Dynamics and profiles of a degenerated reaction-diffusion host-pathogen model with apparent and inapparent infection period.

Inapparent infection plays an important role in the disease spread, which is an infection by a pathogen that causes few or no signs or symptoms of infection in the host. Many pathogens, including HIV, typhoid fever, and coronaviruses such as COVID-19 spread in their host populations through inapparent infection. In this paper, we formulated a degenerated reaction-diffusion host-pathogen model with multiple infection period. We split the infectious individuals into two distinct classes: apparent infectious individuals and inapparent infectious individuals, coming from exposed individuals with a ratio of (1-p) and p, respectively. Some preliminary results and threshold-type results are achieved by detailed mathematical analysis. We also investigate the asymptotic profiles of the positive steady state (PSS) when the diffusion rate of susceptible individuals approaches zero or infinity. When all parameters are all constants, the global attractivity of the constant endemic equilibrium is established. It is verified by numerical simulations that spatial heterogeneity of the transmission rates can enhance the intensity of an epidemic. Especially, the transmission rate of inapparent infectious individuals significantly increases the risk of disease transmission, compared to that of apparent infectious individuals and pathogens in the environment, and we should pay special attentions to how to regulate the inapparent infectious individuals for disease control and prevention, which is consistent with the result on the sensitive analysis to the transmission rates through the normalized forward sensitivity index. We also find that disinfection of the infected environment is an important way to prevent and eliminate the risk of environmental transmission.

COVID-19 diagnosis utilizing wavelet-based contrastive learning with chest CT images.

The pandemic caused by the coronavirus disease 2019 (COVID-19) has continuously wreaked havoc on human health. Computer-aided diagnosis (CAD) system based on chest computed tomography (CT) has been a hotspot option for COVID-19 diagnosis. However, due to the high cost of data annotation in the medical field, it happens that the number of unannotated data is much larger than the annotated data. Meanwhile, having a highly accurate CAD system always requires a large amount of labeled data training. To solve this problem while meeting the needs, this paper presents an automated and accurate COVID-19 diagnosis system using few labeled CT images. The overall framework of this system is based on the self-supervised contrastive learning (SSCL). Based on the framework, our enhancement of our system can be summarized as follows. 1) We integrated a two-dimensional discrete wavelet transform with contrastive learning to fully use all the features from the images. 2) We use the recently proposed COVID-Net as the encoder, with a redesign to target the specificity of the task and learning efficiency. 3) A new pretraining strategy based on contrastive learning is applied for broader generalization ability. 4) An additional auxiliary task is exerted to promote performance during classification. The final experimental result of our system attained 93.55%, 91.59%, 96.92% and 94.18% for accuracy, recall, precision, and F1-score respectively. By comparing results with the existing schemes, we demonstrate the performance enhancement and superiority of our proposed system.

A self-supervised COVID-19 CT recognition system with multiple regularizations.

The diagnosis of Coronavirus Disease 2019 (COVID-19) exploiting machine learning algorithms based on chest computed tomography (CT) images has become an important technology. Though many excellent computer-aided methods leveraging CT images have been designed, they do not possess sufficiently high recognition accuracy. Besides, these methods entail vast amounts of training data, which might be difficult to be satisfied in some real-world applications. To address these two issues, this paper proposes a novel COVID-19 recognition system based on CT images, which has high recognition accuracy, while only requiring a small amount of training data. Specifically, the system possesses the following three improvements: 1) Data: a novel redesigned BCELoss that incorporates Label Smoothing, Focal Loss, and Label Weighting Regularization (LSFLLW-R) technique for optimizing the solution space and preventing overfitting, 2) Model: a backbone network processed by two-phase contrastive self-supervised learning for classifying multiple labels, and 3) Method: a decision-fusing ensemble learning method for getting a more stable system, with balanced metric values. Our proposed system is evaluated on the small-scale expanded COVID-CT dataset, achieving an accuracy of 94.3%, a precision of 94.1%, a recall (sensitivity) of 93.4%, an F1-score of 94.7%, and an Area Under the Curve (AUC) of 98.9%, for COVID-19 diagnosis, respectively. These experimental results verify that our system can not only identify pathological locations effectively, but also achieve better performance in terms of accuracy, generalizability, and stability, compared with several other state-of-the-art COVID-19 diagnosis methods.

Encouraging activity and exercise among children and young people using computer vision and machine learning during gaming

IntroductionPopulation health and wellbeing is a priority in the UK, with new initiatives that empower children to live healthier lives. Excess weight has also been associated to worse outcomes during the COVID-19 pandemic period, complicated by reduced activity within the confinements of a home environment and coupled by increased screen time with remote classroom practices. As a result, children and young people now interact with computer interfaces in their home environment for education, gaming and healthcare purposes for prolonged periods and in new ways.MethodThere is a growing interest in Natural User Interfaces (NUIs) that use natural hand and body gestures to interact with computers. Advances to these technologies mean that they are now more accurate, easier to use and instead of requiring expensive depth cameras, can be operated using simple webcams. In this study, OpenCV library is used to track user movement by calculating the pixel difference between two frames and create a catalogue of exercises. We use PyTorch exercise recognition model to check the status of the user every 8 frames. These are recognised by using Convolutional Neural Networks (CNNs) with static training from datasets and offer users the option to create personalised exercises.ResultWe present University College London’s (UCL) Motion- Input supporting DirectX: Gestures for at-home exercises. This exercise module can recognise six repetitious static exercises, such as running on the spot, squatting, cycling on an exercise bike, and rowing on a rowing machine using a webcam. This is intended for integrated exercise triggers during gaming in place of a handheld control panel (i.e., jumping to trigger commands), remote coaching for fitness and bespoke treatment plans for physical rehabilitation.ConclusionWebcam-based computer vision exercise catalogues using everyday devices like webcams, hold the potential to encourage healthier and more active behaviours during screen-based activities.

MotionInput v2.0 supporting DirectX: A modular library of open-source gesture-based machine learning and computer vision methods for interacting and controlling existing software with a webcam (preprint)

Touchless computer interaction has become an important consideration during the COVID-19 pandemic period. Despite progress in machine learning and computer vision that allows for advanced gesture recognition, an integrated collection of such open-source methods and a user-customisable approach to utilising them in a low-cost solution for touchless interaction in existing software is still missing. In this paper, we introduce the MotionInput v2.0 application. This application utilises published open-source libraries and additional gesture definitions developed to take the video stream from a standard RGB webcam as input. It then maps human motion gestures to input operations for existing applications and games. The user can choose their own preferred way of interacting from a series of motion types, including single and bi-modal hand gesturing, full-body repetitive or extremities-based exercises, head and facial movements, eye tracking, and combinations of the above. We also introduce a series of bespoke gesture recognition classifications as DirectInput triggers, including gestures for idle states, auto calibration, depth capture from a 2D RGB webcam stream and tracking of facial motions such as mouth motions, winking, and head direction with rotation. Three use case areas assisted the development of the modules: creativity software, office and clinical software, and gaming software. A collection of open-source libraries has been integrated and provide a layer of modular gesture mapping on top of existing mouse and keyboard controls in Windows via DirectX. With ease of access to webcams integrated into most laptops and desktop computers, touchless computing becomes more available with MotionInput v2.0, in a federated and locally processed method.

Preparing Workplaces for Digital Transformation: An Integrative Review and Framework of Multi-Level Factors.

The rapid advancement of new digital technologies, such as smart technology, artificial intelligence (AI) and automation, robotics, cloud computing, and the Internet of Things (IoT), is fundamentally changing the nature of work and increasing concerns about the future of jobs and organizations. To keep pace with rapid disruption, companies need to update and transform business models to remain competitive. Meanwhile, the growth of advanced technologies is changing the types of skills and competencies needed in the workplace and demanded a shift in mindset among individuals, teams and organizations. The recent COVID-19 pandemic has accelerated digitalization trends, while heightening the importance of employee resilience and well-being in adapting to widespread job and technological disruption. Although digital transformation is a new and urgent imperative, there is a long trajectory of rigorous research that can readily be applied to grasp these emerging trends. Recent studies and reviews of digital transformation have primarily focused on the business and strategic levels, with only modest integration of employee-related factors. Our review article seeks to fill these critical gaps by identifying and consolidating key factors important for an organization's overarching digital transformation. We reviewed studies across multiple disciplines and integrated the findings into a multi-level framework. At the individual level, we propose five overarching factors related to effective digital transformation among employees: technology adoption; perceptions and attitudes toward technological change; skills and training; workplace resilience and adaptability, and work-related wellbeing. At the group-level, we identified three factors necessary for digital transformation: team communication and collaboration; workplace relationships and team identification, and team adaptability and resilience. Finally, at the organizational-level, we proposed three factors for digital transformation: leadership; human resources, and organizational culture/climate. Our review of the literature confirms that multi-level factors are important when planning for and embarking on digital transformation, thereby providing a framework for future research and practice.

Corticosteroids treatment in severe patients with COVID-19: a propensity score matching study (preprint)

Objectives Explore the efficacy of corticosteroid treatment in patients with severe COVID-19 pneumonia and the association between corticosteroid use and patient mortality.Methods A retrospective investigation was made on the medical records of the patients with severe and critical patients with COVID-19 pneumonia from January to February 2020. First, the patients who received corticosteroid treatment were compared with patients without given corticosteroid treatment. Then a propensity score matching method was used to control confounding factors. Cox survival regression analysis was used to evaluate the effect of corticosteroid therapy on the mortality of severe and critical patients with COVID-19.Results A total of 371 severe and critical patients were enrolled in our statistics. 209 patients were treated with corticosteroid therapy. Most of them were treated with methylprednisolone (197[94.3%]). The median corticosteroid therapy was applied 3(IQR 2–6) days after admission, 13(IQR 10–17) days after symptoms appeared. Temperature on admission(OR = 1.255,[95%CI 1.021–1.547],p = 0.032), ventilation(OR = 1.926,[95%CI 1.148–3.269],p = 0.014) and ICU admission(OR = 3.713, [95%CI 1.776–8.277],p < 0.001) were significantly associated with corticosteroids use. After PS matching, the cox regression survival analysis showed that corticosteroid use was significantly associated with a lower mortality rate (HR = 0.592, [95%CI 0.406–0.862], p = 0.006).Conclusion Corticosteroid therapy use in severe and critical patients with COVID-19 pneumonia leads to lower mortality but may cause other side effects. Corticosteroid therapy should be used carefully.

Corticosteroids treatment in severe patients with COVID-19: a propensity score matching study (preprint)

Objectives Explore the efficacy of corticosteroid treatment in patients with severe COVID-19 pneumonia and the association between corticosteroid use and patient mortality.Methods A retrospective investigation was made on the medical records of the patients with severe and critical patients with COVID-19 pneumonia from January to February 2020. First, the patients who received corticosteroid treatment were compared with patients without given corticosteroid treatment. Then a propensity score matching method was used to control confounding factors. Cox survival regression analysis was used to evaluate the effect of corticosteroid therapy on the mortality of severe and critical patients with COVID-19.Results A total of 371 severe and critical patients were enrolled in our statistics. 209 patients were treated with corticosteroid therapy. Most of them were treated with methylprednisolone (197[94.3%]). The median corticosteroid therapy was applied 3(IQR 2–6) days after admission, 13(IQR 10–17) days after symptoms appeared. Temperature on admission(OR = 1.255,[95%CI 1.021–1.547],p = 0.032), ventilation(OR = 1.926,[95%CI 1.148–3.269],p = 0.014) and ICU admission(OR = 3.713, [95%CI 1.776–8.277],p < 0.001) were significantly associated with corticosteroids use. After PS matching, the cox regression survival analysis showed that corticosteroid use was significantly associated with a lower mortality rate (HR = 0.592, [95%CI 0.406–0.862], p = 0.006).Conclusion Corticosteroid therapy use in severe and critical patients with COVID-19 pneumonia leads to lower mortality but may cause other side effects. Corticosteroid therapy should be used carefully.

Accelerating drug repurposing for COVID-19 via modeling drug mechanism of action with large scale gene-expression profiles (preprint)

The novel coronavirus disease, named COVID-19, emerged in China in December 2019, and has rapidly spread around the world. It is clearly urgent to fight COVID-19 at global scale. The development of methods for identifying drug uses based on phenotypic data can improve the efficiency of drug development. However, there are still many difficulties in identifying drug applications based on cell picture data. This work reported one state-of-the-art machine learning method to identify drug uses based on the cell image features of 1024 drugs generated in the LINCS program. Because the multi-dimensional features of the image are affected by non-experimental factors, the characteristics of similar drugs vary greatly, and the current sample number is not enough to use deep learning and other methods are used for learning optimization. As a consequence, this study is based on the supervised ITML algorithm to convert the characteristics of drugs. The results show that the characteristics of ITML conversion are more conducive to the recognition of drug functions. The analysis of feature conversion shows that different features play important roles in identifying different drug functions. For the current COVID-19, Chloroquine and Hydroxychloroquine achieve antiviral effects by inhibiting endocytosis, etc., and were classified to the same community. And Clomiphene in the same community inibited the entry of Ebola Virus, indicated a similar MoAs that could be reflected by cell image.