; nonlinear (elastic) image registration and recalculation of similarity scores to highlight the most similar/dissimilar image areas.

Directional contact diathermy is one of the most promising methods of physiotherapy. To study it, biophysical modeling of the effect of capacitive-resistive energy transfer (TEKAR therapy, or TR therapy) on biological tissue was carried out in the COMSOL Multiphysics environment using the finite difference method. A model of a biological object exposed to TR therapy was created. The visualization of the distribution of temperature and electric potential in the volume of the model is carried out. The dependence of the heating intensity on the frequency of alternating current is determined. The dynamics of temperature changes in each layer of biological tissue is shown.

The search for anatomical layers in lung CT images will simplify the task of diagnosis and treatment planning, as well as automate the process of image partitioning when preparing a training sample. The paper proposes a methodology for comparison of neural network descriptors and selection of an optimal neural network method for searching for similar anatomical regions. Neural network approaches are compared with traditional methods and a hybrid search algorithm based on the joint use of traditional and neural network methods is proposed. Using the proposed algorithm, the neural network search result for anatomical patterns, expressed in mm to the searched layer, was improved by 47 % for the first ten heart-class images found and by 18 % for images with positions from 10 to 100. The final anatomical region search result was improved over using traditional approaches by 9.7 % for retrieved images with positions from 10 to 100 and by 2 % for the first ten retrieved images.

The article considers machine learning methods and neural networks for diagnosing neurological diseases (Alzheimer’s and Parkinson’s diseases) in patients based on voice analysis. Models of information about disease features (including frequency, jitter, mel-cepstral coefficients, etc.) extracted from voice data are presented. Various classifiers are used to train neural networks and recognize diseases. Among them are the GridSearchCV algorithm for optimizing the hyperparameters of the random forest classifier for recognizing Alzheimer’s disease (recognition accuracy is 87.6 %) and the KNN algorithm for training and testing on publicly available datasets of speech change features in patients with Parkinson’s disease. The KNN algorithm showed the best classification results compared to others, achieving an experimental accuracy of 94 % on the same datasets. It is noted that the use of multidimensional feature extraction and machine learning methods can improve the accuracy of early diagnosis of neurological diseases. 

This paper presents a multi-branch convolutional neural network designed for glaucoma diagnosis using optical coherence tomography biomarkers and synthetic image simulations. The network includes six branches, each targeting key anatomical features. Trained on a synthetic dataset, the model achieved a validation accuracy of 94.2 % and a training loss of 0.162, demonstrating effectiveness in distinguishing between different glaucoma types. The results also highlight the potential for further accuracy improvement, particularly in reducing classification errors between closely related conditions.

The bioelectrical activity of the masticatory and temporal muscles at rest and under voluntary ten  sion in patients with clinical signs of bruxism was assessed. An excess of the average amplitude values for the right and left masticatory and temporal muscles under voluntary tension was found in patients with clinical signs of bruxism compared to patients in the control group. The study of the average resting amplitude for the masticatory and temporal muscles in patients with signs of bruxism compared to patients in the control group allowed us to determine an increase in values for both the masticatory and temporal muscles. The obtained data indicate persistent functional disorders of the muscles of the maxillofacial region in patients with clinical signs of bruxism, which is characterized by a pronounced deviation in the values of the average and maximum amplitudes at rest and under voluntary tension, as well as asymmetry of the amplitude-frequency characteristics. Analysis of bioelectr ical activity data of masticatory and temporal muscles at rest and under voluntary tension after a course of comp lex therapy indicates a marked decrease in this indicator and its tendency to similar values in patients of the control group. The revealed asymmetry of bioelectrical activity of temporal muscles after the course of therapy was not determined, but it remained at the same values in the masticatory muscles proper, which is due to the complexi ty of the symptom complex, including bruxism and disorders of the masticatory-speech apparatus and requiring an expansion of the rapeutic methods of etiopathogenetic orientation. The effectiveness of the complex of treatment methods will be higher with the use of pathogenetic therapy.