A Hybrid Model of Deep Learning Features and Clinical Features for Severe Cases Predication of COVID-19

COVID-19 has spread around the world since 2019. Approximately 6.5% of COVID-19 a risk of developing severe disease with high mortality rate. To reduce the mortality rate and provide appropriate treatment, this research established an integrated models with to predict the clinical outcome of COVID-19 patients with clinical, deep learning and radiomics features. To obtain the optimal feature combination for prediction, 9 clinical features combination was selected from all available clinical factors after using LASSO, 18 deep learning features from U-Net architecture, and 9 radiomics features from segmentation result. A total of 213 COVID-19 patients and 335 non-COVID-19 patients from 5 hospitals were enrolled and used as training and test sample in this research. The proposed model obtained an accuracy, precision, recall, specificity, F1-score and ROC curve of 0.971, 0.943, 0.937, 0.974, 0.941 and 0.979, respectively, which exceeds the related work using only clinical, deep learning or radiomics factors. © 2023 SPIE.

Supplement of iron abrogates SARS-CoV-2 pseudovirus infection in a 3D model of vascularized organoids

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) cause severe outbreak of coronavirus disease 2019 (COVID-19). Even though vaccination, the spread of SARS-CoV-2 is still continue. It is urgent to have a model that can efficiently evaluate potential therapeutic agents to counteract SARS-CoV-2 infection. Iron is an essential molecule for maintaining homeostasis. Supplement of iron significantly to affect virus infection. But the detailed mechanisms of iron on regulating SARS-CoV-2 infection are still unveiled. The three-dimensional (3D) model is a promising system for drug screening and disease progression analysis. Organoid is a typical 3D culture system that recapitulates genetic characteristics and phenotypic features of organs within body. Vasculature is prevalent for all various organs or tumors in the body which transport nutrients, oxygen and metabolites to maintain cellular homeostasis. Thus, we have established a 3D model of vascularized organoid to evaluate the effects of iron on infectivity of SARS-CoV-2 pseudovirus to provide the novel therapeutic strategy in coping SARS-CoV-2 infection. © 2022 IEEE.

Assessment of Atmospheric PM2.5 and PCDD/Fs Collected by Different High-volume Ambient Air Sampling Systems

To evaluate the difference in hazardous air pollutants in PM2.5 between reference method (National Institute of Environmental Analysis;NIEAA205) and high-volume air sampler (European standard:EN14907 and Japan method), we set up a sampling station on the campus of National Yang-Ming Chiao Tung University, northern Taiwan, during 2014-2015. Both vapor and solid phases of dioxins were collected using high-volume samplers, according to EN14907 and Japan method. The flow rate was set at 500 L min(-1) and 1000 L min(-1), respectively. To compare the difference with the high-volume air sampler, we simultaneously used the reference air sampler based on Taiwan NIEA A205.11C, at the flow rate of 16.7 L min(-1) (BGI PQ200-FRM). The mass concentrations of PM2.5 measured with NIEA A205, EN14907, and Japan method were 20.2 +/- 8.79, 25.4 +/- 10.5 and 28.6 +/- 13.9 mu g m(-3), respectively. The difference of the mass concentration of PM2.5 obtained from two different methods was lower than 3.9%. Moreover, the concentrations of PCDD/F between solid and vapor phases were 56.9-1,090 and 38.6-67.1 fg m(-3) via EN14907 and 51.1-1,150 and 18.4-81.8 fg m(-3) via Japan method, respectively. Obviously, there is no significant difference between these two samplers. Compared to the method of NIEA, high volume air sampling method not only provided equivalently good quality data but offer a higher sample quantity for analyzing the trace level chemical component of hazardous air pollutants and the toxicity in different areas.

COKG-QA: Multi-hop Question Answering over COVID-19 Knowledge Graphs

COVID-19 evolves rapidly and an enormous number of people worldwide desire instant access to COVID-19 information such as the overview, clinic knowledge, vaccine, prevention measures, and COVID-19 mutation. Question answering (QA) has become the mainstream interaction way for users to consume the ever-growing information by posing natural language questions. Therefore, it is urgent and necessary to develop a QA system to offer consulting services all the time to relieve the stress of health services. In particular, people increasingly pay more attention to complex multi-hop questions rather than simple ones during the lasting pandemic, but the existing COVID-19 QA systems fail to meet their complex information needs. In this paper, we introduce a novel multi-hop QA system called COKG-QA, which reasons over multiple relations over large-scale COVID-19 Knowledge Graphs to return answers given a question. In the field of question answering over knowledge graph, current methods usually represent entities and schemas based on some knowledge embedding models and represent questions using pre-trained models. While it is convenient to represent different knowledge (i.e., entities and questions) based on specified embeddings, an issue raises that these separate representations come from heterogeneous vector spaces. We align question embeddings with knowledge embeddings in a common semantic space by a simple but effective embedding projection mechanism. Furthermore, we propose combining entity embeddings with their corresponding schema embeddings which served as important prior knowledge, to help search for the correct answer entity of specified types. In addition, we derive a large multi-hop Chinese COVID-19 dataset (called COKG-DATA for remembering) for COKG-QA based on the linked knowledge graph OpenKG-COVID19 launched by OpenKG((1)), including comprehensive and representative information about COVID-19. COKG-QA achieves quite competitive performance in the 1-hop and 2-hop data while obtaining the best result with significant improvements in the 3-hop. And it is more efficient to be used in the QA system for users. Moreover, the user study shows that the system not only provides accurate and interpretable answers but also is easy to use and comes with smart tips and suggestions.

Graph-BAS(3)Net: Boundary-Aware Semi-Supervised Segmentation Network with Bilateral Graph Convolution

Semi-supervised learning (SSL) algorithms have attracted much attentions in medical image segmentation by leveraging unlabeled data, which challenge in acquiring massive pixel-wise annotated samples. However, most of the existing SSLs neglected the geometric shape constraint in object, leading to unsatisfactory boundary and non-smooth of object. In this paper, we propose a novel boundary-aware semi-supervised medical image segmentation network, named Graph-BAS(3)Net, which incorporates the boundary information and learns duality constraints between semantics and geometrics in the graph domain. Specifically, the proposed method consists of two components: a multi-task learning framework BAS(3)Net and a graph-based cross-task module BGCM. The BAS(3)Net improves the existing GAN-based SSL by adding a boundary detection task, which encodes richer features of object shape and surface. Moreover, the BGCM further explores the co-occurrence relations between the semantics segmentation and boundary detection task, so that the network learns stronger semantic and geometric correspondences from both labeled and unlabeled data. Experimental results on the LiTS dataset and COVID-19 dataset confirm that our proposed Graph-BAS(3) Net outperforms the state-of-the-art methods in semi-supervised segmentation task.

PIXEL-LEVEL AND AFFINITY-LEVEL KNOWLEDGE DISTILLATION FOR UNSUPERVISED SEGMENTATION OF COVID-19 LESIONS

Automatic segmentation of COVID-19 lesions is essential for computer-aided diagnosis. However, this task remains challenging because widely-used supervised based methods require large-scale annotated data that is difficult to obtain. Although an unsupervised method based on anomaly detection has shown promising results in [1], its performance is relatively poor. We address this problem by proposing a pixel-level and affinity-level knowledge distillation method. It obtains a pre-trained teacher network with rich semantic knowledge of CT images by constructing and training an auto-encoder at first, and then trains a student network with the same architecture as the teacher by distilling the teacher's knowledge only from normal CT images, and finally localizes COVID-19 lesions using the feature discrepancy between the teacher and the student networks. Besides, except for the traditional pixel-level distillation, we design the affinity-level distillation that takes into account the pairwise relationship of features to fully distill effective knowledge. We evaluate this method by using three different COVID-19 datasets and the experimental results show that the segmentation performance is largely improved when it is compared with the other existing unsupervised anomaly detection methods. © 2022 IEEE

GRAPH-BASED PYRAMID GLOBAL CONTEXT REASONING WITH A SALIENCY-AWARE PROJECTION FOR COVID-19 LUNG INFECTIONS SEGMENTATION

Coronavirus Disease 2019 (COVID-19) has rapidly spread in 2020, emerging a mass of studies for lung infection segmentation from CT images. Though many methods have been proposed for this issue, it is a challenging task because of infections of various size appearing in different lobe zones. To tackle these issues, we propose a Graph-based Pyramid Global Context Reasoning (Graph-PGCR) module, which is capable of modeling long-range dependencies among disjoint infections as well as adapt size variation. We first incorporate graph convolution to exploit long-term contextual information from multiple lobe zones. Different from previous average pooling or maximum object probability, we propose a saliency-aware projection mechanism to pick up infection-related pixels as a set of graph nodes. After graph reasoning, the relation-aware features are reversed back to the original coordinate space for the down-stream tasks. We further construct multiple graphs with different sampling rates to handle the size variation problem. To this end, distinct multi-scale long-range contextual patterns can be captured. Our Graph-PGCR module is plug-and-play, which can be integrated into any architecture to improve its performance. Experiments demonstrated that the proposed method consistently boost the performance of state-of-the-art backbone architectures on both of public and our private COVID-19 datasets.

Public preference and vaccination willingness for COVID-19 vaccine in China

Objective: To understand public preference and immunization willingness for COVID-19 vaccine in China, and analyze influence factors, provide references for sufficient vaccination coverage. Methods: An online D-efficient discrete choice experiment was conducted from Jan 5, 2021 to Jan 12, 2021, in 1 241 people (with 1066 valid feedbacks), using choice sets with 5 vaccine attributes:protection rate, adverse effect, protection duration, convenience of vaccination, and out-of-pocket cost.Conditional Logit and panel mixed Logit models were used to analyze the effect of vaccine attributes on preferences, while random-effects Logit model was used to analyze the effect of vaccine attributes on vaccination willingness. Results: The COVID-19 vaccine with high protection rate(βefficacy 95%=1.76, P<0.001), low adverse effects(βlow risk=1.93, P<0.001), long protection duration (β5 years=0.59, P<0.001), convenient vaccination process(βconvenient=0.53, P<0.001), and less cost(βcost=0.14, P<0.001) was preferred by the public. Conclusion: Public preference and vaccination willingness for COVID-19 vaccine influenced by all 5 vaccine attributes (protection rate, adverse effect, protection duration, convenience of vaccination, and out-of-pocket cost).The efficacy and safety of the vaccine had the most significant impact. © 2021, Editorial Department of Fudan University Journal of Medical Sciences. All right reserved.

BG-Net: Boundary-Guided Network for Lung Segmentation on Clinical CT Images

Lung segmentation on CT images is a crucial step for a computer-aided diagnosis system of lung diseases. The existing deep learning based lung segmentation methods are less efficient to segment lungs on clinical CT images, especially that the segmentation on lung boundaries is not accurate enough due to complex pulmonary opacities in practical clinics. In this paper, we propose a boundary-guided network (BG-Net) to address this problem. It contains two auxiliary branches that seperately segment lungs and extract the lung boundaries, and an aggregation branch that efficiently exploits lung boundary cues to guide the network for more accurate lung segmentation on clinical CT images. We evaluate the proposed method on a private dataset collected from the Osaka university hospital and four public datasets including StructSeg [1], HUG [2], VESSEL12 [3], and a Novel Coronavirus 2019 (COVID-19) dataset [4]. Experimental results show that the proposed method can segment lungs more accurately and outperform several other deep learning based methods.

Unsupervised Detection of Pulmonary Opacities for Computer-Aided Diagnosis of COVID-19 on CT Images

COVID-19 emerged towards the end of 2019 which was identified as a global pandemic by the world heath organization (WHO). With the rapid spread of COVID-19, the number of infected and suspected patients has increased dramatically. Chest computed tomography (CT) has been recognized as an efficient tool for the diagnosis of COVID-19. However, the huge CT data make it difficult for radiologist to fully exploit them on the diagnosis. In this paper, we propose a computer-aided diagnosis system that can automatically analyze CT images to distinguish the COVID-19 against to community-acquired pneumonia (CAP). The proposed system is based on an unsupervised pulmonary opacity detection method that locates opacity regions by a detector unsupervisedly trained from CT images with normal lung tissues. Radiomics based features are extracted insides the opacity regions, and fed into classifiers for classification. We evaluate the proposed CAD system by using 200 CT images collected from different patients in several hospitals. The accuracy, precision, recall, fl-score and AUC achieved are 95.5%, 100%, 91%, 95.1% and 95.9% respectively, exhibiting the promising capacity on the differential diagnosis of COVID-19 from CT images.

Visualising regional disparities in the risk of COVID-19 at different phases of lockdown in England

Since late January 2020 when the first coronavirus case reached England, United Kingdom, the coronavirus disease 2019 (COVID-19) has spread rapidly and widely across all local authorities (LAs) in England. In this featured graphic, we visualise how COVID-19 severity changes nationally and locally from 30 January to 23 November 2020. The geo-visualisation shows that there have been large regional disparities in the severity of the outbreak, and the epicentres have shifted from Greater London, Leicester, to the North of England and remained in the North during pre-lockdown, post-lockdown, easing lockdown and second national lockdown phases. We further find that the increase in the testing capacity may partially explain the sharp increase in the confirmed cases during the second wave of the pandemic. However, the disparities in the severity of COVID-19 (i.e., confirmed cases and deaths) among LAs in England become more significant over time. It further sheds light on the necessity of establishing decisive and timely responses to cope with local pandemic situations.

The adherence to modified callers queries (MCQ) of emergency medical dispatch (EMD) during COVID-19 outbreaks for out-of-hospital cardiac arrest

Purpose: Setting modified-callers-queries (MCQ) was recommended for emergency medical dispatch (EMD) for COVID-19 risks screening during the outbreaks. For out-of-hospital cardiac arrest calls, the adherence to MCQ and its influence to dispatcher-assisted CPR were not known. Materials and methods: A COVID-19-risk MCQ protocol was designed for EMD for safer corresponding response. The three major additional queries included A. The quarantine status of patient/family, B. Patient symptoms (i.e., fever/or respiratory complaints), C. TOCC situations in the recent 14-day period of patient/family including: recent travel (T) to the epidemic regions, occupations (O) with high risk for client contact such as healthcare provider, flight attendant, etc., any close contact (C1) with confirmed COVID-19 patient or person been quarantined, and close contact with a cluster (C2) of people with similar symptoms. The dispatchers’ adherence to the COVID-19-risk MCQ during the outbreaks for EMS calls of non-traumatic OHCA was retrospectively evaluated using audio records. Data were analyzed using Pearson's chi-squared test and Kruskal-Wallis test with SPSS-Version-22. Results: For totally 153 eligible OHCA calls, the adherence to querying were noted for A. quarantine on 44 (28.8%) cases, for B. symptoms on 82 (53.6%), for C. any TOCC on 105 (68.6%) cases – T: 102 (66.7%), O: 31 (20.2%), C1: 71 (46.4%), C2: 26 (17.0%);and completed TOCC on only 14 (9.2%) cases. Completed MCQ (all three A, B, C) were adhered on only 10 (6.5%;[95%CI: 3.6–11.6%]) cases, and 45 (29.4%;[95%CI: 22.8–37.1%]) cases failed to receive any COVID-19-risk MCQ. Eight cases (8/105, 7.6%) inadequately received TOCC queries prior to recognizing patient consciousness. The time intervals (median, IOR) for call-to-chest-compression and total MCQ of those completely queried cases were 290 (206, 334) s. and 52 (22, 94) s. Conclusions: The EMD adherence to COVID-19-risk MCQ would be unsatisfied to achieve under the circumstances of OHCA. MCQ would influence call-to-compression for dispatcher-assisted CPR.

Analysis of the mechanism for potential anti-novel coronavirus 2019-nCoV drugs based on diagnosis and treatment guidelines

The novel coronavirus pneumonia is an acute respiratory infectious disease caused by novel coronavirus(2019- nCoV). The 2019- nCoV genome sequence and the clinical symptoms caused by 2019- nCoV are different from those of the previous large outbreak of SARS virus, and no specific antiviral drugs are available nowadays. In order to treat pneumonia cases of 2019-nCoV infection, the National Health Commission has released several versions of The Pneumonia Diagnosis and Treatment guidelines for Novel Coronavirus Infection. Based on domestic and foreign literature, this paper briefly describes the clinical efficacy and mechanism of the chemical drugs and traditional Chinese medicines recommended for the treatment of 2019-nCoV infections in the Treatment guidelines, so as to provide a necessary theoretical basis for the selection of anti-2019-nCoV drugs.