Targeted next-generation sequencing of pathogens reveals the profile of secondary infections in COVID-19 patients (preprint)

PURPOSE: To use targeted next-generation sequencing (tNGS) of pathogens for analysing the etiological distribution of secondary infections in patients with severe and critical novel coronavirus pneumonia (COVID-19), to obtain microbial epidemiological data on secondary infections in patients with COVID-19, and to provide a reference for early empirical antibiotic treatment of such patients. METHODS: Patients with infections secondary to severe and critical COVID-19 and hospitalised at the First Affiliated Hospital of Shandong First Medical University between 1 December 2022 and 30 June 2023 were included in the study. The characteristics and etiological distribution of secondary infections in these patients were analysed using tNGS. RESULTS: A total of 95 patients with COVID-19 secondary infections were included in the study, of whom 87.37% had one or more underlying diseases. Forty-eight pathogens were detected, the most common being HSV-4, Candida albicans, Klebsiella pneumoniae, Enterococcus faecium, HSV-1, Staphylococcus aureus, Aspergillus fumigatus, Acinetobacter baumannii, HSV-5, and Stenotrophomonas maltophilia, with Pneumocystis jirovecii being detected in 14.29% of cases. The majority (76.84%) of COVID-19 secondary infections were mixed infections, with mixed viral-bacterial-fungal infections being the most common (28.42%). CONCLUSION: Most secondary infections in severe and critical COVID-19 patients are mixed, with high rates of viral and fungal infections. In clinical settings, monitoring for reactivation or secondary infections by Herpesviridae viruses is crucial; additionally, these patients have a significantly higher rate of P. jirovecii infection. tNGS testing on bronchoalveolar lavage fluid can help determine the aetiology of secondary infections early in COVID-19 patients and assist in choosing appropriate antibiotics.

Multiple-Inputs Convolutional Neural Network for COVID-19 Classification and Critical Region Screening From Chest X-ray Radiographs: Model Development and Performance Evaluation.

Background: The COVID-19 pandemic is becoming one of the largest, unprecedented health crises, and chest X-ray radiography (CXR) plays a vital role in diagnosing COVID-19. However, extracting and finding useful image features from CXRs demand a heavy workload for radiologists. Objective: The aim of this study was to design a novel multiple-inputs (MI) convolutional neural network (CNN) for the classification of COVID-19 and extraction of critical regions from CXRs. We also investigated the effect of the number of inputs on the performance of our new MI-CNN model. Methods: A total of 6205 CXR images (including 3021 COVID-19 CXRs and 3184 normal CXRs) were used to test our MI-CNN models. CXRs could be evenly segmented into different numbers (2, 4, and 16) of individual regions. Each region could individually serve as one of the MI-CNN inputs. The CNN features of these MI-CNN inputs would then be fused for COVID-19 classification. More importantly, the contributions of each CXR region could be evaluated through assessing the number of images that were accurately classified by their corresponding regions in the testing data sets. Results: In both the whole-image and left- and right-lung region of interest (LR-ROI) data sets, MI-CNNs demonstrated good efficiency for COVID-19 classification. In particular, MI-CNNs with more inputs (2-, 4-, and 16-input MI-CNNs) had better efficiency in recognizing COVID-19 CXRs than the 1-input CNN. Compared to the whole-image data sets, the efficiency of LR-ROI data sets showed approximately 4% lower accuracy, sensitivity, specificity, and precision (over 91%). In considering the contributions of each region, one of the possible reasons for this reduced performance was that nonlung regions (eg, region 16) provided false-positive contributions to COVID-19 classification. The MI-CNN with the LR-ROI data set could provide a more accurate evaluation of the contribution of each region and COVID-19 classification. Additionally, the right-lung regions had higher contributions to the classification of COVID-19 CXRs, whereas the left-lung regions had higher contributions to identifying normal CXRs. Conclusions: Overall, MI-CNNs could achieve higher accuracy with an increasing number of inputs (eg, 16-input MI-CNN). This approach could assist radiologists in identifying COVID-19 CXRs and in screening the critical regions related to COVID-19 classifications.

Multiple-Inputs Convolutional Neural Network for COVID-19 Classification and Critical Region Screening From Chest X-ray Radiographs: Model Development and Performance Evaluation

Background The COVID-19 pandemic is becoming one of the largest, unprecedented health crises, and chest X-ray radiography (CXR) plays a vital role in diagnosing COVID-19. However, extracting and finding useful image features from CXRs demand a heavy workload for radiologists. Objective The aim of this study was to design a novel multiple-inputs (MI) convolutional neural network (CNN) for the classification of COVID-19 and extraction of critical regions from CXRs. We also investigated the effect of the number of inputs on the performance of our new MI-CNN model. Methods A total of 6205 CXR images (including 3021 COVID-19 CXRs and 3184 normal CXRs) were used to test our MI-CNN models. CXRs could be evenly segmented into different numbers (2, 4, and 16) of individual regions. Each region could individually serve as one of the MI-CNN inputs. The CNN features of these MI-CNN inputs would then be fused for COVID-19 classification. More importantly, the contributions of each CXR region could be evaluated through assessing the number of images that were accurately classified by their corresponding regions in the testing data sets. Results In both the whole-image and left- and right-lung region of interest (LR-ROI) data sets, MI-CNNs demonstrated good efficiency for COVID-19 classification. In particular, MI-CNNs with more inputs (2-, 4-, and 16-input MI-CNNs) had better efficiency in recognizing COVID-19 CXRs than the 1-input CNN. Compared to the whole-image data sets, the efficiency of LR-ROI data sets showed approximately 4% lower accuracy, sensitivity, specificity, and precision (over 91%). In considering the contributions of each region, one of the possible reasons for this reduced performance was that nonlung regions (eg, region 16) provided false-positive contributions to COVID-19 classification. The MI-CNN with the LR-ROI data set could provide a more accurate evaluation of the contribution of each region and COVID-19 classification. Additionally, the right-lung regions had higher contributions to the classification of COVID-19 CXRs, whereas the left-lung regions had higher contributions to identifying normal CXRs. Conclusions Overall, MI-CNNs could achieve higher accuracy with an increasing number of inputs (eg, 16-input MI-CNN). This approach could assist radiologists in identifying COVID-19 CXRs and in screening the critical regions related to COVID-19 classifications.

Prevention and control measures in radiology department for COVID-19.

Since a novel coronavirus was discovered from a cluster of patients with emerging pneumonia of unknown etiology in Wuhan, China, it has spread rapidly through droplet and contact transmission. Recently, the novel coronavirus pneumonia which was named COVID-19 by the World Health Organization (WHO) has been raised as a worldwide problem. Radiological examinations were confirmed as effective methods for the screening and diagnosis of COVID-19. It is reported that some radiologists and radiological technologists were infected when giving examinations to the patients with COVID-19. In order to reduce the infection risk of medical staff in radiology department, we summarized the experience on prevention and control measures in radiology department for COVID-19, aiming to guide the prevention and practical work for radiologists and radiological technologists. KEY POINTS: • The novel coronavirus spreads rapidly through droplet and contact transmission. • Radiologists and radiological technologists were possibly infected by patients. • Prevention and control measures in radiology department for COVID-19 are important.