AI support for accurate and fast radiological diagnosis of COVID-19: an international multicenter, multivendor CT study.

OBJECTIVES: Differentiation between COVID-19 and community-acquired pneumonia (CAP) in computed tomography (CT) is a task that can be performed by human radiologists and artificial intelligence (AI). The present study aims to (1) develop an AI algorithm for differentiating COVID-19 from CAP and (2) evaluate its performance. (3) Evaluate the benefit of using the AI result as assistance for radiological diagnosis and the impact on relevant parameters such as accuracy of the diagnosis, diagnostic time, and confidence. METHODS: We included n = 1591 multicenter, multivendor chest CT scans and divided them into AI training and validation datasets to develop an AI algorithm (n = 991 CT scans; n = 462 COVID-19, and n = 529 CAP) from three centers in China. An independent Chinese and German test dataset of n = 600 CT scans from six centers (COVID-19 / CAP; n = 300 each) was used to test the performance of eight blinded radiologists and the AI algorithm. A subtest dataset (180 CT scans; n = 90 each) was used to evaluate the radiologists' performance without and with AI assistance to quantify changes in diagnostic accuracy, reporting time, and diagnostic confidence. RESULTS: The diagnostic accuracy of the AI algorithm in the Chinese-German test dataset was 76.5%. Without AI assistance, the eight radiologists' diagnostic accuracy was 79.1% and increased with AI assistance to 81.5%, going along with significantly shorter decision times and higher confidence scores. CONCLUSION: This large multicenter study demonstrates that AI assistance in CT-based differentiation of COVID-19 and CAP increases radiological performance with higher accuracy and specificity, faster diagnostic time, and improved diagnostic confidence. KEY POINTS: • AI can help radiologists to get higher diagnostic accuracy, make faster decisions, and improve diagnostic confidence. • The China-German multicenter study demonstrates the advantages of a human-machine interaction using AI in clinical radiology for diagnostic differentiation between COVID-19 and CAP in CT scans.

A network representation approach for COVID-19 drug recommendation.

The coronavirus disease 2019 (COVID-19) has outbreak since early December 2019, and COVID-19 has caused over 100 million cases and 2 million deaths around the world. After one year of the COVID-19 outbreak, there is no certain and approve medicine against it. Drug repositioning has become one line of scientific research that is being pursued to develop an effective drug. However, due to the lack of COVID-19 data, there is still no specific drug repositioning targeting the COVID-19. In this paper, we propose a framework for COVID-19 drug repositioning. This framework has several advantages that can be exploited: one is that a local graph aggregating representation is used across a heterogeneous network to address the data sparsity problem; another is the multi-hop neighbors of the heterogeneous graph are aggregated to recall as many COVID-19 potential drugs as possible. Our experimental results show that our COVDR framework performs significantly better than baseline methods, and the docking simulation verifies that our three potential drugs have the ability to against COVID-19 disease.

Development of spike protein-based fluorescence lateral flow assay for the simultaneous detection of SARS-CoV-2 specific IgM and IgG.

The pandemic outbreak of the 2019 coronavirus disease (COVID-19), which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is still spreading rapidly and poses a great threat to human health. As such, developing rapid and accurate immunodiagnostic methods for the identification of infected persons is needed. Here, we proposed a simple but sensitive on-site testing method based on spike protein-conjugated quantum dot (QD) nanotag-integrated lateral flow immunoassay (LFA) to simultaneously detect SARS-CoV-2-specific IgM and IgG in human serum. Advanced silica-core@dual QD-shell nanocomposites (SiO2@DQD) with superior luminescence and stability were prepared to serve as fluorescent nanotags in the LFA strip and guarantee high sensitivity and reliability of the assay. The performance of the SiO2@DQD-strip was fully optimized and confirmed by using 10 positive serum samples from COVID-19 patients and 10 negative samples from patients with other respiratory diseases. The practical clinical value of the assay was further evaluated by testing 316 serum samples (114 positive and 202 negative samples). The overall detection sensitivity and specificity reached 97.37% (111/114) and 95.54% (193/202), respectively, indicating the huge potential of our proposed method for the rapid and accurate detection of SARS-CoV-2-infected persons and asymptomatic carriers.

Sensitive and Simultaneous Detection of SARS-CoV-2-Specific IgM/IgG Using Lateral Flow Immunoassay Based on Dual-Mode Quantum Dot Nanobeads.

A rapid and accurate method for detection of virus (SARS-CoV-2)-specific antibodies is important to contain the 2019 coronavirus disease (COVID-19) outbreak, which is still urgently needed. Here, we develop a colorimetric-fluorescent dual-mode lateral flow immunoassay (LFIA) biosensor for rapid, sensitive, and simultaneous detection of SARS-CoV-2-specific IgM and IgG in human serum using spike (S) protein-conjugated SiO2@Au@QD nanobeads (NBs) as labels. The assay only needs 1 µL of the serum sample, can be completed within 15 min, and is 100 times more sensitive than the colloidal gold-based LFIA. Two detection modes of our biosensor are available: the colorimetric mode for rapid screening of the patients with suspected SARS-CoV-2 infection without any special instrument and the fluorescent mode for sensitive and quantitative analyses to determine the concentrations of specific IgM/IgG in human serum and detect the infection early and precisely. We validated the proposed method using 16 positive serum samples from patients with COVID-19 and 41 negative samples from patients with other viral respiratory infections. The results demonstrated that combined detection of virus-specific IgM and IgG via SiO2@Au@QD LFIA can identify 100% of patients with SARS-CoV-2 infection with 100% specificity.

Development of a SERS-based lateral flow immunoassay for rapid and ultra-sensitive detection of anti-SARS-CoV-2 IgM/IgG in clinical samples.

The accurate and rapid screening of serum antibodies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the key to control the spread of 2019 coronavirus disease (COVID-19). In this study, we reported a surface-enhanced Raman scattering-based lateral flow immunoassay (SERS-LFIA) for the simultaneous detection of anti-SARS-CoV-2 IgM/IgG with high sensitivity. Novel SERS tags labeled with dual layers of Raman dye were fabricated by coating a complete Ag shell on SiO2 core (SiO2@Ag) and exhibited excellent SERS signals, good monodispersity, and high stability. Anti-human IgM and IgG were immobilized onto the two test lines of the strip to capture the formed SiO2@Ag-spike (S) protein-anti-SARS-CoV-2 IgM/IgG immunocomplexes. The SERS signal intensities of the IgM and IgG test zones were easily recorded by a portable Raman instrument and used for the high-sensitivity analysis of target IgM and IgG. The limit of detection of SERS-LFIA was 800 times higher than that of standard Au nanoparticle-based LFIA for target IgM and IgG. The SERS-LFIA biosensor was tested on 19 positive serum samples from COVID-19 patients and 49 negative serum samples from healthy people to demonstrate the clinical feasibility of our proposed assay. The results revealed that the proposed method exhibited high accuracy and specificity for patients with SARS-CoV-2 infection.

How to evaluate the value of chest CT in COVID-19: case reports and literature review.

The coronavirus disease 2019 (COVID-19) that occurred in Wuhan, Hubei Province, China, has been declared a public health emergency of international concern and a pandemic by the World Health Organization. The Chinese government has temporarily taken strong response measures and effective procedures to stop the further expansion and development of the epidemic. It is important for clinicians to screen, diagnose, and monitor COVID-19.

The value of serum amyloid A for predicting the severity and recovery of COVID-19.

The present study aimed to evaluate the value of serum amyloid A (SAA) in coronavirus disease 2019 (COVID-19) and compared the efficacy of SAA and C-reactive protein (CRP) in predicting the severity and recovery of COVID-19. A retrospective study was conducted on COVID-19 patients hospitalized in Wuhan No. 1 Hospital (Hubei, China) from January 21, 2020 to March 4, 2020. A two-way ANOVA analysis was used to compare the serum CRP and SAA levels between mild group and severe group during hospitalization days. Linear regression was used to analyze the relationship between the serum CRP, SAA levels and treatment days in recovered patients. The Logistic regression analysis and the area under curve (AUC) were calculated to determine the probability for predicting the severity and recovery of COVID-19. The severe group displayed higher CRP and SAA levels compared with the mild group during hospitalization (P<0.001). Logistic regression indicated that SAA and CRP were independent risk factors for the severity of COVID-19. The corresponding AUC of CRP and SAA values for severity of COVID-19 were 0.804 and 0.818, respectively. Linear regression analysis revealed that CRP and SAA levels were negatively correlated with treatment days in recovered patients (r=-0.761, -0.795, respectively). Logistic regression demonstrated that SAA was an independent factor for predicting the recovery of COVID-19. However, CRP could not predict the recovery of COVID-19. The corresponding AUC of SAA for the recovery of COVID-19 was 0.923. The results of the present study indicated that SAA can be considered to be a biomarker for predicting the severity and recovery of COVID-19.

An Analysis on the Clinical Features of MHD Patients with Coronavirus Disease 2019: A Single Center Study (preprint)

Background: In this study, we aimed to find out the features of the maintenance hemodialysis (MHD) patients infected with Coronavirus Disease 2019 (COVID-19) in the Blood Purification Center of Wuhan No.1 Hospital, Hubei Province, China, and provide evidences for clinical treatment.Methods: We collected the data of all the MHD patients in this hemodialysis center by February 20, 2020, including those infected with COVID-19. These patients were divided into three groups: the control group (537 cases), confirmed group (66 cases) and suspected group (24 cases). We compared the relevant data of the three groups and analyzed the factors that may affect the possibility of catching COVID-19.Results: 1. By February 20, 2020, there were 627 MHD patients in the Hemodialysis Center of Wuhan No.1 Hospital. The prevalence rate of the COVID-19 was 14.35% (90/627, including 66 confirmed cases and 24 suspected cases); the fatality rate 13.33% (12/90, including 12 death cases); the mortality rate 1.91% (12/627).2. The comparison between the three groups revealed the following results: weekly hemodialysis duration (WHD), ultrafiltration volume (UFV) and ultrafiltration rate (UFR) of the confirmed group were obviously lower than those of the control and suspected groups (P＜0.05); the neutrophil ratio (N%), neutrophil (N#), monocyte (M#) and total carbon dioxide (TCO2) were significantly higher than those of the control group while the lymphocyte ratio (L%) was much lower (P＜0.05).3. The lung CT scans found three common features: bilateral abnormalities (81.54%), multiple abnormalities (84.62%) and patchy opacity (61.54%).4. The binary logstic regression analysis showed that diabetes (OR=5.404,95% CI 1.950～14.976, P=0.001) and hypertension (OR=3.099,95% CI 1.380～6.963, P=0.006) are independent risk factors for MHD patients to be infected with COVID-19; WHD (OR=0.846,95% CI 0.737～0.970, P=0.017), UFR (OR=0.012,95% CI 0.002～0.058, P＜0.001) and serum ferritin (SF, OR=0.823,95% CI 0.748～0.906, P＜0.001) are independent protective factors.Conclusion: MHD patients with diabetes or hypertension are more likely to be infected with COVID-19. In clinical treatment, hemodialysis duration, UFR and SF levels should be controlled appropriately to reduce the risk of infection.