Automatic Sleep Staging Using BiRNN with Data Augmentation and Label Redirection

Sleep staging has always been a hot topic in the field of sleep medicine, and it is the cornerstone of research on sleep problems. At present, sleep staging heavily relies on manual interpretation, which is a time-consuming and laborious task with subjective interpretation factors. In this paper, we propose an automatic sleep stage classification model based on the Bidirectional Recurrent Neural Network (BiRNN) with data bundling augmentation and label redirection for accurate sleep staging. Through extensive analysis, we discovered that the incorrect classification labels are primarily concentrated in the transition and nonrapid eye movement stage I (N1). Therefore, our model utilizes a sliding window input to enhance data bundling and an attention mechanism to improve feature enhancement after label redirection. This approach focuses on mining latent features during the N1 and transition periods, which can further improve the network model's classification performance. We evaluated on multiple public datasets and achieved an overall accuracy rate of 87.3%, with the highest accuracy rate reaching 93.5%. Additionally, the network model's macro F1 score reached 82.5%. Finally, we used the optimal network model to study the impact of different EEG channels on the accuracy of each sleep stage.

Necrotizing Skin and Soft Tissue Infection after Gluteal Augmentation in a Perioperatively Asymptomatic COVID-19 Patient-Complications of the Post-Lockdown Era? A Case Report.

Introduction: Aesthetic surgery procedures are generally done in a relatively healthy population and carry a rather low risk compared to other surgical specialties. The incidence of complications in aesthetic surgery varies greatly depending on the type, wound cleanliness regarding the anatomical site, complexity of the surgery, patient's age, and comorbidities but is generally considered low. The overall incidence of surgical site infections (SSIs) in all aesthetic surgical procedures is around 1% in most of the literature while cases of necrotizing soft tissue infections are mostly found as individual reports. In contrast, treating COVID-19 patients is still challenging with many diverse outcomes. Surgical stress and general anesthesia are known mediators of cellular immunity impairment while studies regarding COVID-19 infection unquestionably have shown the deterioration of adaptive immunity by SARS-CoV-2. Adding COVID-19 to the modern surgical equation raises the question of immunocompetence in surgical patients. The main question of the modern post-lockdown world is: what could be expected in the postoperative period of perioperatively asymptomatic COVID-19 patients after aesthetic surgery? Case report: Here, we present a purulent, complicated, necrotizing skin and soft tissue infection (NSTI) after gluteal augmentation most likely triggered by SARS-CoV-2-induced immunosuppression followed by progressive COVID-19 pneumonia in an otherwise healthy, young patient. To the best of our knowledge, this is the first report of such adverse events in aesthetic surgery related to COVID-19. Conclusion: Aesthetic surgery in patients during the incubation period of COVID-19 or in asymptomatic patients could pose a significant risk for surgical complications, including severe systemic infections and implant loss as well as severe pulmonary and other COVID-19-associated complications.

A multivariate spatiotemporal model for tracking COVID-19 incidence and death rates in socially vulnerable populations.

Recent studies have produced inconsistent findings regarding the association between community social vulnerability and COVID-19 incidence and death rates. This inconsistency may be due, in part, to the fact that these studies modeled cases and deaths separately, ignoring their inherent association and thus yielding imprecise estimates. To improve inferences, we develop a Bayesian multivariate negative binomial model for exploring joint spatial and temporal trends in COVID-19 infections and deaths. The model introduces smooth functions that capture long-term temporal trends, while maintaining enough flexibility to detect local outbreaks in areas with vulnerable populations. Using multivariate autoregressive priors, we jointly model COVID-19 cases and deaths over time, taking advantage of convenient conditional representations to improve posterior computation. As such, the proposed model provides a general framework for multivariate spatiotemporal modeling of counts and rates. We adopt a fully Bayesian approach and develop an efficient posterior Markov chain Monte Carlo algorithm that relies on easily sampled Gibbs steps. We use the model to examine incidence and death rates among counties with high and low social vulnerability in the state of Georgia, USA, from 15 March to 15 December 2020.

Impact of COVID-19 pandemic on major depressive disorder in acute psychiatric inpatients.

Introduction: The spread of the coronavirus disease 2019 (COVID-19) pandemic and the subsequent restrictions significantly affected mental health, especially major depressive disorder (MDD) whose incidence increased by 27.6% in 2020, after the COVID-19 outbreak. Few studies focused on the impact of the pandemic on the clinical characteristics of outpatients with MDD and even fewer on inpatients admitted for a major depressive episode (MDE). We aimed to compare the characteristics of MDD of two groups of patients admitted for an MDE before and after the pandemic outbreak and to investigate which variables are significantly related to post-lockdown hospitalizations. Methods: This retrospective study included 314 patients with MDD hospitalized from January 2018 to December 2021 for an MDE (DSM-5) before (n = 154) and after (n = 160) the Italian lockdown (9th of March 2020). We compared patients' sociodemographic and clinical characteristics. The characteristics significantly different between the two groups were included in a logistic regression to identify the factors more strictly associated with post-lockdown hospitalizations. Results: During post-lockdown hospitalization, we found a higher rate of severe MDE (33 patients, 21.4%, in the pre-lockdown and 55 patients, 34.4%, in the post), MDE with psychotic features (3 patients, 2.0%, in the pre-lockdown and 11 patients, 6.9%, in the post-lockdown), and suicidal ideation (42, 27.3%, in the pre-lockdown and 67, 41.9%, in the post-lockdown), with a lower proportion of patients followed by psychiatric services before admission (106 patients, 68.8%, in the pre-lockdown and 90 patients, 56.3%, in the post-lockdown) and a higher percentage of them in treatment with psychotherapy (18 patients, 11.7% in the pre-lockdown and 32, 20.0%, in the post-lockdown) and more frequent increase of the antidepressant dosage (16 patients, 10.4% in the pre-lockdown and 32 patients, 20.0% in the post-lockdown) and adoption of augmentation strategies (13 patients, 8.4%, in the pre-lockdown and 26 patients, 16.3%, in the post-lockdown) to treat the MDE. In the regression model, post-lockdown hospitalizations were significantly associated with suicidal ideation (OR = 1.86; p = 0.016) and psychotic features (OR = 4.41; p = 0.029) at admission, the increase in the antidepressant daily dose (OR = 2.45; p = 0.009), and the employment of an augmentation therapy (OR = 2.25; p = 0.029). Discussion: These results showed an association between the COVID-19 pandemic and the occurrence of MDE with more severe clinical features. This might be true also for future calamities, suggesting that in these emergency contexts, patients with MDD would require more attention, resources, and intense treatments with a specific focus on suicide prevention.

Worse Arterial Stiffness, and Not Endothelial Dysfunction, Is Associated with Pasc

Background: COVID-19 survivors can experience lingering symptoms known as PASC that appear in different phenotypes. The etiology remains elusive and endothelial dysfunction has been postulated as a main driver of PASC. Method(s): Prospective cohort including COVID- and COVID+ with (COVID+PASC+) or without (COVID+PASC-) PASC. We measured endothelial function using Endopat, an FDA approved test, with derived reactive hyperemic index RHI (endothelial dysfunction<=1.67) and arterial elasticity (augmentation index standardized at 75 bpm or AI@75;(lower =better). PASC symptoms were categorized into three non-exclusive phenotypes: Cardiopulmonary CP (postexertional malaise, shortness of breath, cough, palpitations), Neurocognitive N (change in smell/taste, neuropathy, 'brain fog', headache), and General G (fatigue, gastrointestinal or bladder problems). Result(s): We included 491 participants with 109 of the 186 with confirmed COVID+ experiencing PASC. Median number of days between COVID diagnosis and study visit was 249 days (IQR: 144, 510). Among COVID+PASC+, the median number of symptoms was 7.0 (IQR: 3.0,13.0);97 experienced symptoms categorized as G, 90 as N, and 87 as CP. COVID+ PASC+ had the lowest RHI (1.77+/-0.47) and the largest proportion [46.79% (n=51)] with RHI<=1.67 (Figure). AI@75 was the lowest in COVID- (3.11+/-15.97) followed by COVID+PASC- (3.57 +/- 16.34). Within COVID+PASC+, the mean AI@75 among G was 10.11+/-14.85, 11.36+/-14.67 with N, and highest (12.01 +/- 14.48) with CP. Symptoms' number was positively associated with AI@75 (p=0.01). The estimated mean difference in AI@75 between COVID+ PASC+ with CP and COVID+ PASC- was 8.44+/-2.46 (p=0.001), between COVID+ PASC+ with CP phenotype and COVID- was 8.9+/-1.91 (p< .0001), and between COVID+ PASC+ with CP phenotype and COVID+ PASC without CP phenotype was 7.51+/-3.75 (p=0.04) Conclusion(s): PASC was associated with worse arterial elasticity and within PASC, the cardiopulmonary phenotype had the highest arterial stiffness. (Figure Presented).

Post-Covid-syndrome and transient microvascular pathology in pulse-waveanalysis - association with Mg/Ca ratio and magnesium therapy-options

Post-COVID-syndromes have a high impact on incapacity for work: a mean of over 100 days has been reported in Germany [1]. Magnesium deficiency is documented as a riskincreasing factor for fatal outcome of acute covid disease [2, 3]. A first case report of post-COVID treatment with hybrid magnesium parenteral/ oral was presented in February 2021 during the Global Magnesium COVID 19 online conference. As of yet, there is no established explanation for post-COVID or long-COVID syndrome as well as there being no established treatment. In recourse to the hypothesis that magnesiumdepletion might favour microvascular early-aging and so favour neuro- degenerative prozesses [4] now preliminary observations of these parameters in post-covid patients in our primary care office result. This is done in connection with long years documentation of pulsewave-analysis (pwv), magnesium and Mg/Caprofiles in patients who suffered covid- disease. Figure 1 shows an over 6-year series of pulse-wave-analyses in a 59-year-old female patient who suffered from post-COVID syndrome. Her augmentation index (AIX) as an indicator of the actual microvascular condition increased from favorable 8% (2020) to highly pathological 39% in the post-COVID disease period - corresponding with the mean value of an 80-year-old person [5]. Another 67-year-old female post-COVID patient recovered clinically very well and quickly with high-dosed magnesium therapy and showed coincident positive decrease of AIX to 4%. Further case reports in the context of magnesium pretests and AIX are presented. Late controlled studies concerning magnesium supplementation and PWV focus on the other parameter - the (macrovascular determined) pulse-wave-velocity (PWV) and found no association of PWV with several months of magnesium supplementation [6]. Therefore, it must be emphasized that all our observations of the last years where not based on PWV but rather focused on AIX as a volatile but more magnesium-dependent parameter. Furthermore, our patients where mostly supplemented over years and not only 24 weeks. Evident is the overall small number of clinically manifesting post-COVID cases among our COVID patients (n= 10 when writing the ) among actually 470 Corona-context treatment cases. We have two working hypotheses for this. I: Persistently high magnesium levels may contrib- ute to reducing the number of post- COVID cases - and II: In the case of post-COVID syndrome, high-dose possibly hybrid magnesium therapy might favorably influence the course of the disease. The Corona pandemic and its microvascular consequences are possibly and unfortunately a non-intended turbo-experiment for microvascular early aging in a great number of undetected magnesium- depletion patients. Facing the burden of disease for individuals - and society as a whole - this justifies not only controlled studies but also the increased attention of medical doctors to the optimal magnesium status of these patients.

Boosting Masked Face Recognition with Multi-Task ArcFace

In this article, we tackle the recognition of faces wearing surgical masks. Surgical masks have become a necessary piece of daily apparel because of the COVID-19-related worldwide health problem. Modern face recognition models are in trouble because they were not made to function with masked faces. Furthermore, in order to stop the infection from spreading, apps capable of detecting if the individuals are wearing masks are also required. To address these issues, we present an end-to-end approach for training face recognition models based on the ArcFace architecture, including various changes to the backbone and loss computation. We also use data augmentation to generate a masked version of the original dataset and mix them on the fly while training. Without incurring any additional computational costs, we modify the chosen network to output also the likelihood of wearing a mask. Thus, the face recognition loss and the mask-usage loss are merged to create a new function known as Multi-Task ArcFace (MTArcFace). The conducted experiments demonstrate that our method outperforms the baseline model results when faces with masks are considered, while achieving similar metrics on the original dataset. In addition, it obtains a 99.78% of mean accuracy in mask-usage classification. © 2022 IEEE.

EXPLORING THE IMPACT OF IMAGE ENHANCEMENT AND DATA AUGMENTATION TECHNIQUES ON LUNG DETECTION IN CHEST RADIOGRAPHY IMAGES

The health and wellbeing of people all over the world are being severely impacted by the ongoing COVID-19 pandemic. One of the most important ways to check for COVID-19 is chest radiography, so ensuring that infected people undergo this test is crucial. This research set out to assess the efficacy of various image enhancement and data augmentation techniques for use with digital chest X-Rays in the detection of COVID-19 patients. White-balance correction (WB) and contrast-limited adaptive histogram equalization (CLAHE) were the two methods used to improve the images. These two technologies have also been applied to examine this impact on COVID-19 discrimination. Also, Data was augmented in two distinct ways, using a different set of techniques and combining it with image enhancement techniques. Transfer learning was used to compare image classification models pre-trained on the ImageNet dataset to well-known deep learning architectures. Our models were evaluated and compared using the novel-combined chest X-Ray datasets. We observed that the VGG-16 model outperforms other models with an accuracy of 98% when image WB and CLAHE are used together. Due to their superior performance, these pre-trained models can greatly improve the speed and accuracy of COVID-19 diagnosis. © 2023, International Organization on 'Technical and Physical Problems of Engineering'. All rights reserved.

Sex Modifies the Effect of Covid-19 and Pasc Status on Arterial Stiffness

Background: Sex differences in immunological responses to COVID-19 infection and mechanisms that may contribute towards post-acute sequelae of SARS-Co-V2 (PASC) have been reported. However, evidence on the effects of COVID infection on vascular dysfunction and PASC are limited. Method(s): FDA approved EndoPAT device was used to measure endothelial function [Reactive Hyperemia Index (RHI)] and arterial stiffness [Augmentation Index standardized at 75 beats/min (AI@75;higher AI = worse arterial elasticity)] in an adult cohort (age >=18 years) with a history of COVID-19 infection (COVID+) or confirmed SARS-CoV2 antibody negative (COVID-). Generalized linear regression was used to compute estimates of RHI and AI@75. Adjusted models included age, sex, race, blood pressure, lipids, body mass index (BMI), smoking status, and pre-existing comorbidities. Two-way interactions were used to determine if the effects of COVID or PASC status on endothelial function depends on age, sex, race, smoking status, or prevalent comorbidities. Result(s): 61.99% (n=305) of study participants were COVID- and 187 (38.01%) were COVID+. Among COVID+, 57.22% (n=107) were female, 31.72% (n=59) were non-white race, and the average age was 46.64+/-13.79 years. COVIDparticipants had a smaller proportion (38.03%) of female sex (p< .0001), lower BMI [COVID+ (30.79+/-8.95 kg/m2) vs. COVID- (27.76+/-5.89 kg/m2);p< .0001], and higher proportion of smokers [COVID+ (17.78%) vs. COVID- (58.22%);p< .0001]. The average follow-up was 349.68+/-276.76 days and 109 (22.15%) COVID+ experienced PASC. 42.48% (n=80) of COVID+ and 41.64% (n=127) of COVID- had RHI<= 1.67 (p=0.8). The average AI@75 among COVID+ without PASC was 3.63+/-16.24, with PASC was 10.5+/-14.72, and 3.11+/-15.97 among COVID- (p=0.0001). Male sex had the lowest AI@75 (-0.08+/-14.9) compared to female sex (10.75+/-15.3;< .0001). In adjusted models, PASC, female sex had 8.14+/-2.95 higher AI@75 compared to PASC, male sex (p=0.006), 18.58+/-2.99 higher AI@75 compared to COVID+ without PASC, male sex (p< .0001), 13.81+/-2.11 higher AI@75 compared to COVID-, male sex (p< .0001), and 4.97+/-2.28 higher AI@75 compared to COVID-, female sex (p=0.03). Sex was not associated with RHI or modified the effect of COVID or PASC status on endothelial function Conclusion(s): The effect of COVID and PASC status on arterial stiffness depends on sex. Female sex is associated with increased arterial stiffness (worse arterial elasticity) in the post-acute phase of COVID-19. (Figure Presented).

Adversarial Approaches to Tackle Imbalanced Data in Machine Learning

Real-world applications often involve imbalanced datasets, which have different distributions of examples across various classes. When building a system that requires a high accuracy, the performance of the classifiers is crucial. However, imbalanced datasets can lead to a poor classification performance and conventional techniques, such as synthetic minority oversampling technique. As a result, this study proposed a balance between the datasets using adversarial learning methods such as generative adversarial networks. The model evaluated the effect of data augmentation on both the balanced and imbalanced datasets. The study evaluated the classification performance on three different datasets and applied data augmentation techniques to generate the synthetic data for the minority class. Before the augmentation, a decision tree was applied to identify the classification accuracy of all three datasets. The obtained classification accuracies were 79.9%, 94.1%, and 72.6%. A decision tree was used to evaluate the performance of the data augmentation, and the results showed that the proposed model achieved an accuracy of 82.7%, 95.7%, and 76% on a highly imbalanced dataset. This study demonstrates the potential of using data augmentation to improve the classification performance in imbalanced datasets.

A linear noise approximation for stochastic epidemic models fit to partially observed incidence counts.

Stochastic epidemic models (SEMs) fit to incidence data are critical to elucidating outbreak dynamics, shaping response strategies, and preparing for future epidemics. SEMs typically represent counts of individuals in discrete infection states using Markov jump processes (MJPs), but are computationally challenging as imperfect surveillance, lack of subject-level information, and temporal coarseness of the data obscure the true epidemic. Analytic integration over the latent epidemic process is impossible, and integration via Markov chain Monte Carlo (MCMC) is cumbersome due to the dimensionality and discreteness of the latent state space. Simulation-based computational approaches can address the intractability of the MJP likelihood, but are numerically fragile and prohibitively expensive for complex models. A linear noise approximation (LNA) that approximates the MJP transition density with a Gaussian density has been explored for analyzing prevalence data in large-population settings, but requires modification for analyzing incidence counts without assuming that the data are normally distributed. We demonstrate how to reparameterize SEMs to appropriately analyze incidence data, and fold the LNA into a data augmentation MCMC framework that outperforms deterministic methods, statistically, and simulation-based methods, computationally. Our framework is computationally robust when the model dynamics are complex and applies to a broad class of SEMs. We evaluate our method in simulations that reflect Ebola, influenza, and SARS-CoV-2 dynamics, and apply our method to national surveillance counts from the 2013-2015 West Africa Ebola outbreak.

Biometric Russian Audio-Visual Extended MASKS (BRAVE-MASKS) Corpus: Multimodal Mask Type Recognition Task

In this paper, we present a new multimodal corpus called Biometric Russian Audio-Visual Extended MASKS (BRAVE-MASKS), which is designed to analyze voice and facial characteristics of persons wearing various masks, as well as to develop automatic systems for bimodal verification and identification of speakers. In particular, we tackle the multimodal mask type recognition task (6 classes). As a result, audio, visual and multimodal systems were developed, which showed UAR of 54.83%, 72.02% and 82.01%, respectively, on the Test set. These performances are the baseline for the BRAVE-MASKS corpus to compare the follow-up approaches with the proposed systems.

T2Snaker: a Robotic Coach for Table Tennis

The restrictions imposed by the Covid-19 pandemic has significantly affected all aspects of daily life, especially human contact. Accordingly, an essential aspect of human contact is for training and skill acquisition, which is difficult to conduct under such restrictions. Therefore, we developed T2Snaker, a table tennis training system that comprises a robotic appendage to guide user's hand movements within a VR environment. T2Snaker's novelty lies in its flexibility to guide users movements, yet as it is not directly attached to the user's limbs, it does not impose restrictions on their movements like traditional exoskeleton systems. We explain the implementation specifics of T2Snaker and discuss its preliminary evaluation that focused on table-tennis skill acquisition. The results show that T2Snaker has high potential in skill acquisition, and users praised is ability to guide their movements and proposed various potential application domains. We discuss some design insights based on our work and present future research directions.

Multiroom Speech Emotion Recognition

Automated audio systems, such as speech emotion recognition, can benefit from the ability to work from another room. No research has yet been conducted on the effectiveness of such systems when the sound source originates in a different room than the target system, and the sound has to travel between the rooms through the wall. New advancements in room-impulse-response generators enable a large-scale simulation of audio sources from adjacent rooms and integration into a training dataset. Such a capability improves the performance of data-driven methods such as deep learning. This paper presents the first evaluation of multiroom speech emotion recognition systems. The isolating policies due to COVID-19 presented many cases of isolated individuals suffering emotional difficulties, where such capabilities would be very beneficial. We perform training, with and without an audio simulation generator, and compare the results of three different models on real data recorded in a real multiroom audio scene. We show that models trained without the new generator achieve poor results when presented with multiroom data. We proceed to show that augmentation using the new generator improves the performances for all three models. Our results demonstrate the advantage of using such a generator. Furthermore, testing with two different deep learning architectures shows that the generator improves the results independently of the given architecture.

A Spectrum of Disease: Breast Implant-Associated Anaplastic Large Cell Lymphoma, Atypicals, and Other Implant Associations.

Breast implant associated anaplastic large cell lymphoma (BIA-ALCL) is an uncommon and emerging malignancy caused by textured breast implants. The most common patient presentation is delayed seromas, other presentations include breast asymmetry, overlying skin rashes, palpable masses, lymphadenopathy, and capsular contracture. Confirmed diagnoses should receive lymphoma oncology consultation, multidisciplinary evaluation, and PET-CT or CT scan evaluation prior to surgical treatment. Disease confined to the capsule is curable in the majority of patients with complete surgical resection. BIA-ALCL is now recognized as one disease among a spectrum of inflammatory mediated malignancies which include implant-associated squamous cell carcinoma and B cell lymphoma.

Convolutional Neural Networks for Detection of COVID-19 from Chest X-Rays

The coronavirus (COVID-19) pandemic was rapid in its outbreak, and the contagion of the virus led to an extensive loss of life globally. This study aims to propose an efficient and reliable means to differentiate between chest x-rays indicating COVID-19 and other lung conditions. The proposed methodology involved combining deep learning techniques such as data augmentation, CLAHE image normalization, and transfer learning with eight pre-trained networks. The highest performing networks for binary, 3-class (normal vs. COVID-19 vs. viral pneumonia) and 4-class classifications (normal vs. COVID-19 vs. lung opacity vs. viral pneumonia) were MobileNetV2, InceptionResNetV2, and MobileNetV2, achieving accuracies of 97.5%, 96.69%, and 92.39%, respectively. These results outperformed many state-of-the-art methods conducted to address the challenges relating to the detection of COVID-19 from chest x-rays. The method proposed can serve as a basis for a computer-aided diagnosis (CAD) system to ensure that patients receive timely and necessary care for their respective illnesses. Copyright © 2022, IGI Global.

Automated COVID-19 Detection from WBC-DIFF Scattergram Images with Hybrid CNN Model Using Feature Selection

In the medical diagnosis such as WBC (white blood cell), the scattergram images show the relationships between neutrophils, eosinophils, basophils, lymphocytes, and monocytes cells in the blood. For COVID-19 detection, the distributions of these cells differ in healthy and COVID-19 patients. This study proposes a hybrid CNN model for COVID-19 detection using scatter images obtained from WBC sub (differential-DIFF) parameters instead of CT or X-Ray scans. As a data set, the scattergram images of 335 COVID-19 suspects without chronic disease, collected from the biochemistry department of Elazig Fethi Sekin City Hospital, are examined. At first, the data augmentation is performed by applying HSV(Hue, Saturation, Value) and CIE-1931(Commission Internationale de l'éclairage) conversions. Thus, three different image large sets are obtained as a result of raw, CIE-1931, and HSV conversions. Secondly, feature extraction is applied by giving these images as separate inputs to the CNN model. Finally, the ReliefF feature extraction algorithm is applied to determine the most dominant features in feature vectors and to determine the features that maximize classification accuracy. The obtaining feature vector is classified with high-performance SVM in binary classification. The overall accuracy is 95.2%, and the F1-Score is 94.1%. The results show that the method can successfully detect COVID -19 disease using scattergram images and is an alternative to CT and X-Ray scans.

MMSports'22: 5th International ACM Workshop on Multimedia Content Analysis in Sports

The fifth ACM International Workshop on Multimedia Content Analysis in Sports (ACM MMSports'22) is part of the ACM International Conference on Multimedia 2022 (ACM Multimedia 2022). After two years of pure virtual MMSports workshops due to COVID-19, MMSports'22 is held on-site again. The goal of this workshop is to bring together researchers and practitioners from academia and industry to address challenges and report progress in mining, analyzing, understanding, and visualizing multimedia/multimodal data in sports, sports broadcasts, sports games and sports medicine. The combination of sports and modern technology offers a novel and intriguing field of research with promising approaches for visual broadcast augmentation and understanding, for statistical analysis and evaluation, and for sensor fusion during workouts as well as competitions. There is a lack of research communities focusing on the fusion of multiple modalities. We are helping to close this research gap with this workshop series on multimedia content analysis in sports. Related Workshop Proceedings are available in the ACM DL at: https://dl.acm.org/doi/proceedings/10.1145/3552437. © 2022 Owner/Author.

The effect of COVID-19 on vascular elasticity and liver function in overweight patients.

Objective. To study the changes in the vascular wall, vascular age and metabolic parameters in polymorbid COVID-19 conva-lescents. Material and methods. The study included 62 patients with hypertension who reached the target blood pressure (BP) with dual an-tihypertensive therapy after severe and extremely severe COVID-19. The following examinations were performed: laboratory tests of metabolic parameters, assessment of changes in the vessel elasticity indices (pulse-wave velocity (PWV), augmentation index (AI), central systolic BP (cSBP), 24-hour BP monitoring, and non-invasive markers of liver fibrosis. Results. According to office BP measurements, after the coronavirus infection, an increase in systolic BP (SBP) by 29.6% and di-astolic BP (DBP) by 23.6%, as well as heart rate (HR) by 11.8% (p<0.05) was reported during regular antihypertensive therapy. In addition, 24-hour BP monitoring data indicated an increase in the average daily SBP, DBP, and heart rate. After the coronavirus infection, an increase in PWV by 35.4% (p<0.05), AI by 24.4% (p<0.05), cSBP by 22.1% were reported. Carbohydrate and lipid metabolism parameters deteriorated. A pronounced adverse effect of coronavirus infection on liver function was observed. The vascular age (according to the modified SCORE scale) increased by 6 years (p<0.05). Conclusion. Our study showed that patients after severe and extremely severe COVID-19 have a high risk of liver fibrosis, hypertension and lipid metabolism control worsening and accelerating vascular aging.Copyright © 2023, Media Sphera Publishing Group. All rights reserved.

The Optimization of COVID-19 Detection Based on DesNet Model

In recent years, with the pandemic of COVID-19, how to identify the positive cases of COVID-19 accurately and rapidly from patients has become the key to block the spread of the epidemic and assist clinical diagnosis. In this paper, a COVID-19 detection model was constructed for the purpose to identify the positive cases from patients with other lung diseases as well as the normal using the chest X-ray images. The basic structure of the detection system is a CNN model based on DesNet with some optimization algorithms and the accuracy has reached 94.2%. We also applied three multi-sample data augmentation methods: SMOTE, mixup and CutMix to the model to analyze their performance. By applying these methods, the model finally reached 97.9% on test set and showed a good generalization on other datasets, which could reach over 80% without extra training. The results show that using transfer learning and some muli-sample data augmentation methods can significantly improve the accuracy and overcome overfitting problem of fewshot learning, while others may not be so effective. © 2023 IEEE.