Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 23
Filter
1.
Front Immunol ; 13: 770982, 2022.
Article in English | MEDLINE | ID: covidwho-1775662

ABSTRACT

The coronavirus disease 2019 (COVID-19) pandemic is caused by a novel coronavirus called severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The spike protein (S) of SARS-CoV-2 is a major target for diagnosis and vaccine development because of its essential role in viral infection and host immunity. Currently, time-dependent responses of humoral immune system against various S protein epitopes are poorly understood. In this study, enzyme-linked immunosorbent assay (ELISA), peptide microarray, and antibody binding epitope mapping (AbMap) techniques were used to systematically analyze the dynamic changes of humoral immune responses against the S protein in a small cohort of moderate COVID-19 patients who were hospitalized for approximately two months after symptom onset. Recombinant truncated S proteins, target S peptides, and random peptides were used as antigens in the analyses. The assays demonstrated the dynamic IgM- and IgG recognition and reactivity against various S protein epitopes with patient-dependent patterns. Comprehensive analysis of epitope distribution along the spike gene sequence and spatial structure of the homotrimer S protein demonstrated that most IgM- and IgG-reactive peptides were clustered into similar genomic regions and were located at accessible domains. Seven S peptides were generally recognized by IgG antibodies derived from serum samples of all COVID-19 patients. The dynamic immune recognition signals from these seven S peptides were comparable to those of the entire S protein or truncated S1 protein. This suggested that the humoral immune system recognized few conserved S protein epitopes in most COVID-19 patients during the entire duration of humoral immune response after symptom onset. Furthermore, in this cohort, individual patients demonstrated stable immune recognition to certain S protein epitopes throughout their hospitalization period. Therefore, the dynamic characteristics of humoral immune responses to S protein have provided valuable information for accurate diagnosis and immunotherapy of COVID-19 patients.


Subject(s)
COVID-19 , Antibodies, Viral , Epitopes , Humans , Immunity, Humoral , Immunoglobulin G , Immunoglobulin M , Peptides , SARS-CoV-2 , Spike Glycoprotein, Coronavirus
2.
Thorax ; 2022 Mar 25.
Article in English | MEDLINE | ID: covidwho-1765137

ABSTRACT

INTRODUCTION: Persisting respiratory symptoms in COVID-19 survivors may be related to development of pulmonary fibrosis. We assessed the proportion of chest CT scans and pulmonary function tests consistent with parenchymal lung disease in the follow-up of people hospitalised with COVID-19 and viral pneumonitis. METHODS: Systematic review and random effects meta-analysis of proportions using studies of adults hospitalised with SARS-CoV-2, SARS-CoV, MERS-CoV or influenza pneumonia and followed up within 12 months. Searches performed in MEDLINE and Embase. Primary outcomes were proportion of radiological sequelae on CT scans; restrictive impairment; impaired gas transfer. Heterogeneity was explored in meta-regression. RESULTS: Ninety-five studies (98.9% observational) were included in qualitative synthesis, 70 were suitable for meta-analysis including 60 SARS-CoV-2 studies with a median follow-up of 3 months. In SARS-CoV-2, the overall estimated proportion of inflammatory sequelae was 50% during follow-up (0.50; 95% CI 0.41 to 0.58; I2=95%), fibrotic sequelae were estimated in 29% (0.29; 95% CI 0.22 to 0.37; I2=94.1%). Follow-up time was significantly associated with estimates of inflammatory sequelae (-0.036; 95% CI -0.068 to -0.004; p=0.029), associations with fibrotic sequelae did not reach significance (-0.021; 95% CI -0.051 to 0.009; p=0.176). Impaired gas transfer was estimated at 38% of lung function tests (0.38 95% CI 0.32 to 0.44; I2=92.1%), which was greater than restrictive impairment (0.17; 95% CI 0.13 to 0.23; I2=92.5%), neither were associated with follow-up time (p=0.207; p=0.864). DISCUSSION: Sequelae consistent with parenchymal lung disease were observed following COVID-19 and other viral pneumonitis. Estimates should be interpreted with caution due to high heterogeneity, differences in study casemix and initial severity. PROSPERO REGISTRATION NUMBER: CRD42020183139.

3.
J Clin Hypertens (Greenwich) ; 24(4): 521-522, 2022 Apr.
Article in English | MEDLINE | ID: covidwho-1752589
4.
EuropePMC; 2021.
Preprint in English | EuropePMC | ID: ppcovidwho-324604

ABSTRACT

Artificial Intelligence (AI) has made leapfrogs in development across all the industrial sectors especially when deep learning has been introduced. Deep learning helps to learn the behaviour of an entity through methods of recognising and interpreting patterns. Despite its limitless potential, the mystery is how deep learning algorithms make a decision in the first place. Explainable AI (XAI) is the key to unlocking AI and the black-box for deep learning. XAI is an AI model that is programmed to explain its goals, logic, and decision making so that the end users can understand. The end users can be domain experts, regulatory agencies, managers and executive board members, data scientists, users that use AI, with or without awareness, or someone who is affected by the decisions of an AI model. Chest CT has emerged as a valuable tool for the clinical diagnostic and treatment management of the lung diseases associated with COVID-19. AI can support rapid evaluation of CT scans to differentiate COVID-19 findings from other lung diseases. However, how these AI tools or deep learning algorithms reach such a decision and which are the most influential features derived from these neural networks with typically deep layers are not clear. The aim of this study is to propose and develop XAI strategies for COVID-19 classification models with an investigation of comparison. The results demonstrate promising quantification and qualitative visualisations that can further enhance the clinician's understanding and decision making with more granular information from the results given by the learned XAI models.

5.
EuropePMC; 2020.
Preprint in English | EuropePMC | ID: ppcovidwho-306305

ABSTRACT

COVID-19 is currently a pandemic in the world, can invade multiple systems, and has a high morbidity and mortality. So far, no cases of acute cerebrovascular disease have been reported. This article reports the clinical features of a COVID-19 patient whose first symptom was cerebral hemorrhage. More importantly, after the craniotomy, the patient had high fever and it was difficult to retreat. After cerebrospinal fluid testing, it was determined that an intracranial infection had occurred. After anti-infection and plasma infusion of the recovered person, the patient's symptoms gradually improved. This case suggests that COVID-19 may infringe on cerebral blood vessels and cause cerebral hemorrhage. Transfusion of plasma from rehabilitation patients is effective for critically ill patients.

6.
EuropePMC; 2020.
Preprint in English | EuropePMC | ID: ppcovidwho-312648

ABSTRACT

An outbreak of a novel coronavirus disease (i.e., COVID-19) has been recorded in Wuhan, China since late December 2019, which subsequently became pandemic around the world. Although COVID-19 is an acutely treated disease, it can also be fatal with a risk of fatality of 4.03% in China and the highest of 13.04% in Algeria and 12.67% Italy (as of 8th April 2020). The onset of serious illness may result in death as a consequence of substantial alveolar damage and progressive respiratory failure. Although laboratory testing, e.g., using reverse transcription polymerase chain reaction (RT-PCR), is the golden standard for clinical diagnosis, the tests may produce false negatives. Moreover, under the pandemic situation, shortage of RT-PCR testing resources may also delay the following clinical decision and treatment. Under such circumstances, chest CT imaging has become a valuable tool for both diagnosis and prognosis of COVID-19 patients. In this study, we propose a weakly supervised deep learning strategy for detecting and classifying COVID-19 infection from CT images. The proposed method can minimise the requirements of manual labelling of CT images but still be able to obtain accurate infection detection and distinguish COVID-19 from non-COVID-19 cases. Based on the promising results obtained qualitatively and quantitatively, we can envisage a wide deployment of our developed technique in large-scale clinical studies.

7.
EuropePMC;
Preprint in English | EuropePMC | ID: ppcovidwho-326532

ABSTRACT

The world is currently experiencing an ongoing pandemic of an infectious disease named coronavirus disease 2019 (i.e., COVID-19), which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Computed Tomography (CT) plays an important role in assessing the severity of the infection and can also be used to identify those symptomatic and asymptomatic COVID-19 carriers. With a surge of the cumulative number of COVID-19 patients, radiologists are increasingly stressed to examine the CT scans manually. Therefore, an automated 3D CT scan recognition tool is highly in demand since the manual analysis is time-consuming for radiologists and their fatigue can cause possible misjudgment. However, due to various technical specifications of CT scanners located in different hospitals, the appearance of CT images can be significantly different leading to the failure of many automated image recognition approaches. The multi-domain shift problem for the multi-center and multi-scanner studies is therefore nontrivial that is also crucial for a dependable recognition and critical for reproducible and objective diagnosis and prognosis. In this paper, we proposed a COVID-19 CT scan recognition model namely coronavirus information fusion and diagnosis network (CIFD-Net) that can efficiently handle the multi-domain shift problem via a new robust weakly supervised learning paradigm. Our model can resolve the problem of different appearance in CT scan images reliably and efficiently while attaining higher accuracy compared to other state-of-the-art methods.

8.
Appl Soft Comput ; 116: 108291, 2022 Feb.
Article in English | MEDLINE | ID: covidwho-1568513

ABSTRACT

The world is currently experiencing an ongoing pandemic of an infectious disease named coronavirus disease 2019 (i.e., COVID-19), which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Computed Tomography (CT) plays an important role in assessing the severity of the infection and can also be used to identify those symptomatic and asymptomatic COVID-19 carriers. With a surge of the cumulative number of COVID-19 patients, radiologists are increasingly stressed to examine the CT scans manually. Therefore, an automated 3D CT scan recognition tool is highly in demand since the manual analysis is time-consuming for radiologists and their fatigue can cause possible misjudgment. However, due to various technical specifications of CT scanners located in different hospitals, the appearance of CT images can be significantly different leading to the failure of many automated image recognition approaches. The multi-domain shift problem for the multi-center and multi-scanner studies is therefore nontrivial that is also crucial for a dependable recognition and critical for reproducible and objective diagnosis and prognosis. In this paper, we proposed a COVID-19 CT scan recognition model namely coronavirus information fusion and diagnosis network (CIFD-Net) that can efficiently handle the multi-domain shift problem via a new robust weakly supervised learning paradigm. Our model can resolve the problem of different appearance in CT scan images reliably and efficiently while attaining higher accuracy compared to other state-of-the-art methods.

9.
2021.
Preprint in English | Other preprints | ID: ppcovidwho-294677

ABSTRACT

Background Approximately half of COVID-19 survivors present persisting breathlessness, which may include development of pulmonary fibrosis. Research Question What is the prevalence of long-term radiological and functional pulmonary sequelae of parenchymal lung disease following hospitalisation with COVID-19 and other viral pneumonia? Study design and methods We performed systematic review and random effects meta-analysis of studies in adults hospitalised with SARS-CoV-2, SARS-CoV, MERS-CoV, or Influenza pneumonia and followed within 12 months from discharge. Searches were run on MEDLINE and Embase, updated 29 July 2021. Primary outcomes were proportion of 1) radiologic sequelae at CT scans;2) restrictive impairment;3) impaired gas transfer. Heterogeneity was explored in meta-regression. Results Ninety-five studies were included for qualitative synthesis, of which 70 were suitable for meta-analysis, including 60 studies of SARS-CoV-2 with a median follow up of 3 months. In SARS-CoV-2 the overall estimated proportion of inflammatory changes during follow up was 0.50 (95%CI 0.41 to 0.58, I 2 =94.6%), whilst fibrotic changes were estimated at 0.29 (95%CI 0.22 to 0.37, I 2 =94.1%). Inflammatory changes reduced compared with CTs performed during hospitalisation (−0.47;95%CI -0.56 to -0.37), whereas no significant resolution was observed in fibrotic changes (−0.09;95%CI -0.25 to 0.07). Impaired gas transfer was estimated at 0.38 (95%CI 0.32 to 0.44, I 2 =92.1%), which was greater than estimated restrictive impairment (0.17;95%CI 0.13 to 0.23, I 2 =92.5%). High heterogeneity means that estimates should be interpreted with caution. Confidence in the estimates was deemed low due to the heterogeneity and because studies were largely observational without controls. Interpretation A substantial proportion of radiological and functional sequelae consistent with parenchymal lung disease are observed following COVID-19 and other viral pneumonitis. Estimates of prevalence are limited by differences in case mix and initial severity. This highlights the importance of extended radiological and functional follow-up post hospitalisation. PROSPERO registration CRD42020183139 (April 2020)

10.
Nat Commun ; 12(1): 7083, 2021 12 06.
Article in English | MEDLINE | ID: covidwho-1555251

ABSTRACT

The availability of viral entry factors is a prerequisite for the cross-species transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Large-scale single-cell screening of animal cells could reveal the expression patterns of viral entry genes in different hosts. However, such exploration for SARS-CoV-2 remains limited. Here, we perform single-nucleus RNA sequencing for 11 non-model species, including pets (cat, dog, hamster, and lizard), livestock (goat and rabbit), poultry (duck and pigeon), and wildlife (pangolin, tiger, and deer), and investigated the co-expression of ACE2 and TMPRSS2. Furthermore, cross-species analysis of the lung cell atlas of the studied mammals, reptiles, and birds reveals core developmental programs, critical connectomes, and conserved regulatory circuits among these evolutionarily distant species. Overall, our work provides a compendium of gene expression profiles for non-model animals, which could be employed to identify potential SARS-CoV-2 target cells and putative zoonotic reservoirs.


Subject(s)
Atlases as Topic , Single-Cell Analysis/veterinary , Angiotensin-Converting Enzyme 2/genetics , Angiotensin-Converting Enzyme 2/metabolism , Animals , Birds , Cell Communication , Evolution, Molecular , Gene Regulatory Networks , Host-Pathogen Interactions , Lung/cytology , Lung/metabolism , Lung/virology , Mammals , Receptors, Virus/genetics , Receptors, Virus/metabolism , Reptiles , SARS-CoV-2/metabolism , Serine Endopeptidases/genetics , Serine Endopeptidases/metabolism , Transcriptome , Viral Tropism , Virus Internalization
11.
Front Public Health ; 9: 640205, 2021.
Article in English | MEDLINE | ID: covidwho-1394833

ABSTRACT

The rapid evolution of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) emergency involved Italy as the first European country. Meanwhile, China was the only other country to experience the emergency scenario, implementing public health recommendations and raising concerns about the mental health of the population. The Italian National Institute of Health [Istituto Superiore di Sanità (ISS)] reviewed relevant scientific literature in mental health to evaluate the best clinical practices and established the collaboration with the WHO, World Psychiatry Association, and China to support the public health system in a phase of acute emergency. This process permitted the definition of organizational and practical-operational Italian guidelines for the protection of the well-being of healthcare workers. These guidelines have been extensively disseminated within the Italian territory for maximum stakeholder utilization.


Subject(s)
COVID-19 , Pandemics , Humans , Italy/epidemiology , Mental Health , Public Health , SARS-CoV-2
12.
FASEB J ; 35(9): e21870, 2021 09.
Article in English | MEDLINE | ID: covidwho-1373669

ABSTRACT

COVID-19 is often characterized by dysregulated inflammatory and immune responses. It has been shown that the Traditional Chinese Medicine formulation Qing-Fei-Pai-Du decoction (QFPDD) is effective in the treatment of the disease, especially for patients in the early stage. Our network pharmacology analyses indicated that many inflammation and immune-related molecules were the targets of the active components of QFPDD, which propelled us to examine the effects of the decoction on inflammation. We found in the present study that QFPDD effectively alleviated dextran sulfate sodium-induced intestinal inflammation in mice. It inhibited the production of pro-inflammatory cytokines IL-6 and TNFα, and promoted the expression of anti-inflammatory cytokine IL-10 by macrophagic cells. Further investigations found that QFPDD and one of its active components wogonoside markedly reduced LPS-stimulated phosphorylation of transcription factor ATF2, an important regulator of multiple cytokines expression. Our data revealed that both QFPDD and wogonoside decreased the half-life of ATF2 and promoted its proteasomal degradation. Of note, QFPDD and wogonoside down-regulated deubiquitinating enzyme USP14 along with inducing ATF2 degradation. Inhibition of USP14 with the small molecular inhibitor IU1 also led to the decrease of ATF2 in the cells, indicating that QFPDD and wogonoside may act through regulating USP14 to promote ATF2 degradation. To further assess the importance of ubiquitination in regulating ATF2, we generated mice that were intestinal-specific KLHL5 deficiency, a CUL3-interacting protein participating in substrate recognition of E3s. In these mice, QFPDD mitigated inflammatory reaction in the spleen, but not intestinal inflammation, suggesting CUL3-KLHL5 may function as an E3 for ATF2 degradation.


Subject(s)
Activating Transcription Factor 2/metabolism , Down-Regulation/drug effects , Drugs, Chinese Herbal/pharmacology , Flavanones/pharmacology , Glucosides/pharmacology , Inflammation/drug therapy , Proteolysis/drug effects , Ubiquitin Thiolesterase/deficiency , Animals , Cell Line , Colitis/chemically induced , Colitis/drug therapy , Cullin Proteins/metabolism , Cytokines/metabolism , Dextran Sulfate/pharmacology , Dextran Sulfate/therapeutic use , Drugs, Chinese Herbal/therapeutic use , Flavanones/therapeutic use , Glucosides/therapeutic use , Inflammation/chemically induced , Macrophages/drug effects , Macrophages/metabolism , Male , Mice , Mice, Inbred C57BL , Phosphorylation/drug effects , Proteasome Endopeptidase Complex/drug effects , Proteasome Endopeptidase Complex/metabolism , Pyrroles/pharmacology , Pyrrolidines/pharmacology , Ubiquitin Thiolesterase/antagonists & inhibitors , Ubiquitination
14.
J Clin Hypertens (Greenwich) ; 23(9): 1651-1663, 2021 09.
Article in English | MEDLINE | ID: covidwho-1329010

ABSTRACT

Since the COVID-19 pandemic, physicians concerned about the potential adverse effects of angiotensin converting enzyme inhibitors (ACEIs)/angiotensin receptor blockers (ARBs). To explore the relationship between ACEIs/ARBs and the risk of mortality and other clinical outcomes in COVID-19 patients, the authors conducted a systemic review and meta-analysis. An electronic search was performed from inception to November 12, 2020 in PubMed, Medline, EMBASE, ClinicalTrials, TRIP, the Cochrane Library, CNKI, Wanfang, and CBM database. Risk of bias was assessed using the Risk Of Bias In Non-randomized Studies of Interventions tool. The primary outcome was in-hospital all-cause mortality. Secondary outcomes included all-cause mortality measured at 30-day or longer term, mechanical ventilation, length of hospital stay, readmission, and cardiac adverse events. A total of 28 studies with 73 465 patients was included. Twenty-two studies with 19 871 patients reported the incidence of all-cause mortality. Results showed no association between using ACEIs/ARBs and risk of mortality crude odds ratio (OR) of 1.02, 95% CI 0.71-1.46, p = .90, I2  = 88%, adjusted OR in 6260 patients of 0.96, 95% CI 0.77-1.18, p = .68, I2  = 0%. While six studies with 10 030 patients reported a lower risk of mortality in ACEIs/ARBs group hazard ratio (HR) of 0.53, 95% CI 0.34-0.84, p = .007, I2  = 68%. Similar association (for HR) was found in hypertension subgroup. There was no significant association for the secondary outcomes. Based on the available data, we concluded that ACEIs/ARBs is not associated with the risk of in-hospital all-cause mortality in COVID-19 patients, but may be associated with a decreased risk of 30-day all-cause mortality. Patients with hypertension may benefit from using ACEIs/ARBs.


Subject(s)
COVID-19 , Hypertension , Angiotensin Receptor Antagonists/adverse effects , Angiotensin-Converting Enzyme Inhibitors/adverse effects , Humans , Hypertension/drug therapy , Pandemics , SARS-CoV-2
15.
Front Med (Lausanne) ; 8: 699984, 2021.
Article in English | MEDLINE | ID: covidwho-1291051

ABSTRACT

The rapid spread of coronavirus 2019 disease (COVID-19) has manifested a global public health crisis, and chest CT has been proven to be a powerful tool for screening, triage, evaluation and prognosis in COVID-19 patients. However, CT is not only costly but also associated with an increased incidence of cancer, in particular for children. This study will question whether clinical symptoms and laboratory results can predict the CT outcomes for the pediatric patients with positive RT-PCR testing results in order to determine the necessity of CT for such a vulnerable group. Clinical data were collected from 244 consecutive pediatric patients (16 years of age and under) treated at Wuhan Children's Hospital with positive RT-PCR testing, and the chest CT were performed within 3 days of clinical data collection, from January 21 to March 8, 2020. This study was approved by the local ethics committee of Wuhan Children's Hospital. Advanced decision tree based machine learning models were developed for the prediction of CT outcomes. Results have shown that age, lymphocyte, neutrophils, ferritin and C-reactive protein are the most related clinical indicators for predicting CT outcomes for pediatric patients with positive RT-PCR testing. Our decision support system has managed to achieve an AUC of 0.84 with 0.82 accuracy and 0.84 sensitivity for predicting CT outcomes. Our model can effectively predict CT outcomes, and our findings have indicated that the use of CT should be reconsidered for pediatric patients, as it may not be indispensable.

16.
Future Microbiology ; 15(12):1101-1107, 2020.
Article in English | GIM | ID: covidwho-1016036

ABSTRACT

Since December 2019, an outbreak of SARS coronavirus 2 (SARS-CoV-2) began in Wuhan, and has rapidly spread worldwide. Previously, discharged patients with coronavirus disease 2019 (COVID-19) patients met the criteria of China's pneumonia diagnosis and treatment program of novel coronavirus infection (trial version 7) for cure of viral infection. Nevertheless, positive detection of SARS-CoV-2 has been found again in several cured COVID-19 patients, leading to conflicts with current criteria. Here, we report clinically cured cases with positive results only in anal swabs, and investigate the clinical value of anal swabs for SARS-CoV-2 detection.

17.
SSRN; 2020.
Preprint | SSRN | ID: ppcovidwho-599

ABSTRACT

Background: Few studies have comprehensively examined COVID-19 infection in children. Consequently, several important clinical questions remain unanswered. br

18.
IEEE Access ; (8): 118869-118883, 2020.
Article in English | WHO COVID, ELSEVIER | ID: covidwho-705593

ABSTRACT

An outbreak of a novel coronavirus disease (i.e., COVID-19) has been recorded in Wuhan, China since late December 2019, which subsequently became pandemic around the world. Although COVID-19 is an acutely treated disease, it can also be fatal with a risk of fatality of 4.03% in China and the highest of 13.04% in Algeria and 12.67% Italy (as of 8th April 2020). The onset of serious illness may result in death as a consequence of substantial alveolar damage and progressive respiratory failure. Although laboratory testing, e.g., using reverse transcription polymerase chain reaction (RT-PCR), is the golden standard for clinical diagnosis, the tests may produce false negatives. Moreover, under the pandemic situation, shortage of RT-PCR testing resources may also delay the following clinical decision and treatment. Under such circumstances, chest CT imaging has become a valuable tool for both diagnosis and prognosis of COVID-19 patients. In this study, we propose a weakly supervised deep learning strategy for detecting and classifying COVID-19 infection from CT images. The proposed method can minimise the requirements of manual labelling of CT images but still be able to obtain accurate infection detection and distinguish COVID-19 from non-COVID-19 cases. Based on the promising results obtained qualitatively and quantitatively, we can envisage a wide deployment of our developed technique in large-scale clinical studies.

19.
Radiology ; 296(2): E65-E71, 2020 08.
Article in English | MEDLINE | ID: covidwho-657750

ABSTRACT

Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity. Results The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (±standard deviation) was 49 years ± 15, and there were slightly more men than women (1838 vs 1484, respectively; P = .29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P < .001). The per-scan sensitivity and specificity for detecting CAP in the independent test set was 87% (152 of 175 scans) and 92% (239 of 259 scans), respectively, with an area under the receiver operating characteristic curve of 0.95 (95% CI: 0.93, 0.97). Conclusion A deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. © RSNA, 2020 Online supplemental material is available for this article.


Subject(s)
Artificial Intelligence , Betacoronavirus , Coronavirus Infections/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Adult , Aged , COVID-19 , COVID-19 Testing , Clinical Laboratory Techniques/methods , Community-Acquired Infections/diagnostic imaging , Coronavirus Infections/diagnosis , Deep Learning , Diagnosis, Differential , Female , Humans , Imaging, Three-Dimensional/methods , Male , Middle Aged , Pandemics , ROC Curve , Radiographic Image Interpretation, Computer-Assisted/methods , Retrospective Studies , SARS-CoV-2 , Sensitivity and Specificity , Tomography, X-Ray Computed/methods
SELECTION OF CITATIONS
SEARCH DETAIL