The article describes the stages of development of electronic medical document management (EMD) in the Russian Federation healthcare based on structured electronic medical documents (SEMD), as the basis for the «digital transformation» of the industry, including key aspects of technology development, methodology and regulatory frameworks.
The main indicators of digital health performance in terms of volume and types of electronic documents recorded are presented. The main prospects for the development of EMD are described, including the extraction and use of SEMD data to solve the problems of medical care and management of the healthcare industry

The introduction of digital medical services, which has been actively pursued in recent years in the Russian Federation, is aimed at improving accessibility of medical care and the convenience of patient interaction with the health care system. However, age-related barriers to the use of these services by the elderly can partially offset this potential. In this regard, this paper studies the most pressing problems in the use of digital medical services by patients of older working age and searches for solutions to eliminate them

The aim of the study was to evaluate the performance of SMOTE, GAN and VAE data synthesis methods in the task of predicting postoperative atrial fibrillation (PoAF) and in-hospital mortality (IHM) in coronary heart disease (CH) patients after coronary artery bypass grafting (CABG).
Materials and methods. A single-center retrospective study was conducted, in which the medical history data of 999 patients with CHD undergoing elective CABG were analyzed. The end points of the study were PoAF and IHM. Development of predictive models was performed using machine learning methods: multivariate logistic regression (MLR), random forest (RF) and eXtreme Gradient Boosting (XGB). Nine data synthesis methods were used to generate new minority class samples: 5 SMOTE group methods, SOMO, GAN, WGAN and VAE methods.
Results. Comparison of quality criteria for the predictive models of PoAF and IHM, developed on the basis of real and synthetic data, showed that for the MLR and RF models, the use of synthetic objects was not associated with an increase in prediction accuracy. When using the XGB method to solve IHM prediction problem, in which the majority class volume was dominant (15 to 1), only the ProWRAS method was associated with an increase in prediction quality. When class imbalance is not significant (4 to 1), which corresponds to the PoAF end point, the use of data synthesis methods does not improve prediction quality.
Conclusion. The use of SMOTE, GAN and VAE methods does not guarantee an improvement in the accuracy of predictive models for PoAF and IHM in CHD patients after CABG

This study is aimed at developing a hardware-software system (HSS) for the rehabilitation of patients with mild (subclinical) and severe disorders of cognitive processes and motor functions of the upper extremities based on the application of multimodal biofeedback (BFB) including transcranial magnetic stimulation (TMS).
Materials and Methods: Electroencephalography (EEG) data with additional channels for electromyogram (EMG) recordings data of healthy volunteers were used in the work. The spatial filter, linear discriminant analysis, augmented covariance matrix method with classification in the space of tangents in the Riemann manifold, and support vector method were used to classify imaginary movements.
Results: Based on the neurophysiological study and literature analysis, an HSS was developed for rehabilitation of patients with mild (subclinical) and severe impairments of cognitive processes and motor functions. The developed real-time algorithms were shown to have an average accuracy of 86% for motor act classification, 75% for imagination with an animated visual stimulus, and 73% for imagination with a static visual stimulus.
Conclusions: An effective and versatile HSS based on modern BCI algorithms has been developed for rehabilitation of patients with cognitive and motor disorders

Background. The key functionality of the medical information system (MIS) is the maintenance of electronic medical records (EMR), which play an integral role in modern healthcare practice, allowing medical organizations to consistently collect, systematize and provide medical professionals with access to information on the diagnosis and treatment of patients. Despite the existence of a large volume of accumulated EMRs and a long history of their design and development, modern EMRs have a rather low quality of clinical information collected in them. Currently, there is no recommended approach to assessing the quality of EMR data.
Objective. To develop a methodology for assessing the quality of data contained in EMRs.
Materials and methods. Requirements for the procedure of EMR data quality assessment and calculation of the quality index based on the results of such procedure were collected and systematized. Based on the requirements, a methodology for data quality assessment was formed, approaches to its practical implementation were worked out for each stage of the methodology and specific examples of quality criteria calculations for the most common basic elements of EMC were given. Results. The paper presents a methodology for assessing the quality of EMR data, as well as an algorithm for calculating the final quality indices based on the Webiomed platform data. The methodology allows us to obtain not only an integral quality assessment, but also its components assessing different data quality parameters, as well as to detail the quality assessment for different EHRs elements.
Conclusion. The developed methodology allows to evaluate the basic elements of the EHRs. The proposed methodology also provides an approach and an algorithm for extending to any additional element of the EHRs

Background. The difficulty in diagnosing of hereditary connective tissue diseases (HDCTD) in children lies in the variability of signs of individual nosologic forms and lack of experience of physicians due to the low frequency of occurrence of these pathological conditions. Incorrect and untimely diagnosis often leads to negative consequences for the patient, including disability and death. Many pediatricians need consultative support from more experienced colleagues when diagnosing rare diseases.
The aim of this work is to create a system to support medical decision-making in the diagnosis of connective tissue dysplasia in children and its implementation in the form of a web application.
Materials and methods. The article presents the development of a medical decision support system that allows the average specialist to apply in his practice the experience accumulated by experts in the diagnosis of connective tissue dysplasia. The knowledge system was based on international criteria for the diagnosis of Marfan and Ehlers-Danlos syndromes. The database includes multidimensional information about the diseases in question, such as photographs of clinical manifestations and radiographs, which are intended to provide information support to the physician when entering patient data.
Results. With the help of experts, a database of product rules was formed, as well as a list of informative features for diagnosing the above syndromes, and heuristic algorithms for testing diagnostic hypotheses based on the analysis of the knowledge base were proposed. A web application was developed to perform differential diagnosis of Marfan syndrome and Ehlers-Danlo syndrome, including 13 types of this syndrome, and the system was validated on an array of 152 patients. Conclusion. The system developed by the authors helps to identify symptoms during patient examination, assess the degree of phenotypic manifestations, form diagnostic hypotheses, and justify the need for additional studies to confirm the diagnosis

Aim: to analyze the results of the implementation and use of a product with artificial intelligence (AI) technology in the practice of radiologists during mammographic examination.
Materials and methods: database of patients who underwent mammographic examination within the framework of medical examination of certain groups of the adult population and preventive medical check-ups, whose images were reviewed by specialists of the Reference Center of the Krasnoyarsk Regional Clinical Oncology Dispensary and AI. The results were processed using the StatTech 4.0.6 software. Discordance was considered for clinically significant discrepancies in which the patient's management tactics were changed.
Results: in the Krasnoyarsk Territory, the introduction of AI into the practice of radiologists during mammography examination led to an increase in diagnostically difficult categories of BI-RADS 3,4, which increased the workload on the Reference Center by 40.8%. There was a 1.9% decrease in the discordance rate compared to the period when AI was not used in the region, indicating that doctors are not simply accepting the AI results and sending them to the Reference Center for review, but are analyzing the resulting AI report, and the key decision rests with the radiologist. Conclusion: the use of AI in the practice of a radiologist has both positive and negative sides. The negative ones are mostly related to technical and organizational problems, eliminating which it is possible to improve the quality of mammographic studies and their description.