Corpus overview


MeSH Disease

Human Phenotype


    displaying 1 - 10 records in total 34
    records per page

    Dual Attention Multiple Instance Learning with Unsupervised Complementary Loss for COVID-19 Screening

    Authors: Philip Chikontwe; Miguel Luna; Myeongkyun Kang; Kyung Soo Hong; June Hong Ahn; Sang Hyun Park; Florian Krammer

    doi:10.1101/2020.09.14.20194654 Date: 2020-09-18 Source: medRxiv

    Chest computed tomography (CT) based analysis and diagnosis of the Coronavirus Disease MESHD 2019 (COVID-19) plays a key role in combating the outbreak of the pandemic that has rapidly spread worldwide. To date, the disease has infected more than 18 million people with over 690k deaths reported. Reverse transcription polymerase chain reaction (RT-PCR) is the current gold standard for clinical diagnosis but may produce false positives; thus, chest CT based diagnosis is considered more viable. However, accurate screening is challenging due to difficulty in annotation efforts of infected areas, curation of large datasets, and the slight discrepancies between COVID-19 and other viral pneumonia MESHD pneumonia HP. In this study, we propose an attention-based end-to-end weakly supervised framework for the rapid diagnosis of COVID-19 and bacterial pneumonia MESHD pneumonia HP based on multiple instance learning (MIL). We further incorporate unsupervised contrastive learning for improved accuracy with attention applied both in spatial and latent contexts, herein we propose Dual Attention Contrastive based MIL (DA-CMIL). DA-CMIL takes as input a several patient CT slices (considered as a bag of instances) and outputs a single label. Attention based pooling is applied to implicitly select key slices in latent space, and spatial attention learns slice spatial context for interpretable diagnosis. A contrastive loss is applied at the instance level to encode similarity in features from the same patient against pooled patient features. Empirical results show our algorithm achieves an overall accuracy of 98.6% and an AUC of 98.4%. Moreover, ablation studies show the benefit of contrastive learning with MIL.

    Deep-learning convolutional neural networks with transfer learning accurately classify COVID19 lung infection MESHD on portable chest radiographs

    Authors: Shreeja Kikkisetti; Jocelyn Zhu; Beiyi Shen; Haifang Li; Tim Duong; Peng Wang; Xu Zhang; Kangli Cui; Tingting Tao; Zhongyu Li; Wenwen Chen; Yongtang Zheng; Jianhua Qin; Zhiqiang Ku; Zhiqiang An; Birte Kalveram; Alexander N Freiberg; Vineet D Menachery; Xuping Xie; Kenneth S Plante; Scott C Weaver; Pei-Yong Shi; Pieter S. Hiemstra; Bruce A. Ponder; Mika J Makela; Kristiina Malmstrom; Robert C. Rintoul; Paul A. Reyfman; Fabian J. Theis; Corry-A Brandsma; Ian Adcock; Wim Timens; Cheng J. Xu; Maarten van den Berge; Roland F. Schwarz; Gerard H. Koppelman; Martijn C. Nawijn; Alen Faiz

    doi:10.1101/2020.09.02.20186759 Date: 2020-09-02 Source: medRxiv

    Portable chest x-ray (pCXR) has become an indispensable tool in the management of Coronavirus Disease MESHD 2019 (COVID-19) lung infection MESHD. This study employed deep-learning convolutional neural networks to classify COVID-19 lung infections on pCXR from normal and related lung infections MESHD to potentially enable more timely and accurate diagnosis. This retrospect study employed deep-learning convolutional neural network (CNN) with transfer learning to classify based on pCXRs COVID-19 pneumonia HP pneumonia MESHD (N=455) on pCXR from normal (N=532), bacterial pneumonia MESHD pneumonia HP (N=492), and non-COVID viral pneumonia MESHD pneumonia HP (N=552). The data was split into 75% training and 25% testing. A five-fold cross-validation was used. Performance SERO was evaluated using receiver-operating curve analysis. Comparison was made with CNN operated on the whole pCXR and segmented lungs. CNN accurately classified COVID-19 pCXR from those of normal, bacterial pneumonia MESHD pneumonia HP, and non-COVID-19 viral pneumonia MESHD pneumonia HP patients in a multiclass model. The overall sensitivity SERO, specificity, accuracy, and AUC were 0.79, 0.93, and 0.79, 0.85 respectively (whole pCXR), and were 0.91, 0.93, 0.88, and 0.89 (CXR of segmented lung). The performance SERO was generally better using segmented lungs. Heatmaps showed that CNN accurately localized areas of hazy appearance, ground glass opacity and/or consolidation on the pCXR. Deep-learning convolutional neural network with transfer learning accurately classifies COVID-19 on portable chest x-ray against normal, bacterial pneumonia MESHD pneumonia HP or non-COVID viral pneumonia MESHD pneumonia HP. This approach has the potential to help radiologists and frontline physicians by providing more timely and accurate diagnosis.

    Coronavirus Disease MESHD 2019 Induced Inflammatory Response are Associated with Changes in Lipid Profiles

    Authors: Chuanwei Li; Wen Zhang; Chunmei Xu; Hu Tan; Guoqiang Cao; Li Li; Qidi Sun; Gengze Wu; Mingdong Hu; Shuang Wu; Qi Li; Guansong Wang; Xiaohua Zhang; Chunyu Zeng

    doi:10.21203/ Date: 2020-08-24 Source: ResearchSquare

    Background: Previous studies have found some evidence of association between changes in lipids and lipoprotein and viral pneumonia MESHD pneumonia HP. No data are available about the effect of coronavirus disease MESHD 2019 (Covid-19) on lipids. The aim of this study was to investigate the relationships between lipid profiles and inflammation MESHD markers among patients with Covid-19. Methods: In this retrospective analysis, Covid-19 patients in Jin-yin-tan Hospital and healthy individuals from Daping Hospital were enrolled. The clinical and biochemical characteristics of Covid-19 patients and healthy controls were compared. We correlated lipid parameters to disease severity and inflammatory markers. The severity of Covid-19 for all patients were stipulated according to the diagnostic and treatment guideline for Covid-19 issued by Chinese National Health Committee (the 7th edition).Results: A total of 242 Covid-19 patients and 242 sex- age TRANS matched controls were enrolled. Compared with controls, Covid-19 patients had lower lymphocyte counts as well as total cholesterol (TC), high density lipoprotein (HDL-c), low density lipoprotein cholesterol (LDL-c), non-high density lipoprotein cholesterol (non-HDL-c) and apoA-I levels on admission. Whereas apolipoprotein B (apoB) and apoB/apoA-I ratio were slightly higher in patients with Covid-19. There was no difference in lipid levels between the moderate and severe groups. The total lymphocytes were weakly positively associated with TC, LDL-c and apoA-I. Conclusion: Patients with Covid-19 are associated with decreased lipid and lipoprotein levels. Covid-19 infection MESHD induced inflammation MESHD response and cytokine storm were associated with a shift of lipids, lipoproteins toward a more atherogenic lipid profile.

    Self-Reported Taste and Smell Disorders MESHD in Patients with COVID-19: Distinct Features in China

    Authors: Jia Song; Yi-Ke Deng; Hai Wang; Zhi-Chao Wang; Bo Liao; Jin Ma; Chao He; Li Pan; Yang Liu; Isam Alobid; De-Yun Wang; Ming Zeng; Joaquim Mullol; Zheng Liu

    doi:10.21203/ Date: 2020-08-03 Source: ResearchSquare

    Background: Last December 2019, a cluster of viral pneumonia MESHD pneumonia HP cases identified as coronavirus disease MESHD 2019 (COVID-19), was reported in Wuhan, China. We aimed to explore the frequencies of nasal symptoms in patients with COVID-19, including loss of smell and taste, as well as their presentation as the first symptom of the disease and their association with the severity of COVID-19.Methods: In this retrospective study, 1,206 laboratory-confirmed COVID-19 patients were included and followed-up by telephone call one month after discharged from Tongji Hospital, Wuhan. Demographic data, laboratory values, comorbidities, symptoms, and numerical rating scale scores (0-10) of nasal symptoms were extracted from the hospital medical records, and confirmed or reevaluated by the telephone follow-up. Results: From COVID-19 patients (N = 1,172) completing follow-up, 199 (17%) subjects had severe COVID-19 and 342 (29.2%) reported nasal symptoms. The most common nasal symptom was loss of taste (20.6%, median score = 6), while 11.4% had loss of smell (median score = 5). The incidence of nasal symptom including loss of smell and loss of taste as the first onset symptom TRANS was <1% in COVID-19 patients. Loss of smell or taste scores showed no correlation with the scores of other nasal symptoms. Loss of taste scores, but not loss of smell scores, were significantly increased in severe vs. non-severe COVID-19 patients. Interleukin (IL)-6 and lactose dehydrogenase (LDH) serum SERO levels positively correlated with loss of taste scores. About 80% of COVID-19 patients recovered from smell and taste dysfunction MESHD in 2 weeks.Conclusions: In the Wuhan COVID-19 cohort, only 1 out of 10 hospital admitted patients had loss of smell while 1 out 5 reported loss of taste which was associated to severity of COVID-19. Most patients recovered smell and taste dysfunctions MESHD in 2 weeks.

    IgG antibody SERO seroconversion and the clinical progression of COVID-19 pneumonia HP pneumonia MESHD: A retrospective, cohort study

    Authors: Kazuyoshi Kurashima; Naho Kagiyama; Takashi Ishiguro; Yotaro Takaku; Hiromi Nakajima; Shun Shibata; Yuma Matsui; Kenji Takano; Taisuke Isono; Takashi Nishida; Eriko Kawate; Chiaki Hosoda; Yoichi Kobayashi; Noboru Takayanagi; Tsutomu Yanagisawa

    doi:10.1101/2020.07.16.20154088 Date: 2020-07-17 Source: medRxiv

    Background: Coronavirus Disease MESHD 2019 (COVID-19) causes severe acute respiratory failure HP respiratory failure MESHD. Antibody SERO-dependent enhancement (ADE) is known as the mechanism for severe forms of other coronavirus diseases MESHD. The clinical progression of COVID-19 before and after IgG antibody SERO seroconversion was investigated. Methods: Fifty-three patients with reverse transcriptase PCR (RT-PCT)-confirmed COVID-19 viral pneumonia MESHD pneumonia HP with or without respiratory failure HP respiratory failure MESHD were retrospectively investigated. The timing of the first IgG antibody SERO against SARS-CoV-2-positive date, as well as changes of C-reactive protein (CRP) as an inflammatory marker and blood SERO lymphocyte numbers, was assessed using serial preserved blood SERO samples. Findings: Ten patients recovered without oxygen therapy (mild/moderate group), 32 patients had hypoxemia HP hypoxemia MESHD and recovered with antiviral drugs (severe/non-ICU group), and 11 patients had severe respiratory failure HP respiratory failure MESHD and were treated in the ICU (6 of them died; critical/ICU group). The first IgG-positive date (day 0) was observed from 5 to 18 days from the onset of disease. At day 0, a CRP peak was observed in the severe and critical groups, whereas there was no synchronized CRP peak on day 0 in the mild/moderate group. In the severe/non-ICU group, the blood SERO lymphocyte number increased (P=0.0007) and CRP decreased (P=0.0007) after day 0, whereas CRP did not decrease and the blood SERO lymphocyte number further decreased (P=0.0370) in the critical/ICU group. Interpretation: The respiratory failure HP respiratory failure MESHD due to COVID-19 viral pneumonia MESHD pneumonia HP observed in week 2 may be related to an antibody SERO-related mechanism rather than uncontrolled viral replication. In the critical form of COVID-19, inflammation MESHD was sustained after IgG seroconversion.

    SARS-CoV-2 infection MESHD of primary human lung epithelium for COVID-19 modeling and drug discovery MESHD

    Authors: Apoorva Mulay; Bindu Konda; Gustavo Garcia Jr.; Changfu Yao; Stephen Beil; Chandani Sen; Arunima Purkayastha; Jay Kolls; Derek Pociask; Patrizia Pessina; Carolina Garcia-de-Alba; Carla Kim; Brigitte Gomperts; Vaithilingaraja Arumugaswami; Barry Stripp

    doi:10.1101/2020.06.29.174623 Date: 2020-06-29 Source: bioRxiv

    Coronavirus disease 2019 (COVID-19) is the latest respiratory pandemic resulting from zoonotic transmission TRANS of severe acute respiratory syndrome MESHD-related coronavirus 2 (SARS-CoV-2). Severe symptoms include viral pneumonia MESHD pneumonia HP secondary to infection MESHD and inflammation MESHD of the lower respiratory tract, in some cases causing death MESHD. We developed primary human lung epithelial infection MESHD models to understand responses of proximal and distal lung epithelium to SARS-CoV-2 infection MESHD. Differentiated air-liquid interface cultures of proximal airway epithelium and 3D organoid cultures of alveolar MESHD epithelium were readily infected by SARS-CoV-2 leading to an epithelial cell-autonomous proinflammatory response. We validated the efficacy of selected candidate COVID-19 drugs confirming that Remdesivir strongly suppressed viral infection MESHD/replication. We provide a relevant platform for studying COVID-19 pathobiology and for rapid drug screening against SARS-CoV-2 and future emergent respiratory pathogens. One Sentence SummaryA novel infection model of the adult TRANS human lung epithelium serves as a platform for COVID-19 studies and drug discovery.

    Coronavirus Disease MESHD 2019 (COVID-19) in Italy: Double reading of chest CT examination

    Authors: Reginelli Alfonso; Grassi Roberto; Feragalli Beatrice; Belfiore Maria Paola; Montanelli Alessandro; Patelli Gianluigi; La Porta Michelearcangelo; Urraro Fabrizio; Roberta Fusco; Granata Vincenza; Petrillo Antonella; Giacobbe Giuliana; Russo Gaetano Maria; Sacco Palmino; Grassi Roberta; Cappabianca Salvatore

    doi:10.21203/ Date: 2020-06-19 Source: ResearchSquare

    OBJECTIVETo assess the performance SERO of the second reading of chest Compute Tomography (CT) examinations by expert radiologists in patients with discordance between the reverse transcription real-time fluorescence polymerase chain reaction (RT-PCR) test for COVID-19 viral pneumonia MESHD pneumonia HP and the first CT report.MATERIALS AND METHODS.Three hundred seventy-heigth patients were included in this retrospective study (121 women and 257 men; 71 years of median age TRANS - range, 29–93 years) subjected to RT-PCR test for suspicious COVID-19 infection MESHD. All patients were subjected to CT examination in order to evaluate the pulmonary disease MESHD involvement by COVID-19. CT images were reviewed first by two radiologists who identified COVID-19 typical CT patterns and then reanalyzed by anoter two radiologists using a CT structured report for COVID-19 diagnosis.RESULTS.The median temporal window between RT-PCRs execution and CT scan was 0 days with a range of [-9, 11] days. RT-PCR test was resulted positive in 328/378 (86.8%). Discordance between RT-PCR and CT findings for viral pneumonia MESHD pneumonia HP was revealed in 60 cases. The second reading changed the CT diagnosis in 16/60 (26.7%) cases contributing to increase the concordance with the RT-PCR. Among these 60 cases, 8 were false negative with positive RT-PCR, and 36 were false positive with negative RT-PCR. Sensitivity SERO, specificity, positive predictive value SERO and negative predictive value SERO of CT were respectively of 97.3%, 53.8%, 89.0%, and 88.4%.CONCLUSION.Double reading of CT could increase the diagnostic confidence of radiological interpretation in COVID-19 patients. Using expert second readers could reduce the rate of discrepant cases between RT-PCR results and CT diagnosis for COVID-19 viral pneumonia MESHD pneumonia HP.

    COVID-CXNet: Detecting COVID-19 in Frontal Chest X-ray Images using Deep Learning

    Authors: Arman Haghanifar; Mahdiyar Molahasani Majdabadi; Younhee Choi; S. Deivalakshmi; Seokbum Ko

    id:2006.13807v2 Date: 2020-06-16 Source: arXiv

    One of the primary clinical observations for screening the infectious by the novel coronavirus is capturing a chest x-ray image. In most of the patients, a chest x-ray contains abnormalities, such as consolidation, which are the results of COVID-19 viral pneumonia MESHD pneumonia HP. In this study, research is conducted on efficiently detecting imaging features of this type of pneumonia HP pneumonia MESHD using deep convolutional neural networks in a large dataset. It is demonstrated that simple models, alongside the majority of pretrained networks in the literature, focus on irrelevant features for decision-making. In this paper, numerous chest x-ray images from various sources are collected, and the largest publicly accessible dataset is prepared. Finally, using the transfer learning paradigm, the well-known CheXNet model is utilized for developing COVID-CXNet. This powerful model is capable of detecting the novel coronavirus pneumonia MESHD pneumonia HP based on relevant and meaningful features with precise localization. COVID-CXNet is a step towards a fully automated and robust COVID-19 detection system.

    Machine learning-based CT radiomics model Distinguishes COVID-19 from other viral pneumonia HP pneumonia MESHD

    Authors: Hui Juan Chen; Yang Chen; Li Yuan; Fei Wang; Li Mao; Xiuli Li; Qinlei Cai; Jie Qiu; Jie Tian; Feng Chen

    doi:10.21203/ Date: 2020-05-29 Source: ResearchSquare

    Purpose To develop a machine learning-based CT radiomics model is critical for the accurate diagnosis of the rapid spread Coronavirus disease MESHD 2019 (COVID-19).Methods In this retrospective study, a machine learning-based CT radiomics model was developed to extract features from chest CT exams for the detection of COVID-19. Other viral-pneumonia MESHD pneumonia HP CT exams of the corresponding period were also included. The radiomics features extracted from the region of interest (ROI), the radiological features evaluated by the radiologists, the quantity features calculated by the AI segmentation and evaluation, and the clinical parameters including clinical symptoms, epidemiology history and biochemical results were enrolled in this study. The SVM model was built and the performance SERO on the testing cohort was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity SERO and specificity. Results For the SVM model that built on the radiomics features only, it reached an AUC of 0.688(95% CI 0.496 to 0.881) on the testing cohort. After the radiological features were enrolled, the AUC achieved 0.696(95% CI 0.501 to 0.892), then the AUC reached 0.753(95% CI 0.596 to 0.910) after the quantity features were included. Our final model employed all the features, reached the per-exam sensitivity SERO and specificity for differentiating COVID-19 was 29 of 38 (0.763, 95% CI: 0.598 to 0.886]) and 12 of 13 (0.923, 95% CI: 0.640 to 0.998]), respectively, with an AUC of 0.968(95% CI 0.911 to 1.000). Conclusion The machine learning-based CT radiomics models may accurately detect COVID-19 and differentiate it from other viral pneumonia HP pneumonia MESHD.

    Noninvasive respiratory support in acute hypoxemicrespiratory failure MESHD associated with COVID-19 and other viralinfections

    Authors: Claudia Crimi; Alberto Noto; Andrea Cortegiani; Pietro Impellizzeri; Mark W Elliott; Nicolino Ambrosino; Cesare Gregoretti

    doi:10.1101/2020.05.24.20111013 Date: 2020-05-26 Source: medRxiv

    Introduction: Noninvasive respiratory support (NRS) such as noninvasive ventilation (NIV) and high flow nasal therapy (HFNT) have been used in the treatment of acute hypoxemic respiratory failure MESHD respiratory failure HP ( AHRF MESHD) related to the coronavirus disease MESHD (COVID-19) and other viral infections MESHD. However, there is a lack of consensus in favor of or against NRS use due to the risks of worsening hypoxemia HP hypoxemia MESHD, intubation delay, and aerosols environmental contamination associated with the use of these tools. We aimed to summarize the evidence on the use of NRS in adult TRANS patients with COVID-19 and other viral pneumonia MESHD pneumonia HP (i.e. H1N1, SARS, MERS) and AHRF MESHD. We also searched for studies evaluating the risk of aerosolization/contamination with these tools. Evidence Acquisition: We searched MEDLINE, PubMed EMBASE and two major preprint servers (biorXiv and medRxiv) from inception to April 14, 2020, for studies on the use of respiratory support in AHRF MESHD and viral pneumonia MESHD pneumonia HP. Evidence Synthesis: The search identified 4086 records and we found only one randomized controlled trial out of 58 studies included, with great variabilities in support utilization and failure rates. Fifteen studies explored the issue of aerosolization/contamination showing a high risk of airborne transmission TRANS via droplets generation during the use of these modalities Conclusions: Use of NRS and treatment failure in the context of COVID-19 and viral infection associated- AHRF MESHD, varied widely. Dispersion of exhaled air is different depending on the type of respiratory therapies and interfaces. Data from randomized controlled trials are lacking.

The ZB MED preprint Viewer preVIEW includes all COVID-19 related preprints from medRxiv and bioRxiv, from ChemRxiv, from ResearchSquare, from arXiv and from and is updated on a daily basis (7am CET/CEST).
The web page can also be accessed via API.



MeSH Disease
Human Phenotype

Export subcorpus as...

This service is developed in the project nfdi4health task force covid-19 which is a part of nfdi4health.

nfdi4health is one of the funded consortia of the National Research Data Infrastructure programme of the DFG.