Sovremennye Tehnologii v Medicine最新文献

Chronic resuscitation patients who have survived the acute phase of a disease represent a fast-growing cohort of patients requiring specialized medical assistant in intensive care and resuscitation units (ICRU) for several months or years. The term "chronic critical illness" (CCI) was proposed for such patients in the mid-80s of the last century. Patients with CCI make up from 5 to 20% of ICRU. Over time, they develop homeostasis disorders resulting in multiple organ failure and death. Mortality in CCI exceeds that of the majority of malignant neoplasms and functional dependence remains in most of survivors. In the present review, the attempt is made to show the main links of CCI pathogenesis which, if acted upon, can prevent unfavorable outcome. The publications describing epidemiology of CCI, its outcomes, and clinical phenotype have been analyzed. Several researchers consider CCI as a result of persistent inflammation, immunosuppression, and catabolism syndrome. Some works show the importance of nutrition for ICRU patients. The role of gastrointestinal tract in CCI formation has been noted. The effect of intensive therapy on microbiota of the ICRU patients has been demonstrated. Microbiome disturbances in dysbiosis and sepsis have been considered, as well as the effect of intestinal microbiome on the distant organs. Post-intensive care syndrome is a significant constituent of CCI. The main sequelae of the syndrome, as well as the general questions of its prevention and treatment, have been denoted.

The aim of the study was to assess the capabilities of age determination (age group) at death using classification techniques by histomorphometric characteristics of osseous and cartilaginous tissue aging.

Materials and methods: The study material was a database containing the findings of morphometric researches of osseous and cartilaginous tissue histologic specimens from 294 categorized male corpses aged 10-93 years. For data analysis and classification we used modern machine learning methods: k-NN, SVM, logistic regression, CatBoost, SGD, naive Bayes, random forest, nonlinear dimensionality reduction methods (t-SNE and uMAP), and recursive feature elimination for feature selection.

Results: The used techniques (algorithms) provided effective representation of a complex data set (76 histomorphometric features), allowing to reveal the cluster structure inside the low dimensional feature space, thus fitting the classifier becomes even more reasonable. During feature selection, we estimated their importance for age group classification and studied the relationship between classification quality and the number of features inside the feature space. Data pre-processing made it possible to get rid of noise and keep most informative features, thereby accelerating a learning process and improving the classification quality. Data projection showed more well-defined cluster structure in the space of selected features. The accuracy of establishing certain groups was equal to 90%. It proves high efficiency of machine learning techniques used for forensic age diagnostics based on histomorphometric findings.

The aim of the study was to develop a methodology for conducting post-registration clinical monitoring of software as a medical device based on artificial intelligence technologies (SaMD-AI).

Materials and methods: The methodology of post-registration clinical monitoring is based on the requirements of regulatory legal acts issued by the Board of the Eurasian Economic Commission. To comply with these requirements, the monitoring involves submission of the review of adverse events reports, the review of developers' routine reports on the safety and efficiency of SaMD-AI, and the assessment of the system for collecting and analyzing developers' post-registration data on the safety and efficiency of medical devices. The methodology was developed with regard to the recommendations of the International Medical Device Regulators Forum and the documents issued by the Food and Drug Administration (USA). Field-testing of this methodology was carried out using SaMD-AI designed for diagnostic imaging.

Results: The post-registration monitoring of SaMD-AI consists of three key stages: collecting user feedback, technical monitoring and clinical validation. Technical monitoring involves routine evaluation of SaMD-AI output data quality to detect and remove flaws in a timely manner, and to secure the product stability. Major outcomes include an ordered list of technical flaws in SaMD-AI and their classification using evidence from diagnostic imaging studies. The application of this methodology resulted in a gradual reduction in the number of studies with flaws due to timely improvements in artificial intelligence algorithms: the number of flaws decreased to 5% in various aspects during subsequent testing. Clinical validation confirmed that SaMD-AI is capable of producing clinically meaningful outputs related to its intended use within the functionality determined by the developer. The testing procedure and the baseline testing framework were established during the field testing.

Conclusion: The developed methodology will ensure the safety and efficiency of SaMD-AI taking into account its specifics as intangible medical devices. The methodology presented in this paper can be used by SaMD-AI developers to plan and carry out the post-registration clinical monitoring.

Multigene testing using NGS (next-generation sequencing) provides a large amount of information and can detect multiple molecular alterations. Subsequent clinical interpretation is a time-consuming process necessary to select a treatment strategy. Existing databases often contain inconsistent information and are not regularly updated. The use of ESCAT levels of evidence requires a deep understanding of the nature of alterations and does not answer the question of which therapy option to select when multiple biomarkers with the same level of evidence are detected. To address these issues, we created the Clinical Relevance of Alterations in Cancer (CRAC) database on the relevance of detected alterations in specific genes, which are often analyzed as part of NGS panels. The team of oncologists and biologists assigned a CRAC score from 1 to 10 to each biomarker (a type of genomic alteration characteristic of specific genes) for 15 malignancies; an average score was entered into the database. CRAC scores are a numerical reflection of the following factors: therapy availability and the prospects of drug treatment with experimental drugs for patients with a particular type of tumor. A total of 134 genes and 15 of the most common tumor types have been selected for CRAC. The biomarker-nosology associations with CRAC scores in the range of 1-3 are the most frequent (n=2719 out of 3495; 77.8%), the least frequent ones (n=52 out of 3495; 1.5%) are with the highest CRAC scores 9 and 10. To estimate the practical effectiveness of the CRAC database, 208 reports on comprehensive molecular profiling were retrospectively analyzed; the applicability of CRAC was compared with the ESCAT level of evidence system. The highest CRAC scores corresponded to the ESCAT maximum levels of evidence: the range of scores 8-10 corresponded to evidence levels I and II. No biomarker within the same level of evidence was represented by the same CRAC score; the largest range of CRAC scores was observed for biomarkers of levels evidence IIIA and IV - from 2 to 10 and from 1 to 9, respectively. The use of CRAC scores allowed to identify additional 95 alterations with CRAC scores of 1-5 in the studied patients. The developed database is available at: https://crac.oncoatlas.ru/.

The aim of the study was to develop an algorithm for the selection of discriminating probes to identify a wide range of causative agents of human infectious diseases.

Materials and methods: The algorithm for selecting the probes was implemented in the form of the disprose (DIScrimination PRObe SElection) computer program written in the R language. Additionally, third-party software was used: the BLAST+ and ViennaRNA Package programs. The developed algorithm was tested by selecting specific probes for detecting Chlamydophila (Chlamydia) pneumoniae - an atypical bacterial pathogen causing community-acquired pneumonia (CAP). Nucleotide sequences for analysis were downloaded from the NCBI databank.

Results: An algorithm for the selection of specific probes capable of detecting human infectious pathogens has been developed. The algorithm is implemented in the form of the disprose modular program, which allows for performing all stages of the probe selection process: loading the nucleotide sequences and their metadata from available databanks, creating local databases, forming a pool of probes, calculating their physicochemical parameters, aligning the probes and sequences contained in local databases, processing and evaluating the alignment results. The algorithm was successfully tested and its performance was confirmed by selecting a set of probes for the specific detection of Chlamydophila pneumoniae. The specificity of the selected probes calculated in silico indicated a low risk of their nonspecific binding and a high potential of using them as molecular genetic diagnostic tools (DNA microarrays, PCR).

Conclusion: An algorithm for the selection of specific probes detecting a wide range of human pathogens in clinical biomaterial has been developed and implemented in the form of the disprose modular program. The probes selected using this program can serve as the functional basis of DNA-oriented microarrays able to identify causative agents of polyetiological diseases, such as CAP. Due to the flexibility and openness of the program, the scope of its application can be expanded.

Multiple studies in patients with obsessive-compulsive disorder (OCD) became the basis for revealing selective attention, inhibitory control, and working memory impairments, which correlates with an imbalance in the activity of the cortico-striatal-thalamic-cortical circuit associated with maintenance of cognitive control functions. Patients with OCD often demonstrate changes in the parameters of target-oriented eye movement reactions being a consequence of a possible impairment of the cognitive control neurophysiological framework. This review summarizes and analyzes data on cognitive control disorders in OCD obtained with eye movement recording techniques. It was established that the most often used are smooth pursuit eye movements tasks, memory-guided saccades, and anti-saccadic tasks. Data on smooth pursuit eye movements tasks and memory-guided saccades are contradictory, although they partially confirm selective attention and working memory impairment. Most studies on the anti-saccadic task identified impaired inhibitory control in patients with OCD. Similar disorders in form of increased latency and higher error rate in anti-saccades were also noted in the patients' first-degree relatives, which allows considering such disorders as manifestations of the endophenotype associated with the underlying risk of OCD. Future confirmation of these results in experiments using complex anti-saccadic tasks with images of various modalities (taking into account the increased anxiety in patients with OCD as the disorder basis) might contribute to validation of the OCD-specific markers.

Currently, software products for use in medicine are actively developed. Among them, the dominant share belongs to clinical decision support systems (CDSS), which can be intelligent (based on mathematical models obtained by machine learning methods or other artificial intelligence technologies) or non-intelligent. For the state registration of CDSSs as software medical products, clinical trials are required, and the protocol of trial is developed jointly by the developer and an authorized medical organization. One of the mandatory components of the protocol is the calculation of the sample size. This article discusses the calculation of the sample size for the most common case, the binary outcome in diagnostic/screening and predictive systems. For diagnostic/screening models, cases of a non-comparative study, comparative study with testing of the superiority hypothesis, comparative study with testing of a hypothesis of non-inferiority in cross-sectional studies are considered. For predictive models, cases of randomized controlled trials of the complex intervention "prediction + prediction-dependent patient management" with testing of the hypothesis of superiority and non-inferiority are considered. It is emphasized that representativeness of the sample and other design components are no less important in clinical trials than sample size. They are even more important since systematic biases in clinical trials are primary, and even the most sophisticated statistical analysis cannot compensate for design defects. The reduction of clinical trials to external validation of models (i.e. evaluation of accuracy metrics on external data) seems completely unreasonable. It is recommended to perform clinical trials with the design adequate to the tasks, so that further clinical and economic analysis and comprehensive assessment of medical technologies are possible. The sample size calculation methods described in the article can potentially be applied to a wider range of medical devices.

The aim of the investigation is to study the concentration of potassium in erythrocytes using the proposed method, potassium interconnection with other electrolyte and acid-base parameters of blood plasma, and to create the basis for clinical interpretation of the results.

Materials and methods: Potassium content in erythrocytes was measured using a blood gas analyzer with ion-selective electrodes in parallel with the laboratory procedure. Patients from intensive care units were randomly selected for the study.

Results: No correlations of potassium with other plasma parameters have been found, however its buffer dependence on chlorine in plasma has been established. Minimal value of potassium concentration in erythrocytes (for 356 measurements) was 68.2 mmol/L, maximal - 210.2 mmol/L.Following the logic of the acid-base status, a nomogram for clinical interpretation of intracellular potassium homeostasis has been developed. The low values are mainly connected with the deficit of potassium which is impossible to determine in blood plasma (e.g. in severe metabolic alkalosis or diuretic therapy). The elevated concentration of potassium in erythrocytes is caused by eryptosis: released potassium is absorbed by normal erythrocytes (protection from hyperkalaemia). So, the increased concentration of potassium indicates directly the presence of eryptosis triggers, i.e. inflammatory mediators, oxidative stress, and others, for example in sepsis. The results of the study have shown that measurement of potassium concentration in erythrocytes with the help of ion-selective electrodes is an effective method of monitoring its intracellular homeostasis. Potassium in erythrocytes is an independent biological marker which can provide clinically relevant information.