Analysis of CT scan images for COVID-19 pneumonia based on a deep ensemble framework with DenseNet, Swin transformer, and RegNet.

COVID-19 has caused enormous challenges to global economy and public health. The identification of patients with the COVID-19 infection by CT scan images helps prevent its pandemic. Manual screening COVID-19-related CT images spends a lot of time and resources. Artificial intelligence techniques including deep learning can effectively aid doctors and medical workers to screen the COVID-19 patients. In this study, we developed an ensemble deep learning framework, DeepDSR, by combining DenseNet, Swin transformer, and RegNet for COVID-19 image identification. First, we integrate three available COVID-19-related CT image datasets to one larger dataset. Second, we pretrain weights of DenseNet, Swin Transformer, and RegNet on the ImageNet dataset based on transformer learning. Third, we continue to train DenseNet, Swin Transformer, and RegNet on the integrated larger image dataset. Finally, the classification results are obtained by integrating results from the above three models and the soft voting approach. The proposed DeepDSR model is compared to three state-of-the-art deep learning models (EfficientNetV2, ResNet, and Vision transformer) and three individual models (DenseNet, Swin transformer, and RegNet) for binary classification and three-classification problems. The results show that DeepDSR computes the best precision of 0.9833, recall of 0.9895, accuracy of 0.9894, F1-score of 0.9864, AUC of 0.9991 and AUPR of 0.9986 under binary classification problem, and significantly outperforms other methods. Furthermore, DeepDSR obtains the best precision of 0.9740, recall of 0.9653, accuracy of 0.9737, and F1-score of 0.9695 under three-classification problem, further suggesting its powerful image identification ability. We anticipate that the proposed DeepDSR framework contributes to the diagnosis of COVID-19.

Platinum nanoparticles (PtNPs)-based CRISPR/Cas12a platform for detection of nucleic acid and protein in clinical samples.

Early rapid screening diagnostic assay is essential for the identification, prevention, and evaluation of many contagious or refractory diseases. The optical density transducer created by platinum nanoparticles (PtNPs) (OD-CRISPR) is reported in the present research as a cheap and easy-to-execute CRISPR/Cas12a-based diagnostic platform. The OD-CRISPR uses PtNPs, with ultra-high peroxidase-mimicking activity, to increase the detection sensitivity, thereby enabling the reduction of detection time and cost. The OD-CRISPR can be utilized to identify nucleic acid or protein biomarkers within an incubation time of 30-40min in clinical specimens. In the case of taking severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) N gene as an instance, when compared to a quantitative reverse transcription-polymerase chain reaction (RT-qPCR), the OD-CRISPR test attains a sensitivity of 79.17% and a specificity of 100%. In terms of detecting prostate-specific antigen (PSA), aptamer-based OD-CRISPR assay achieves the least discoverable concentration of 0.01 ng mL-1. In general, the OD-CRISPR can detect nucleic acid and protein biomarkers, and is a potential strategy for early rapid screening diagnostic tools.

15-Month Health Outcomes and the Related Risk Factors of Hospitalized COVID-19 Patients From Onset: A Cohort Study.

Objective: The long-term impact of COVID-19 on patient health has been a recent focus. This study aims to determine the persistent symptoms and psychological conditions of patients hospitalized with COVID-19 15 months after onset, that patients first developed symptoms. The potential risk factors were also explored. Methods: A cohort of COVID-19 patients discharged from February 20, 2020 to March 31, 2020 was recruited. Follow-ups were conducted using validated questionnaires and psychological screening scales at 15 months after onset to evaluate the patients' health status. The risk factors for long-term health impacts and their associations with disease severity was analyzed. Findings: 534 COVID-19 patients were enrolled. The median age of the patients was 62.0 years old (IQR 52.0-70.0) and 295 were female (55.2%). The median time from onset to follow-up was 460.0 (451.0-467.0) days. Sleep disturbance (18.5%, 99/534) and fatigue (17.2%, 92/534) were the most common persistent symptoms. 6.4% (34/534) of the patients had depression, 9.2% (49/534) were anxious, 13.0% (70/534) had insomnia and 4.7% (25/534) suffered from post-traumatic stress disorder (PTSD). Multivariate adjusted logistic regression analysis showed that glucocorticoid use during hospitalization (OR 3.58, 95% CI 1.12-11.44) was significantly associated with an increased risk of fatigue. The OR values for anxiety and sleep disorders were 2.36 (95% CI 1.07-5.20) and 2.16 (95% CI 1.13-4.14) in females to males. The OR value of PTSD was 25.6 (95% CI 3.3-198.4) in patients with persistent symptoms to those without persistent symptoms. No significant associations were observed between fatigue syndrome or adverse mental outcomes and disease severity. Conclusions: 15-month follow-up in this study demonstrated the need of extended rehabilitation intervention for complete recovery in COVID-19 patients.

Progress in the Diagnosis and Treatment of COVID-19 in Children: A Review.

Coronavirus disease 2019 (COVID-19) has been circulating in many countries around the world, characterized by long incubation period, strong infectivity, strong variability, high population susceptibility and diversified transmission methods. Its causative agent is severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Compared with adult patients, the clinical manifestations of COVID-19 in children are often dominated by mild or asymptomatic infections, but children are also important virus carriers and play an important role in the transmission of the virus. In addition, some children will show excessive inflammatory response and experience serious complications such as multisystem inflammatory syndrome in children (MIS-C). At present, the research on COVID-19 in children is still imperfect. This article will review epidemiological characteristics, the mechanism of action, variant characteristics, clinical manifestations, auxiliary examinations and treatment of children with COVID-19, in order to provide help for the diagnosis, treatment and research of children with COVID-19.

Application of the amplification-free SERS-based CRISPR/Cas12a platform in the identification of SARS-CoV-2 from clinical samples.

The control of contagious or refractory diseases requires early, rapid diagnostic assays that are simple, fast, and easy-to-use. Here, easy-to-implement CRISPR/Cas12a-based diagnostic platform through Raman transducer generated by Raman enhancement effect, term as SERS-CRISPR (S-CRISPR), are described. The S-CRISPR uses high-activity noble metallic nanoscopic materials to increase the sensitivity in the detection of nucleic acids, without amplification. This amplification-free platform, which can be performed within 30-40 min of incubation time, is then used for detection of SARS-CoV-2 derived nucleic acids in RNA extracts obtained from nasopharyngeal swab specimens (n = 112). Compared with the quantitative reverse transcription polymerase chain reaction (RT-qPCR), the sensitivity and specificity of S-CRISPR reaches 87.50% and 100%, respectively. In general, the S-CRISPR can rapidly identify the RNA of SARS-CoV-2 RNA without amplification and is a potential strategy for nucleic acid point of care test (POCT).

Clinical course of patients on maintenance hemodialysis and COVID-19: a retrospective longitudinal study.

Coronavirus Disease 2019 (COVID-19) emerges as a global pandemic and there is a lack of evidence about the clinical course and outcome of patients on maintenance hemodialysis (MHD). Here we conducted a retrospective longitudinal study aimed to analyze the clinical features and outcome of MHD patients hospitalized with COVID-19. Of 3126 inpatients with COVID-19 at 3 Branches of Wuhan Tongji Hospital from Jan 18th to Mar 9th, 2020, 19 patients were undergoing maintenance hemodialysis. Among the 19 MHD patients with COVID-19, 6 patients (31.6%) died, and 13 patients (68.4%) were able to be discharged. Baseline characteristics, clinical courses, laboratory findings, and dynamic trajectories of major laboratory markers were compared between survivors and nonsurvivors. According to our findings, MHD patients with COVID-19 who experienced non-surviving outcome had more elevated CRP, IL6 and procalcitonin as well as fibrinogen levels at various points compared to survivors. Thus the dysregulation of immune response as well as coagulation abnormalities might be highly involved in the pathological process of COVID-19, contributing to the poor prognosis in MHD patients.

Association of liver abnormalities with in-hospital mortality in patients with COVID-19.

BACKGROUND & AIMS: The evolution and clinical significance of abnormal liver chemistries and the impact of hepatitis B infection on outcome in patients with COVID-19 is not well characterized. This study aimed to explore these issues. METHODS: This large retrospective cohort study included 2,073 patients with coronavirus disease 2019 (COVID-19) and definite outcomes in Wuhan, China. Longitudinal liver function tests were conducted, with associated factors and risk of death determined by multivariate regression analyses. A prognostic nomogram was formulated to predict the survival of patients with COVID-19. The characteristics of liver abnormalities and outcomes of patients with COVID-19, with and without hepatitis B, were compared after 1:3 propensity score matching. RESULTS: Of the 2,073 patients, 1,282 (61.8%) had abnormal liver chemistries during hospitalization, and 297 (14.3%) had a liver injury. The mean levels of aspartate aminotransferase (AST) and direct bilirubin (D-Bil) increased early after symptom onset in deceased patients and showed disparity compared to levels in discharged patients throughout the clinical course of the disease. Abnormal AST (adjusted hazard ratio [HR] 1.39; 95% CI 1.04-1.86, p = 0.027) and D-Bil (adjusted HR 1.66; 95% CI 1.22-2.26; p = 0.001) levels at admission were independent risk factors for mortality due to COVID-19. A nomogram was established based on the results of multivariate analysis and showed sufficient discriminatory power and good consistency between the prediction and the observation. HBV infection in patients did not increase the risk of poor COVID-19-associated outcomes. CONCLUSIONS: Abnormal AST and D-Bil levels at admission were independent predictors of COVID-19-related mortality. Therefore, monitoring liver chemistries, especially AST and D-Bil levels, is necessary in hospitalized patients with COVID-19. LAY SUMMARY: Liver test abnormalities (in particular elevations in the levels of aspartate aminotransferase [AST] and direct bilirubin [D-Bil]) were observed after symptom onset in patients who went on to die of coronavirus disease 2019 (COVID-19). Abnormal levels of AST and D-Bil at admission were independent predictors of COVID-19-related mortality. HBV infection in patients did not increase the risk of poor COVID-19-associated outcomes.