Dynamic chest computed tomography change analysis and prediction of length of stay for delta variant COVID-19 patients

OBJECTIVE: As hospital admission rate is high during the COVID-19 pandemic, hospital length of stay (LOS) is a key indicator of medical resource allocation. This study aimed to elucidate specific dynamic longitudinal computed tomography (CT) imaging changes for patients with COVID-19 over in-hospital and predict individual LOS of COVID-19 patients with Delta variant of SARS-CoV-2 using the machine learning method. MATERIALS AND METHODS: This retrospective study recruited 448 COVID-19 patients with a total of 1761 CT scans from July 14, 2021 to August 20, 2021 with an averaged hospital LOS of 22.5 ± 7.0 days. Imaging features were extracted from each CT scan, including CT morphological characteristics and artificial intelligence (AI) extracted features. Clinical features were obtained from each patient's initial admission. The infection distribution in lung fields and progression pattern tendency was analyzed. Then, to construct a model to predict patient LOS, each CT scan was considered as an independent sample to predict the LOS from the current CT scan time point to hospital discharge combining with the patients' corresponding clinical features. The 1761 follow-up CT data were randomly split into training set and testing set with a ratio of 7:3 at patient-level. A total of 85 most related clinical and imaging features selected by Least Absolute Shrinkage and Selection Operator were used to construct LOS prediction model. RESULTS: Infection-related features were obtained, such as the percentage of the infected region of lung, ground-glass opacity (GGO), consolidation and crazy-paving pattern, and air bronchograms. Their longitudinal changes show that the progression changes significantly in the earlier stages (0–3 days to 4–6 days), and then, changes tend to be statistically subtle, except for the intensity range between (−470 and −70) HU which exhibits a significant increase followed by a continuous significant decrease. Furthermore, the bilateral lower lobes, especially the right lower lobe, present more severe. Compared with other models, combining the clinical, imaging reading, and AI features to build the LOS prediction model achieved the highest R2 of 0.854 and 0.463, Pearson correlation coefficient of 0.939 and 0.696, and lowest mean absolute error of 2.405 and 4.426, and mean squared error of 9.176 and 34.728 on the training and testing set. CONCLUSION: The most obvious progression changes were significantly in the earlier stages (0–3 days to 4–6 days) and the bilateral lower lobes, especially the right lower lobe. GGO, consolidation, and crazy-paving pattern and air bronchograms are the most main CT findings according to the longitudinal changes of infection-related features with LOS (day). The LOS prediction model of combining clinical, imaging reading, and AI features achieved optimum performance.

Safety and immunogenicity of aerosolised Ad5-nCoV, intramuscular Ad5-nCoV, or inactivated COVID-19 vaccine CoronaVac given as the second booster following three doses of CoronaVac: a multicentre, open-label, phase 4, randomised trial

Background Aerosolised Ad5-nCoV is the first approved mucosal respiratory COVID-19 vaccine to be used as a booster after the primary immunisation with COVID-19 vaccines. This study aimed to evaluate the safety and immunogenicity of aerosolised Ad5-nCoV, intramuscular Ad5-nCoV, or inactivated COVID-19 vaccine CoronaVac given as the second booster. Methods This is an open-label, parallel-controlled, phase 4 randomised trial enrolling healthy adult participants (≥18 years) who had completed a two-dose primary immunisation and a booster immunisation with inactivated COVID-19 vaccines (CoronaVac only) at least 6 months before, in Lianshui and Donghai counties, Jiangsu Province, China. We recruited eligible participants from previous trials in China (NCT04892459, NCT04952727, and NCT05043259) as cohort 1 (with the serum before and after the first booster dose available), and from eligible volunteers in Lianshui and Donghai counties, Jiangsu Province, as cohort 2. Participants were randomly assigned at a ratio of 1:1:1, using a web-based interactive response randomisation system, to receive the fourth dose (second booster) of aerosolised Ad5-nCoV (0·1 mL of 1·0 × 1011 viral particles per mL), intramuscular Ad5-nCoV (0·5 mL of 1·0 × 1011 viral particles per mL), or inactivated COVID-19 vaccine CoronaVac (0·5 mL), respectively. The co-primary outcomes were safety and immunogenicity of geometric mean titres (GMTs) of serum neutralising antibodies against prototype live SARS-CoV-2 virus 28 days after the vaccination, assessed on a per-protocol basis. Non-inferiority or superiority was achieved when the lower limit of the 95% CI of the GMT ratio (heterologous group vs homologous group) exceeded 0·67 or 1·0, respectively. This study was registered with ClinicalTrials.gov, NCT05303584 and is ongoing. Findings Between April 23 and May 23, 2022, from 367 volunteers screened for eligibility, 356 participants met eligibility criteria and received a dose of aerosolised Ad5-nCoV (n=117), intramuscular Ad5-nCoV (n=120), or CoronaVac (n=119). Within 28 days of booster vaccination, participants in the intramuscular Ad5-nCoV group reported a significantly higher frequency of adverse reactions than those in the aerosolised Ad5-nCoV and intramuscular CoronaVac groups (30% vs 9% and 14%, respectively;p<0·0001). No serious adverse events related to the vaccination were reported. The heterologous boosting with aerosolised Ad5-nCoV triggered a GMT of 672·4 (95% CI 539·7–837·7) and intramuscular Ad5-nCoV triggered a serum neutralising antibody GMT of 582·6 (505·0–672·2) 28 days after the booster dose, both of which were significantly higher than the GMT in the CoronaVac group (58·5 [48·0–71·4];p<0·0001). Interpretation A heterologous fourth dose (second booster) with either aerosolised Ad5-nCoV or intramuscular Ad5-nCoV was safe and highly immunogenic in healthy adults who had been immunised with three doses of CoronaVac. Funding National Natural Science Foundation of China, Jiangsu Provincial Science Fund for Distinguished Young Scholars, and Jiangsu Provincial Key Project of Science and Technology Plan.

Large-scale screening of COVID-19 from community acquired pneumonia using infection size-aware classification.

The worldwide spread of coronavirus disease (COVID-19) has become a threatening risk for global public health. It is of great importance to rapidly and accurately screen patients with COVID-19 from community acquired pneumonia (CAP). In this study, a total of 1658 patients with COVID-19 and 1027 CAP patients underwent thin-section CT. All images were preprocessed to obtain the segmentations of infections and lung fields. A set of handcrafted location-specific features was proposed to best capture the COVID-19 distribution pattern, in comparison to conventional CT severity score (CT-SS) and Radiomics features. An infection Size Aware Random Forest method (iSARF) was used for classification. Experimental results show that the proposed method yielded best performance when using the handcrafted features with sensitivity of 91.6%, specificity of 86.8%, and accuracy of 89.8% over state-of-the-art classifiers. Additional test on 734 subjects with thick slice images demonstrates great generalizability. It is anticipated that our proposed framework could assist clinical decision making. Furthermore, the data of extracted features will be made available after the review process.

Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification With Chest CT.

Chest computed tomography (CT) becomes an effective tool to assist the diagnosis of coronavirus disease-19 (COVID-19). Due to the outbreak of COVID-19 worldwide, using the computed-aided diagnosis technique for COVID-19 classification based on CT images could largely alleviate the burden of clinicians. In this paper, we propose an Adaptive Feature Selection guided Deep Forest (AFS-DF) for COVID-19 classification based on chest CT images. Specifically, we first extract location-specific features from CT images. Then, in order to capture the high-level representation of these features with the relatively small-scale data, we leverage a deep forest model to learn high-level representation of the features. Moreover, we propose a feature selection method based on the trained deep forest model to reduce the redundancy of features, where the feature selection could be adaptively incorporated with the COVID-19 classification model. We evaluated our proposed AFS-DF on COVID-19 dataset with 1495 patients of COVID-19 and 1027 patients of community acquired pneumonia (CAP). The accuracy (ACC), sensitivity (SEN), specificity (SPE), AUC, precision and F1-score achieved by our method are 91.79%, 93.05%, 89.95%, 96.35%, 93.10% and 93.07%, respectively. Experimental results on the COVID-19 dataset suggest that the proposed AFS-DF achieves superior performance in COVID-19 vs. CAP classification, compared with 4 widely used machine learning methods.

Safety and immunogenicity of aerosolised Ad5-nCoV, intramuscular Ad5-nCoV, or inactivated COVID-19 vaccine CoronaVac given as the second booster following three doses of CoronaVac: a multicentre, open-label, phase 4, randomised trial.

BACKGROUND: Aerosolised Ad5-nCoV is the first approved mucosal respiratory COVID-19 vaccine to be used as a booster after the primary immunisation with COVID-19 vaccines. This study aimed to evaluate the safety and immunogenicity of aerosolised Ad5-nCoV, intramuscular Ad5-nCoV, or inactivated COVID-19 vaccine CoronaVac given as the second booster. METHODS: This is an open-label, parallel-controlled, phase 4 randomised trial enrolling healthy adult participants (≥18 years) who had completed a two-dose primary immunisation and a booster immunisation with inactivated COVID-19 vaccines (CoronaVac only) at least 6 months before, in Lianshui and Donghai counties, Jiangsu Province, China. We recruited eligible participants from previous trials in China (NCT04892459, NCT04952727, and NCT05043259) as cohort 1 (with the serum before and after the first booster dose available), and from eligible volunteers in Lianshui and Donghai counties, Jiangsu Province, as cohort 2. Participants were randomly assigned at a ratio of 1:1:1, using a web-based interactive response randomisation system, to receive the fourth dose (second booster) of aerosolised Ad5-nCoV (0·1 mL of 1·0 × 1011 viral particles per mL), intramuscular Ad5-nCoV (0·5 mL of 1·0 × 1011 viral particles per mL), or inactivated COVID-19 vaccine CoronaVac (0·5 mL), respectively. The co-primary outcomes were safety and immunogenicity of geometric mean titres (GMTs) of serum neutralising antibodies against prototype live SARS-CoV-2 virus 28 days after the vaccination, assessed on a per-protocol basis. Non-inferiority or superiority was achieved when the lower limit of the 95% CI of the GMT ratio (heterologous group vs homologous group) exceeded 0·67 or 1·0, respectively. This study was registered with ClinicalTrials.gov, NCT05303584 and is ongoing. FINDINGS: Between April 23 and May 23, 2022, from 367 volunteers screened for eligibility, 356 participants met eligibility criteria and received a dose of aerosolised Ad5-nCoV (n=117), intramuscular Ad5-nCoV (n=120), or CoronaVac (n=119). Within 28 days of booster vaccination, participants in the intramuscular Ad5-nCoV group reported a significantly higher frequency of adverse reactions than those in the aerosolised Ad5-nCoV and intramuscular CoronaVac groups (30% vs 9% and 14%, respectively; p<0·0001). No serious adverse events related to the vaccination were reported. The heterologous boosting with aerosolised Ad5-nCoV triggered a GMT of 672·4 (95% CI 539·7-837·7) and intramuscular Ad5-nCoV triggered a serum neutralising antibody GMT of 582·6 (505·0-672·2) 28 days after the booster dose, both of which were significantly higher than the GMT in the CoronaVac group (58·5 [48·0-71·4]; p<0·0001). INTERPRETATION: A heterologous fourth dose (second booster) with either aerosolised Ad5-nCoV or intramuscular Ad5-nCoV was safe and highly immunogenic in healthy adults who had been immunised with three doses of CoronaVac. FUNDING: National Natural Science Foundation of China, Jiangsu Provincial Science Fund for Distinguished Young Scholars, and Jiangsu Provincial Key Project of Science and Technology Plan.

Structural Attention Graph Neural Network for Diagnosis and Prediction of COVID-19 Severity.

With rapid worldwide spread of Coronavirus Disease 2019 (COVID-19), jointly identifying severe COVID-19 cases from mild ones and predicting the conversion time (from mild to severe) is essential to optimize the workflow and reduce the clinician's workload. In this study, we propose a novel framework for COVID-19 diagnosis, termed as Structural Attention Graph Neural Network (SAGNN), which can combine the multi-source information including features extracted from chest CT, latent lung structural distribution, and non-imaging patient information to conduct diagnosis of COVID-19 severity and predict the conversion time from mild to severe. Specifically, we first construct a graph to incorporate structural information of the lung and adopt graph attention network to iteratively update representations of lung segments. To distinguish different infection degrees of left and right lungs, we further introduce a structural attention mechanism. Finally, we introduce demographic information and develop a multi-task learning framework to jointly perform both tasks of classification and regression. Experiments are conducted on a real dataset with 1687 chest CT scans, which includes 1328 mild cases and 359 severe cases. Experimental results show that our method achieves the best classification (e.g., 86.86% in terms of Area Under Curve) and regression (e.g., 0.58 in terms of Correlation Coefficient) performance, compared with other comparison methods.

Technology-based interventions for health challenges older women face amid COVID-19: a systematic review protocol.

BACKGROUND: Pandemics, such as COVID-19, are dangerous and socially disruptive. Though no one is immune to COVID-19, older persons often bear the brunt of its consequences. This is particularly true for older women, as they often face more pronounced health challenges relative to other segments in society, including complex care needs, insufficient care provisions, mental illness, neglect, and increased domestic abuse. To further compound the situation, because protective measures like lockdowns can result in unintended consequences, many health services older women depend on can become disrupted or discontinued amid pandemics. While technology-based interventions have the potential to provide near-time, location-free, and virtually accessible care, there is a dearth of systematic insights into this mode of care in the literature. To bridge the research gaps, this investigation aims to examine the characteristics and effectiveness of technology-based interventions that could address health challenges older women face amid COVID-19. METHODS: A systematic review of randomized trials reporting on technology-based interventions for older women (≥65 years) during COVID-19 will be conducted. The databases of Web of Science, ScienceDirect, PubMed/MEDLINE, PsycINFO, CINAHL, and Scopus will be searched. Retrieved citations will be screened independently by at least two reviewers against the eligibility criteria. Included studies will be assessed using the Cochrane ROB-2 tool. Data will be extracted independently by the reviewers. Where possible, meta-analyses will be performed on relevant study outcomes and analysed via odds ratios on the dichotomized outcomes. Where applicable, heterogeneity will be measured using the Cochrane Q test, and publication bias will be assessed via funnel plots and Egger's regression test. DISCUSSION: Technology has the potential to transform healthcare for the better. To help society better safeguard vulnerable populations' health and quality of life, this investigation sets out to gauge the state-of-the-art development of technology-based interventions tailored to the health challenges older women face amid COVID-19. In light of the growing prevalence of population ageing and the inevitability of infectious disease outbreaks, greater research efforts are needed to ensure the timely inception and effective implementation of technology-based health solutions for vulnerable populations like older women, amid public health crises like COVID-19 and beyond. SYSTEMATIC REVIEW REGISTRATION: PROSPERO CRD42020194003.

Safety and immunogenicity of heterologous boost immunisation with an orally administered aerosolised Ad5-nCoV after two-dose priming with an inactivated SARS-CoV-2 vaccine in Chinese adults: a randomised, open-label, single-centre trial.

BACKGROUND: Due to waning immunity and protection against infection with SARS-CoV-2, a third dose of a homologous or heterologous COVID-19 vaccine has been proposed by health agencies for individuals who were previously primed with two doses of an inactivated COVID-19 vaccine. METHODS: We did a randomised, open-label, controlled trial to evaluate the safety and immunogenicity of heterologous boost immunisation with an orally administered aerosolised adenovirus type-5 vector-based COVID-19 vaccine (Ad5-nCoV) in Chinese adults (≥18 years old) who had previously received two doses of an inactivated SARS-CoV-2 vaccine-Sinovac CoronaVac. Eligible participants were randomly assigned (1:1:1) to receive a heterologous booster vaccination with a low dose (1·0 × 1011 viral particles per mL; 0·1 mL; low dose group), or a high dose (1·0 × 1011 viral particles per mL; 0·2 mL; high dose group) aerosolised Ad5-nCoV, or a homologous intramuscular vaccination with CoronaVac (0·5 mL). Only laboratory staff were masked to group assignment. The primary endpoint for safety was the incidence of adverse reactions within 14 days after the booster dose. The primary endpoint for immunogenicity was the geometric mean titres (GMTs) of serum neutralising antibodies (NAbs) against live SARS-CoV-2 virus 14 days after the booster dose. This study was registered with ClinicalTrials.gov, NCT05043259. FINDINGS: Between Sept 14 and 16, 2021, 420 participants were enrolled: 140 (33%) participants per group. Adverse reactions were reported by 26 (19%) participants in the low dose group and 33 (24%) in the high dose group within 14 days after the booster vaccination, significantly less than the 54 (39%) participants in the CoronaVac group (p<0·0001). The low dose group had a serum NAb GMT of 744·4 (95% CI 520·1-1065·6) and the high dose group had a GMT of 714·1 (479·4-1063·7) 14 days after booster dose, significantly higher than the GMT in the CoronaVac group (78·5 [60·5-101·7]; p<0·0001). INTERPRETATION: We found that a heterologous booster vaccine with an orally administered aerosolised Ad5-nCoV is safe and highly immunogenic in adults who have previously received two doses of CoronaVac as the primary series vaccination. FUNDING: National Natural Science Foundation of China and Jiangsu Provincial Key Research and Development Program.

Diagnostic Efficacy of CT Examination on Early Detection of Lung Cancer during Pandemic of COVID-19.

BACKGROUND: Since the outbreak of COVID-19 in 2020, routine CT examination was recommended to hospitalized patients at some hospitals and discovered lung cancer patients at an early stage. This study aimed to investigate the detection efficacy of routine CT examination on early diagnosis of lung cancer, especially on pathological characteristics. METHODS: The epidemic of COVID-19 outbreak in January 2020 in China, and routine CT examination was recommended to hospitalized patients in June 2020 and ended in July 2021. Based on the time points, we compared the diagnosis efficacy between three periods: pre-period, peri-period, and the period of routine CT examination. RESULTS: During the period of routine CT examination, more early stages of lung cancer were detected and the tumor size was reduced to 2.14 cm from 3.21 cm at pre-period (p = 0.03). The proportion of lung adenocarcinoma and early stage adenocarcinoma was increased by 12% and 30% in the period of routine CT examination, with referral to the pre-period of CT examination (p < 0.05). A total of 61% of diagnosed patients had the wild type of TP53 gene during the period of routine CT examination, compared to 45% of patients at the pre-period of CT examination (p = 0.001). The median Ki-67 index was 15% among patients diagnosed at the period of routine CT examination and increased to 35% at the pre-period of CT examination (p < 0.001). The period of routine CT examination was associated with a 78% higher probability of detecting an early stage of adenocarcinoma (OR = 1.78, 95%CI 1.03, 3.08) but no significant association was observed for squamous cell carcinoma. From the pre-period to the period of routine CT examination, the proportion of female patients and non-smoking patients increased by 57% and 44%, respectively (p < 0.001). CONCLUSION: Routine CT examination could detect more lung cancer at an early stage, especially for adenocarcinoma, and detect patients with less aggressive features. Further studies were warranted to confirm the findings.

Behaviour in public open spaces: A systematic review of studies with quantitative research methods

Public open spaces are important assets that play a significant role in city lives, based on which a great number of behaviour-based studies are being conducted. These studies often use one or more case studies to observe people's preferences and usage habits and to investigate their influencing factors such as outdoor thermal comfort, environmental conditions, urban configuration, and local settings. Because the subject is complex and falls within the purview of multiple academic disciplines, it is a challenging task to understand the current status and development trends of existing studies. To fill this gap, this article presents a systematic review of quantitative evidence-based behaviour studies in public open spaces. Following the PRISMA method and searching using eight academic search engines, full texts of 116 research articles have been included for this review. The main contributions of this review are that: (1) it proposed a relatively complete system that categorizes people's behaviour in public open spaces;(2) it introduced outdoor subjective influencing procedure including behaviour, feeling and health impacts;(3) the review illustrated the distribution of existing research as well as research trends;and finally (4) the article also timely discussed the influence of the COVID-19 on people's behaviour in public open spaces. The authors consider this article to be useful as it can facilitate further behaviour-based studies in public open spaces. With a robust classification and future trend discussion of factors associated, fellow researchers, urban designers, city managers, and policymakers are easier to integrate and use the knowledge learned.

A Systematic Review of Objective Factors Influencing Behavior in Public Open Spaces.

As a significant part of outdoor built-environment, public open spaces are closely associated with people's daily lives. Studies of outdoor behavior in these spaces can shed light on users' environmental perceptions and contribute to the promotion of physiological and psychological health. Many recent studies are case studies focused where observations, surveys and interviews have been conducted to understand the factors influencing people's behavior on one or few sites or city environments. There have been few reviews related to this topic, and none have been based on the systematic understanding of influencing factors. This paper presents a systematic review of interactions between behavior and the built environment in public open spaces, and highlights the impacts of diverse and objective influencing factors. Followed the rules of PRISMA method (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), 109 papers published in 2000-2021 were selected and reviewed. The distribution of the studied interactions is analyzed, and the impacts of four distinct factors: personal background, location and context, environmental component, and climate stimuli, are extracted, categorized, and specified. Moreover, outdoor health benefits are discussed based on which, crucial factors that require emphasis after the outbreak of COVID-19 are identified. Throughout this paper, behavioral influencing processes, including objective influencing factors, subjective feedback, and the relationships involved, are considered to provide a comprehensive picture. With the robust classification of existing factors, architects, urban designers, policy makers and fellow researches could be easier to get a more comprehensive trend from the past. This paper also provides guidance for future research, especially given that COVID-19 has created huge changes to outdoor needs and customary behavior. Systematic Review Registration: http://www.prisma-statement.org/.

6G and Artificial Intelligence Technologies for Dementia Care: Literature Review and Practical Analysis.

BACKGROUND: The dementia epidemic is progressing fast. As the world's older population keeps skyrocketing, the traditional incompetent, time-consuming, and laborious interventions are becoming increasingly insufficient to address dementia patients' health care needs. This is particularly true amid COVID-19. Instead, efficient, cost-effective, and technology-based strategies, such as sixth-generation communication solutions (6G) and artificial intelligence (AI)-empowered health solutions, might be the key to successfully managing the dementia epidemic until a cure becomes available. However, while 6G and AI technologies hold great promise, no research has examined how 6G and AI applications can effectively and efficiently address dementia patients' health care needs and improve their quality of life. OBJECTIVE: This study aims to investigate ways in which 6G and AI technologies could elevate dementia care to address this study gap. METHODS: A literature review was conducted in databases such as PubMed, Scopus, and PsycINFO. The search focused on three themes: dementia, 6G, and AI technologies. The initial search was conducted on April 25, 2021, complemented by relevant articles identified via a follow-up search on November 11, 2021, and Google Scholar alerts. RESULTS: The findings of the study were analyzed in terms of the interplay between people with dementia's unique health challenges and the promising capabilities of health technologies, with in-depth and comprehensive analyses of advanced technology-based solutions that could address key dementia care needs, ranging from impairments in memory (eg, Egocentric Live 4D Perception), speech (eg, Project Relate), motor (eg, Avatar Robot Café), cognitive (eg, Affectiva), to social interactions (eg, social robots). CONCLUSIONS: To live is to grow old. Yet dementia is neither a proper way to live nor a natural aging process. By identifying advanced health solutions powered by 6G and AI opportunities, our study sheds light on the imperative of leveraging the potential of advanced technologies to elevate dementia patients' will to live, enrich their daily activities, and help them engage in societies across shapes and forms.

NLRP3 Inflammasome: Mechanism of Action, Role, and Therapeutics in Liver Diseases (preprint)

Liver inflammation is a universal characteristic of chronic liver diseases. NLRP3 is an intracellular sensor that recognizes various endogenous danger signals and environmental irritants, contributing to the formation and activation of the NLRP3 inflammasome. NLRP3 inflammasome is closely related to the progression of various liver diseases and is strongly associated with replicating COVID-19, which is still spreading globally. The assembly and activation of NLRP3 inflammasome in the liver diseases aggravate inflammation and subsequent fibrosis, and this effect is abolished by genetic or pharmacologic deletion of NLRP3 inflammasome. Here, we summarized the latest advances in the critical regulatory role of NLRP3 inflammasome in a variety of liver diseases, including COVID-19 induced liver diseases, NAFLD, ALD, and ischemia-reperfusion (I/R) injury. Additionally, we also discuss small-molecule inhibitors identifying the NLRP3 inflammasome signaling are novel therapeutic targets in treating liver diseases. Our review provides novel insights into the underlying mechanisms of NLRP3 inflammasome in liver diseases and may offer a potential therapeutic strategy for treating liver diseases by targeting NLRP3 inflammasome.

Cross-Site Severity Assessment of COVID-19 From CT Images via Domain Adaptation.

Early and accurate severity assessment of Coronavirus disease 2019 (COVID-19) based on computed tomography (CT) images offers a great help to the estimation of intensive care unit event and the clinical decision of treatment planning. To augment the labeled data and improve the generalization ability of the classification model, it is necessary to aggregate data from multiple sites. This task faces several challenges including class imbalance between mild and severe infections, domain distribution discrepancy between sites, and presence of heterogeneous features. In this paper, we propose a novel domain adaptation (DA) method with two components to address these problems. The first component is a stochastic class-balanced boosting sampling strategy that overcomes the imbalanced learning problem and improves the classification performance on poorly-predicted classes. The second component is a representation learning that guarantees three properties: 1) domain-transferability by prototype triplet loss, 2) discriminant by conditional maximum mean discrepancy loss, and 3) completeness by multi-view reconstruction loss. Particularly, we propose a domain translator and align the heterogeneous data to the estimated class prototypes (i.e., class centers) in a hyper-sphere manifold. Experiments on cross-site severity assessment of COVID-19 from CT images show that the proposed method can effectively tackle the imbalanced learning problem and outperform recent DA approaches.

GACDN: generative adversarial feature completion and diagnosis network for COVID-19.

BACKGROUND: The outbreak of coronavirus disease 2019 (COVID-19) causes tens of million infection world-wide. Many machine learning methods have been proposed for the computer-aided diagnosis between COVID-19 and community-acquired pneumonia (CAP) from chest computed tomography (CT) images. Most of these methods utilized the location-specific handcrafted features based on the segmentation results to improve the diagnose performance. However, the prerequisite segmentation step is time-consuming and needs the intervention by lots of expert radiologists, which cannot be achieved in the areas with limited medical resources. METHODS: We propose a generative adversarial feature completion and diagnosis network (GACDN) that simultaneously generates handcrafted features by radiomic counterparts and makes accurate diagnoses based on both original and generated features. Specifically, we first calculate the radiomic features from the CT images. Then, in order to fast obtain the location-specific handcrafted features, we use the proposed GACDN to generate them by its corresponding radiomic features. Finally, we use both radiomic features and location-specific handcrafted features for COVID-19 diagnosis. RESULTS: For the performance of our generated location-specific handcrafted features, the results of four basic classifiers show that it has an average of 3.21% increase in diagnoses accuracy. Besides, the experimental results on COVID-19 dataset show that our proposed method achieved superior performance in COVID-19 vs. community acquired pneumonia (CAP) classification compared with the state-of-the-art methods. CONCLUSIONS: The proposed method significantly improves the diagnoses accuracy of COVID-19 vs. CAP in the condition of incomplete location-specific handcrafted features. Besides, it is also applicable in some regions lacking of expert radiologists and high-performance computing resources.

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19.

The pandemic of coronavirus disease 2019 (COVID-19) is spreading all over the world. Medical imaging such as X-ray and computed tomography (CT) plays an essential role in the global fight against COVID-19, whereas the recently emerging artificial intelligence (AI) technologies further strengthen the power of the imaging tools and help medical specialists. We hereby review the rapid responses in the community of medical imaging (empowered by AI) toward COVID-19. For example, AI-empowered image acquisition can significantly help automate the scanning procedure and also reshape the workflow with minimal contact to patients, providing the best protection to the imaging technicians. Also, AI can improve work efficiency by accurate delineation of infections in X-ray and CT images, facilitating subsequent quantification. Moreover, the computer-aided platforms help radiologists make clinical decisions, i.e., for disease diagnosis, tracking, and prognosis. In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up. We particularly focus on the integration of AI with X-ray and CT, both of which are widely used in the frontline hospitals, in order to depict the latest progress of medical imaging and radiology fighting against COVID-19.

Mental health solutions for domestic violence victims amid COVID-19: a review of the literature.

BACKGROUND: Due to COVID-19, domestic violence victims face a range of mental health challenges, possibly resulting in substantial human and economic consequences. However, there is a lack of mental health interventions tailored to domestic violence victims and in the context of COVID-19. In this study, we aim to identify interventions that can improve domestic violence victims' mental health amid the COVID-19 pandemic to address the research gap. MAIN TEXT: Drawing insights from established COVID-19 review frameworks and a comprehensive review of PubMed literature, we obtained information on interventions that can address domestic violence victims' mental health challenges amid COVID-19. We identified practical and timely solutions that can be utilized to address mental health challenges domestic violence victims face amid COVID-19, mainly focusing on (1) decreasing victims' exposure to the abuser and (2) increasing victims' access to mental health services. CONCLUSION: Domestic violence is a public health crisis that affects all demographics and could result in significant morbidity and mortality. In addition to emphasizing mental health challenges faced by domestic violence victims, multidisciplinary interventions are identified that could provide timely and practical solutions to domestic violence victims amid the pandemic, which range from tailored shelter home strategies, education programs, escape plans, laws and regulations, as well as more technology-based mental health solutions. There is a significant need for more multipronged and multidisciplinary strategies to address domestic violence amid and beyond the pandemic, particularly interventions that could capitalize on the ubiquity and cost-effectiveness of technology-based solutions.

Assessing inequality, irregularity, and severity regarding road traffic safety during COVID-19.

COVID-19 has affected every sector of our society, among which human mobility is taking a dramatic change due to quarantine and social distancing. We investigate the impact of the pandemic and subsequent mobility changes on road traffic safety. Using traffic accident data from the city of Los Angeles and New York City, we find that the impact is not merely a blunt reduction in traffic and accidents; rather, (1) the proportion of accidents unexpectedly increases for "Hispanic" and "Male" groups; (2) the "hot spots" of accidents have shifted in both time and space and are likely moved from higher-income areas (e.g., Hollywood and Lower Manhattan) to lower-income areas (e.g., southern LA and southern Brooklyn); (3) the severity level of accidents decreases with the number of accidents regardless of transportation modes. Understanding those variations of traffic accidents not only sheds a light on the heterogeneous impact of COVID-19 across demographic and geographic factors, but also helps policymakers and planners design more effective safety policies and interventions during critical conditions such as the pandemic.

What medical waste management system may cope With COVID-19 pandemic: Lessons from Wuhan.

The global pandemic caused by the 2019 coronavirus (COVID-19) has led to a dramatic increase in medical waste worldwide. This tremendous increase in medical waste is an important transmission medium for the virus and thus poses new and serious challenges to urban medical waste management. This study investigates the response of medical waste management to the COVID-19 pandemic and subsequent changes in Wuhan City based on the most detailed data available, including waste generation, storage, transportation, and disposal. The results show that despite a 5-fold increase in the demand for daily medical waste disposal in the peak period, the quick responses in the storage, transportation, and disposal sectors during the pandemic ensured that all medical waste was disposed of within 24 hours of generation. Furthermore, this paper discusses medical waste management during future emergencies in Wuhan. The ability of the medical waste management system in Wuhan to successfully cope with the rapid increase in medical waste caused by major public health emergencies has important implications for other cities suffering from the pandemic and demonstrates the need to establish resilient medical emergency systems in urban areas.

Computing infection distributions and longitudinal evolution patterns in lung CT images.

BACKGROUND: Spatial and temporal lung infection distributions of coronavirus disease 2019 (COVID-19) and their changes could reveal important patterns to better understand the disease and its time course. This paper presents a pipeline to analyze statistically these patterns by automatically segmenting the infection regions and registering them onto a common template. METHODS: A VB-Net is designed to automatically segment infection regions in CT images. After training and validating the model, we segmented all the CT images in the study. The segmentation results are then warped onto a pre-defined template CT image using deformable registration based on lung fields. Then, the spatial distributions of infection regions and those during the course of the disease are calculated at the voxel level. Visualization and quantitative comparison can be performed between different groups. We compared the distribution maps between COVID-19 and community acquired pneumonia (CAP), between severe and critical COVID-19, and across the time course of the disease. RESULTS: For the performance of infection segmentation, comparing the segmentation results with manually annotated ground-truth, the average Dice is 91.6% ± 10.0%, which is close to the inter-rater difference between two radiologists (the Dice is 96.1% ± 3.5%). The distribution map of infection regions shows that high probability regions are in the peripheral subpleural (up to 35.1% in probability). COVID-19 GGO lesions are more widely spread than consolidations, and the latter are located more peripherally. Onset images of severe COVID-19 (inpatients) show similar lesion distributions but with smaller areas of significant difference in the right lower lobe compared to critical COVID-19 (intensive care unit patients). About the disease course, critical COVID-19 patients showed four subsequent patterns (progression, absorption, enlargement, and further absorption) in our collected dataset, with remarkable concurrent HU patterns for GGO and consolidations. CONCLUSIONS: By segmenting the infection regions with a VB-Net and registering all the CT images and the segmentation results onto a template, spatial distribution patterns of infections can be computed automatically. The algorithm provides an effective tool to visualize and quantify the spatial patterns of lung infection diseases and their changes during the disease course. Our results demonstrate different patterns between COVID-19 and CAP, between severe and critical COVID-19, as well as four subsequent disease course patterns of the severe COVID-19 patients studied, with remarkable concurrent HU patterns for GGO and consolidations.