Introduction. Gait disorders are a common and severe consequence of stroke, limiting patient autonomy and quality of life. A functional near-infrared spectroscopy (NIRS)-based brain–computer interface (BCI) represents a promising technology for restoring motor functions; however, its application in gait rehabilitation remains insufficiently studied. Study aim: To evaluate the clinical applicability and technical feasibility of an NIRS-based BCI technology combined with a pneumatic plantar support load simulator (pneumatic orthosis) as an adjunct to comprehensive motor rehabilitation in post-stroke patients. Materials and methods. Seventeen patients were enrolled in the pilot study, of whom 15 (median age 58.0 [47.0; 64.0] years, median time since stroke 6.0 [3.0; 9.0] months) completed a course of 7–13 (median 10 [9; 10]) training sessions with the NIRS-BCI–pneumatic orthosis technology in addition to a comprehensive motor rehabilitation program. Motor function was assessed using the Fugl–Meyer Assessment scale for the lower extremity, the 10-Meter Walk Test, and the Timed Up and Go test. Results. A total of 147 NIRS-BCI–pneumatic orthosis training sessions were conducted, with a total median exposure of 229 minutes per patient. The median BCI classifier recognition rate for patients’ mental states was 54.93% [53.10; 69.70]. The median of the maximum achieved recognition rates was 75.57% [67.54; 87.14]. Characteristic hemodynamic activation patterns were identified in motor and associative cortical areas. Following the course, statistically significant improvements were noted on the Fugl–Meyer Assessment scale (from 19.0 [16.0; 24.0] to 24.0 [20.0; 25.0] points; p = 0.001) and the Timed Up and Go test (from 17.61 [14.21; 22.34] to 16.06 [13.00; 17.41] s; p = 0.041), but not on the 10-Meter Walk Test (p 0.05). Most patients tolerated the procedures satisfactorily; two participants withdrew early. Conclusion. The clinical applicability and technical feasibility of the NIRS-BCI–pneumatic orthosis technology for post-stroke gait rehabilitation have been confirmed. Randomized controlled trials are required to assess its clinical efficacy.

AbstractThis paper presents an open dataset of over 50 hours of near infrared spectroscopy (NIRS) recordings. Fifteen stroke patients completed a total of 237 motor imagery brain–computer interface (BCI) sessions. The BCI was controlled by imagined hand movements; visual feedback was presented based on the real– time data classification results. We provide the experimental records, patient demographic profiles, clinical scores (including ARAT and Fugl–Meyer), online BCI performance, and a simple analysis of hemodynamic response. We assume that this dataset can be useful for evaluating the effectiveness of various near– infrared spectroscopy signal processing and analysis techniques in patients with cerebrovascular accidents.

Introduction. The high prevalence of post-COVID syndrome (PCS), which frequently manifests with emotional disturbances, cognitive impairment, and asthenia, necessitates effective rehabilitation methods. One potential approach is electroencephalography (EEG)-based biofeedback (BFB) therapy, though its use in PCS management has been explored in only a few studies to date. The study aimed to evaluate the effects of EEG α-rhythm BFB training on emotional state and cognitive function recovery, and reduction of astheniа symptoms in PCS patients. Materials and methods. Patients diagnosed with U09. Post-COVID-19 condition were randomly assigned to two groups of 10 participants each. The main group underwent 12–15 sessions of EEG α-rhythm BFB training using the NeuroPlay-6C headset with the Neurocorrection of COVID-19 Psychoemotional Consequences protocol, while the control group received identical training without biofeedback. Assessments performed before and after the intervention included: emotional state evaluation (State-Trait Anxiety Inventory [STAI], Short Health Anxiety Inventory [SHAI], Beck Depression Inventory [BDI], Psychological Stress Measure [PSM-25]), cognitive function assessment (Addenbrooke’s Cognitive Examination III [ACE-III], Schulte tables, Stroop test, Tower of London test, N-back test, 10-word memory test), assessment of asthenia (Multidimensional Fatigue Inventory [MFI]), and sleep quality evaluation (Insomnia Severity Index [ISI]). Results. In both groups, the training resulted in a significant reduction of personal anxiety, psychological stress, depression, and asthenia. The main group additionally demonstrated decreased health-related anxiety and improved information retention parameters. Intergroup comparison revealed more pronounced dynamics in the main group: greater reduction of general fatigue manifestations, increased immediate word recall volume, and improved retention of verbal information in working memory. The proportion of patients transitioning to milder symptom severity levels on individual scales was comparable between both groups. Conclusion. EEG α-rhythm biofeedback training can be implemented at the outpatient rehabilitation stage for PCS patients.

Brain-computer interfaces allow the exchange of data between the brain and an external device, bypassing the muscular system. Clinical studies of invasive brain-computer interface technologies have been conducted for over 20 years. During this time, there has been a continuous improvement of approaches to neuronal signal processing in order to improve the quality of control of external devices. Currently, brain-computer interfaces with intracortical implants allow completely paralyzed patients to control robotic limbs for self-service, use a computer or a tablet, type text, and reproduce speech at an optimal speed. Studies of invasive brain-computer interfaces regularly provide new fundamental data on functioning of the central nervous system. In recent years, breakthrough discoveries and achievements have been annually made in this sphere. This review analyzes the results of clinical experiments of brain-computer interfaces with intracortical implants, provides information on the stages of this technology development, its main discoveries and achievements.

Motor imagery training under the control of a brain-computer interface (BCI) facilitates motor recovery after stroke. The efficacy of BCI based on electroencephalography (EEG-BCI) has been confirmed by several meta-analyses, but a more convenient and noise-resistant method of near-infrared spectroscopy in the BCI circuit (NIRS-BCI) has been practically unexamined; comparisons of the two types of BCI have not been performed.Objective: to compare the control accuracy and clinical efficacy of NIRS-BCI and EEG-IMC in post-stroke rehabilitation.Material and methods. The NIRS-BCI group consisted of patients from an uncontrolled study (n=15; 9 men and 6 women; age – 59.0 [49.0; 70.0] years; stroke duration – 7.0 [2.0; 10.0] months; upper limb paresis – 47.0 [35.0; 54.0] points on the Fugl-Meyer Assessment for motor function evaluation of the upper limb – FM-UL). The EEG-IMC group was formed from the main group of the randomized controlled trial “iMove” (n=17; 13 men and 4 women; age – 53.0 [49.0; 70.0] years; stroke duration – 10.0 [6.0; 13.0] months; upper limb paresis – 33.0 [12.0; 53.0] points on the FM-UL). Patients participated in a comprehensive rehabilitation program supplemented by BCI-guided movement imagery training (average of 9 training sessions).Results. Median of average BCI control rates achieved by the patients was 46.4 [44.2; 60.4]% in the NIRS group and 40.0 [35.7; 45.1]% in the EEG group (p=0.004). For the NIRS-BCI group, the median of the maximum BCI control accuracy achieved was 66.2 [56.4; 73.7]%, for EEGBCI – 50.6 [43.0; 62.3]% (p=0.006). The proportion of patients who achieved a clinically significant improvement according ARAT and the proportion of patients who achieved a clinically significant improvement according FM-UL were comparable in both groups. The NIRS-BCI group showed greater improvement in motor function compared to the EEG-BCI group according to Action Research Arm Test (ARAT; an increase of 5.0 [4.0; 8.0] points compared to an increase of 1.0 [0.0; 3.0] points; p=0.008), but not according to FM-UL scale (an increase of 5.0 [1.0; 10.0] and 4.0 [2.0; 5.0] points, respectively; p=0.455).Conclusion. NIRS-BCI has an advantage in control accuracy and ease of use in clinical practice. Achieving higher control accuracy of BCI provides additional opportunities for the use of game feedback scenarios to increase patient motivation.

Introduction. Non-invasive brain–computer interfaces (BCIs) enable feedback motor imagery [MI] training in neurological patients to support their motor rehabilitation. Nowadays, the use of BCIs based on functional near-infrared spectroscopy (fNIRS) for motor rehabilitation is yet to be investigated. Objective: To evaluate the potential fNIRS BCI use in hand MI training for comprehensive post-stroke rehabilitation. Materials and methods. This pilot study included clinically stable patients with mild-to-moderate post-stroke hand paresis. In addition to the standard rehabilitation, the patients underwent 10 nine-minute MI fNIRS BCI training sessions. To evaluate the quality of fNIRS BCI control, we assessed the percentage of time during which the classifier accurately detected patient's mental state. We scored the hand function using the Action Research Arm Test (ARAT) and the Fugl-Meyer Assessment (FMA). Results. The study included 5 patients at 1 day to 12 months of stroke. All the participants completed the study. All study participants achieved BCI control rates higher than random (41–68%). While three patients demonstrated the clinically significant improvements in their ARAT scores, one of them also showed an improvement in the FMA score. All the participants reported experiencing drowsiness during training. Conclusions. Post-stroke patients can operate the fNIRS BCI system under investigation. We suggest adjusting the feedback system, extending the duration of training, and incorporating functional electromyostimulation to enhance training effectiveness.

Brain-computer interfaces (BCIs) are a group of technologies that allow mental training with feedback for post-stroke motor recovery.Varieties of these technologies have been studied in numerous clinical trials for more than 10 years, and their construct and software are constantly being improved.Despite the positive treatment results and the availability of registered medical devices, there are currently a number of problems for the wide clinical application of BCI technologies.This review provides information on the most studied types of BCIs and its training protocols and describes the evidence base for the effectiveness of BCIs for upper limb motor recovery after stroke.The main problems of scaling this technology and ways to solve them are also described.

In this review, we focused on the applicability of artificial intelligence (AI) for opportunistic abdominal aortic aneurysm (AAA) detection in computed tomography (CT). We used the academic search system PubMed as the primary source for the literature search and Google Scholar as a supplementary source of evidence. We searched through 2 February 2022. All studies on automated AAA detection or segmentation in noncontrast abdominal CT were included. For bias assessment, we developed and used an adapted version of the QUADAS-2 checklist. We included eight studies with 355 cases, of which 273 (77%) contained AAA. The highest risk of bias and level of applicability concerns were observed for the “patient selection” domain, due to the 100% pathology rate in the majority (75%) of the studies. The mean sensitivity value was 95% (95% CI 100–87%), the mean specificity value was 96.6% (95% CI 100–75.7%), and the mean accuracy value was 95.2% (95% CI 100–54.5%). Half of the included studies performed diagnostic accuracy estimation, with only one study having data on all diagnostic accuracy metrics. Therefore, we conducted a narrative synthesis. Our findings indicate high study heterogeneity, requiring further research with balanced noncontrast CT datasets and adherence to reporting standards in order to validate the high sensitivity value obtained.

BACKGROUND: In Russia, a semi-quantitative CT 04 scoring system is used in the analysis of thoracic computed tomography (CT) scans of COVID-19 patients to grade the severity of lung lesions. Despite the widespread use of this approach, the scoring systems diagnostic accuracy for identification hospitalizations for patients with the disease is currently unknown. AIM: To evaluate the sensitivity, specificity, positive (PPV) and negative (NPV) predictive value of the CT 04 system for the triage of COVID-19 patients. MATERIALS AND METHODS: This retrospective study enrolled 575 patients of Moscow clinics with laboratory-verified COVID-19, aged 57.213.9 years, 55% females. All patients were examined with four consecutive chest CT scans, and the disease severity was assessed using the CT 04 scoring system. Sensitivity and specificity were calculated as conditional probabilities that a patient would experience clinical improvement or deterioration, depending on the preceding CT examination results. For the calculation of the NPV and PPV, we estimated the COVID-19 prevalence in Moscow. The data on total cases of COVID-19 from March 6 to November 28, 2020, were taken from the Rospotrebnadzor website. We used several ARIMA and EST models with different parameters to fit the data and forecast the incidence. RESULTS: The median specificity of the CT 04 scoring system was 69% (95% CI 32%, 100%), and the sensitivity was 92% (95% CI 74%, 100%). The best statistical model describing the epidemiological situation in Moscow was ARIMA (0,2,1). According to our calculations, with the predicted point prevalence of 9.6%, the values of PPV and NPV were 56% and 97%, correspondingly. CONCLUSION: The maximum Youdens index was observed for the period between the first and the second chest CT examinations when the majority of the included patients experienced clinical deterioration. The CT 04 scoring system makes it possible to safely exclude the development of pathological changes in patients with mild and moderate disease (categories CT-0 and CT-1), thereby optimizing the burden on hospitals in an unfavorable epidemic situation.

论证 ：在俄罗斯联邦，为了检测COVID-19肺炎及其并发症和与其他肺部疾病的鉴别诊断，以及对患者进行分类，使用了胸部CT，并在CT 0–4的半定量视觉尺度上评估变化。尽管胸部CT广泛使用，但其用于确定COVID-19患者住院需求的诊断准确性的数字指标目前尚不清楚。 目的 ： 是确定该量表的敏感性、特异性、阳性预测值、阴性预测值。 材料与方法 ：研究涉及575名经实验室确诊的COVID-19患者（55%为女性），年龄为57.2±13.9岁。对于每个患者，进行了4次连续的胸部CT研究，并对疾病的严重程度进行了CT评分（0–4）。根据既往CT研究结果，将敏感性和特异性作为患者病情恶化或改善的条件概率进行计算。为计算阳性预测值（PPV）和阴性预测值（NPV），对COVID-19在莫斯科的流行情况进行了估计。2020年3月6日至11月28日期间所有COVID-19病例的数据来自俄国国家管理的保护消费者服务机构（Rospotrebnadzor）网站。使用了许多具有不同参数的ARIMA和EST模型来选择与现有数据最匹配的模型，并预测发病率的发展。 结果 ：0–4 CT分级的中位特异性为69%，敏感性为92%。描述莫斯科流行病学情况的最佳统计模型是ARIMA（0,2,1）。经计算，预测年发病率为9.6%，PPV值为56，NPV值为97%。 结果 ：Yuden指数最大的阶段出现在胸部CT第一次研究和第二次研究之间，此时样本中大多数患者表现出临床病情恶化的趋势。0–4 CT分级可以安全地排除轻、中度病程（CT0、CT1类）患者的病理变化发展，有助于优化患者在疫情不利的情况下住院。

Aim: To assess the specificity of COVID-19- associated pneumonia detection by radiologists using a chest CT scan.Materials and methods: From mid-February to early March 2020, 65 patients have been retrospectively selected from the Moscow City Clinical Hospital database; all of them had been treated in an inpatient facility with a verified diagnosis of COVID-19. In addition, 75 patients from the Unified Radiological Information Service have been randomly selected. In December 2019, these outpatients had been sent by an attending physician for a chest CT scan with suspected pneumonia. The imaging studies showed non-specific inflammation signs in the lungs. All 140 scans were analyzed by seven radiologists from different Russian cities, who independently categorized each study as “COVID-19” or “Other pneumonia”.Results: Chest computed tomography had a 92% specificity in the differential diagnosis of COVID-19-associated pneumonia, and its specificity in the general population is expected to be at least 80% with a high probability. The inter-rater variability was low (coefficient of variation for specificity 12.6%). The sensitivity in our study was 76.2%, and the coefficient of variation for sensitivity 23.5%. These findings are generally consistent with other studies. The primary study limitation is the absence of a sample with confirmed pneumonia caused by other viruses.Conclusion: Chest CT is highly specific for the detection of COVID-19-associated pneumonia.

This paper addresses changes in blood flow parameters in the area behind a saccular aneurysm. The hemodynamics modelling was conducted with the ANSYS software using the Lattice Boltzmann method. We performed a computational fluid dynamics simulation of the blood flow in two vessels of 8.4 mm in diameter, one of which contained an aneurysm of 23 mm in diameter, and the other had no abnormalities. The maximum relative deviation of the blood flow velocity registered 35 mm away from the aneurysm, provided the inflow velocity was 86 cm/s at 60 th ms from the start of the simulation, was 38.5% compared to the flow velocity in the normal vessel.

Artificial intelligence technologies in medical practice are a promising direction in the world. Artificial intelligence medical decision support systems, diagnostic and screening programs can help medical personnel in routine and complex tasks and improve the level of medical care provided to patients. At the same time, the development, production and distribution of artificial intelligence systems must be regulated without fail. Registration and subsequent control (post-registration monitoring) of artificial intelligence systems in medicine require the creation, adjustment of the legal framework and technological regulation. The Russian Federation has developed a promising development strategy in this area. Seven national standards have been developed by experts in the field of Artificial intelligence in healthcare. These standards establish the procedures for conducting clinical and technical trials, performance requirements and the concept of life cycle, a quality management system and risk management. Aseparate standards is devoted to dataset creation for training and testing the developed algorithms, requirements for them and a metadata format. There are plans to bring the developed national standards to the international level, which will allow Russian manufacturers of artificial intelligence systems implemented these national standards to comply with foreign counterparts and become more competitive at the international level. The international community has already supported the development of an ISO standard based on the national standard for clinical trials. The development will be performed based on the technical committee ISO/TC215 (Health informatics) in conjunction with ISO/IEC JTC1/SC42 (Artificial intelligence), this will allow bringing the national requirements for the Artificial intelligence to the international level. The cycle of these standards will summarize recognized methodologies, helping both manufacturers and medical organizations, doctors and patients to produce and use aquality, safe and effective product.

Обоснование . В период пандемии компьютерная томография (КТ) является одним из ключевых инструментов оценки изменений в лёгких, связанных с COVID-19. Рентгенологи Москвы используют адаптированную шкалу КТ 0–4 для визуальной оценки зависимости тяжести общего состояния от характера и выраженности рентгенологических признаков изменений в лёгких при COVID-19 по данным КТ. В большом потоке исследований врач может пропустить находку и ошибиться в оценке объёма поражения лёгких, поэтому применение сервисов искусственного интеллекта (ИИ) обосновано в амбулаторном здравоохранении в период пандемии. Цель ― сравнить распределение категорий КТ 0–4 в заключениях, сформированных рентгенологами с использованием ИИ-сервисов и без них. Материал и методы . Ретроспективное исследование, протокол исследования зарегистрирован в ClinicalTrials.gov (NCT04489992). Проанализированы результаты первичных КТ с категориями КТ 0–4 в период с 08.04.2020 по 01.12.2020 и отдельно за ноябрь 2020 года (с 01.11.2020 по 01.12.2020) в амбулаторных медицинских организациях Департамента здравоохранения. КТ проводились на 48 компьютерных томографах по стандартным протоколам, результаты обрабатывались через Единый радиологический информационный сервис. В тестовую группу включены КТ, обработанные ИИ-сервисами, в контрольную ― без обработки ИИ. В анализ включены 5 ИИ-сервисов: RADlogics COVID-19 (RADLogics, США); COVID-IRA (IRA labs, Россия); Care Mentor AI, COVID (CareMentor AI, Россия); Третье Мнение. КТ-COVID-19 (Третье мнение, Россия); COVID-MULTIVOX (Гаммамед, Россия). ИИ-сервисы кодированы случайным образом. Результаты . Проанализированы результаты КТ 260 594 пациентов (соотношение мужчины/женщины ― 44/56%, средний возраст 49,5 года). В тестовую группу включены 115 618 КТ, в контрольную ― 144 976. В зависимости от конкретного ИИ-сервиса для разных подгрупп категорий КТ-0 выставлено от 2,3 до 18,5% меньше, категорий КТ 3–4 ― от 4,7 до 27,6% меньше, КТ-4 ― от 40 до 60% меньше, чем в контрольной группе ( p <0,0001). За ноябрь (с 01.11.2020 по 01.12.2020) проанализированы результаты КТ 41 386 пациентов (соотношение мужчины/ женщины ― 44/56%, средний возраст 53,2 года). В тестовую группу включено 28 881 КТ, в контрольную ― 12 505. В зависимости от конкретного ИИ-сервиса для разных подгрупп категорий КТ-0, КТ 3–4 и КТ-4 выставлено соответственно от 1 до 2,6, от 0,2 до 15,7 и на 25% меньше, чем в контрольной группе ( p =0,001). Заключение . Применение ИИ-сервисов для первичных КТ в амбулаторных условиях приводит к уменьшению количества выставляемых категорий КТ-0 и КТ 3–4, способных влиять на тактику ведения пациентов с COVID-19.

Aim : To assess the specificity of COVID-19- associated pneumonia detection by radiologists using a chest CT scan. Materials and methods : From mid-February to early March 2020, 65  patients have been retrospectively selected from the Moscow City Clinical Hospital database; all of them had been treated in an inpatient facility with a  verified diagnosis of COVID-19. In addition, 75  patients from the Unified Radiological Information Service have been randomly selected. In December 2019, these outpatients had been sent by an attending physician for a  chest CT scan with suspected pneumonia. The imaging studies showed non-specific inflammation signs in the lungs. All 140  scans were analyzed by seven radiologists from different Russian cities, who independently categorized each study as “COVID-19” or “Other pneumonia”. Results : Chest computed tomography had a  92%  specificity in the differential diagnosis of COVID-19-associated pneumonia, and its specificity in the general population is expected to be at least 80% with a high probability. The inter-rater variability was low (coefficient of variation for specificity 12.6%). The sensitivity in our study was 76.2%, and the coefficient of variation for sensitivity 23.5%. These findings are generally consistent with other studies. The primary study limitation is the absence of a sample with confirmed pneumonia caused by other viruses. Conclusion : Chest CT is highly specific for the detection of COVID-19-associated pneumonia.

The article analyzes ethical issues inherent to different life-cycle stages of artificial intelligence systems and provides up-to-date information about global and domestic trends in this area. The international and national experience concerning ethical issues of artificial intelligence systems use in healthcare is described. In addition, the international and national strategies for the development of artificial intelligence in healthcare are analyzed focusing on the national development; and the main trends, similarities, and differences between strategies are identified. Furthermore, ethical components of the process of clinical trials to evaluate the safety and efficacy of artificial intelligence systems in Russia are described. Domestic state-of-the-art and globally unique experience in technical regulation of artificial intelligence systems are shown on unification papers and standardization of requirements for the development, testing, and operation of artificial intelligence systems in healthcare are presented, and unparalleled Russian experience in terms of certification requirements for artificial intelligence-based medical devices is demonstrated. The article also summarizes the main conclusions and emphasizes the importance of a strong successful healthcare system based on artificial intelligence technologies that build trust and compliance with ethical standards.

BACKGROUND: During the pandemic, computed tomography (CT) was one of the most important tools for assessing COVID-19-related lung changes. In COVID-19 patients, radiologists in Moscow used the adapted CT0-4 scale to visually assess the dependence of the severity of the general condition on the nature and severity of radiological signs of changes in the lungs based on computed tomography. In a large stream of scans, the doctor may miss findings and make errors in assessing the volume of lung damage, so the use of AI services in outpatient healthcare during a pandemic can be beneficial. AIM: The goal of this study is to compare the distribution of CT0-4 categories designed by radiologists with the results of AI services processing and categories formed without AI services. METHODS: We used retrospective study design, full study protocol is registered on ClinicalTrials.gov (NCT04489992). The results of primary CT scans with the CT0-4 categories were analyzed in outpatient medical institutions of the Health Department from April 08, 2020, to December 01, 2020, and separately for November (from November 01, 2020, to December 01, 2020). CT was performed on 48 computed tomographs in accordance with standard protocols, and the data was processed by the single radiology information systems. CTs in the test group received AI services, while CTs in the control group did not. The analysis includes five AI services: RADLogics COVID-19 (RADLogics, USA), COVID-IRA (IRA labs, Russia), Care Mentor AI, COVID (Care Mentor AI, Russia), Third Opinion. CT-COVID-19 (Third Opinion, Russia), and COVID-MULTIVOX (Gammamed, Russia). Moreover, AI services are encoded at random. RESULTS: The CT scan results of 260,594 patients were examined (m/f % = 44/56, mean age = 49.5). The test group consisted of 115,618 CT scans, while the control group consisted of 144,976 CT scans. Depending on the specific AI service, CT0 was established by 2.318.5% less than the control group for different subgroups of categories. The categories CT3-4 were established by 4.727.6% less than without AI, and the categories CT4 by 4060% less than without AI (p 0.0001). For November (from November 01, 2020, to December 01, 2020), the CT scan results of 41,386 patients were analyzed (m/f % = 44/56, average age = 53.2 years). The test group consisted of 28,881 CT scans, while the control group included 12,505 CT scans. Depending on the specific AI service, CT0 was established by 12.6% less than the control group for different subgroups of categories. Further, the categories CT3CT4 were established by 0.215.7% less than without AI, and the categories CT4 were established by 25% less than without AI (p = 0.001). CONCLUSION: The use of AI services for primary CT scans on an outpatient basis reduces the number of CT0 and CT3CT4 results, which can influence the therapeutic approach for COVID-19 patients.

The project is aimed at investigating efficacy of a BCI-controlled palm exoskeleton as a tool for motor function recovery in post-stroke patients. The idea of using the system is grounded on vast amount of data supported by physiologic literature and our own findings in healthy subjects, suggesting that kinesthetic motor imagery (MI) requires activation of the brain areas involved in motion planning, execution and control. Thus, the common idea of using a MI-based BCI for neurorehabilitation is to reinforce motor imagery of intention to move with visual, proprioceptive and\or tactile feedback. Results of a four-year multi-center randomized controlled study of post-stroke motor rehabilitation procedure with BCI-controlled hand exoskeleton complex are presented. The study has the largest number of participants so far. Statistical analysis of different clinical scales used to assess motor function recovery show that incorporating the BCI+exoskeleton procedure into rehabilitation significantly improves its outcome. The analysis also revealed non-monotonical dependency of motor function recovery rate on initial motor and sensory function status, as well as on age, and BCI control accuracy. Hopefully, the reported data combined with the results obtained by other groups in the world, would provide solid evidence supporting inclusion of the BCI-based systems into rehabilitation practice.

BACKGROUND:Effective and safe tools assisting triage decisions for COVID-19 patients could optimize the pressure on the healthcare system. COVID-19 often has respiratory manifestations, and medical imaging techniques provide an opportunity to assess the diseases severity. AIMS:To estimate the sensitivity and specificity of lung ultrasound for different degrees of pulmonary involvement in COVID-19 patients by a systematic review of English articles using PubMed and Google Scholar databases. Search terms included lung ultrasound, chest ultrasound, thoracic ultrasound, ultrasonography, COVID-19, SARS-CoV-2, coronavirus, diagnosis, diagnostic value, specificity, and sensitivity. Only studies addressing lung ultrasound diagnostic accuracy for patients with suspected COVID-19 using thoracic computed tomography, reverse transcription polymerase chain reaction, or laboratory data as a reference standard were included. Independent extraction of articles was performed by two authors using predefined data fields with subsequent assessment of study quality indicators. The random-effect model was used to analyze and pool lung ultrasound sensitivity and specificity across the included studies. Sixteen studies met our inclusion criteria, but only three of them divided patients into distinct and defined groups depending on the disease severity. We used the remaining studies data to assess the secondary outcomes: the values of sensitivity and specificity of lung ultrasound for COVID-19 regardless of the patients clinical status. Heterogeneity for primary and secondary outcomes was observed that remained when pooling for different scenarios (screening, assessing severity) and cohorts of participants. Lung ultrasound had the highest accuracy for confirmed COVID-19 patients with severe disease (sensitivity 87.6% 12.3%, specificity 80.5% 7.1%), and the lowest accuracy for the patients with mild disease (sensitivity 72.8% 7.1%, specificity 74.3% 2.7%). CONCLUSIONS:Lung ultrasound can be used in patients with confirmed COVID-19 to detect serious damage to the lung tissue. The diagnostic value of the method for assessing mild and moderate lung lesions is relatively low.

论证：在评估COVID-19患者病情的严重程度时，主要依赖肺组织损伤的体积。有许多诊断方法允许分析该指标，每一种方法都有一定的局限性。研究的目的和设计，观察患者的特点，设备的可用性，所有这些参数都可以影响最佳方法的选择。 目的是通过对PubMed和Google Scholar数据库中相关英文文章的系统回顾，评估超声作为一种分析COVID-19患者肺损伤程度的方法的敏感性和特异性。关键词：lung ultrasound; chest ultrasound; thoracic ultrasound; ultrasonography; COVID-19; SARS-CoV-2; coronavirus; diagnosis; diagnostic value; specificity; sensitivity该综述仅包括了针对疑似COVID-19患者肺部超声诊断准确性问题的研究。参考方法包括胸部CT、逆转录聚合酶链反应检测病毒RNA、实验室数据等。论文由两位作者独立抽取，填写标准化表格的指定字段，然后对研究质量指标进行评价。为了分析和分组所选研究中肺超声评估肺组织改变体积的敏感性和特异性的数据，使用了随机效应模型。根据规定的纳入标准，适合16项研究，但仅对3例患者根据疾病严重程度划分明确组。通过其他有关材料，为了评估次要结果，使用了肺部超声诊断COVID-19的敏感性和特异性值，而不考虑患者的病情。当研究根据筛查、疾病严重程度评估和患者队列进行分组时，观察到的主要结果和次要结果的异质性得以保持。肺部超声诊断重症冠状病毒感染COVID-19患者肺损害的准确性最高（敏感性为87.6±12.3%，特异性为80.5±7.1%）。同时，该方法在轻度疾病患者中的准确率最低（敏感性为72.8±7.1%，特异性为74.3±2.7%）。 结果。肺部超声检查可用于确诊COVID-19的患者，以检测肺组织的严重损害。该方法评估轻微-中度肺损伤的诊断价值相对较低。