Artificial intelligence model on chest imaging to diagnose COVID-19 and other pneumonias: A systematic review and meta-analysis.

Objectives: When diagnosing Coronavirus disease 2019(COVID-19), radiologists cannot make an accurate judgments because the image characteristics of COVID-19 and other pneumonia are similar. As machine learning advances, artificial intelligence(AI) models show promise in diagnosing COVID-19 and other pneumonias. We performed a systematic review and meta-analysis to assess the diagnostic accuracy and methodological quality of the models. Methods: We searched PubMed, Cochrane Library, Web of Science, and Embase, preprints from medRxiv and bioRxiv to locate studies published before December 2021, with no language restrictions. And a quality assessment (QUADAS-2), Radiomics Quality Score (RQS) tools and CLAIM checklist were used to assess the quality of each study. We used random-effects models to calculate pooled sensitivity and specificity, I2 values to assess heterogeneity, and Deeks' test to assess publication bias. Results: We screened 32 studies from the 2001 retrieved articles for inclusion in the meta-analysis. We included 6737 participants in the test or validation group. The meta-analysis revealed that AI models based on chest imaging distinguishes COVID-19 from other pneumonias: pooled area under the curve (AUC) 0.96 (95 % CI, 0.94-0.98), sensitivity 0.92 (95 % CI, 0.88-0.94), pooled specificity 0.91 (95 % CI, 0.87-0.93). The average RQS score of 13 studies using radiomics was 7.8, accounting for 22 % of the total score. The 19 studies using deep learning methods had an average CLAIM score of 20, slightly less than half (48.24 %) the ideal score of 42.00. Conclusions: The AI model for chest imaging could well diagnose COVID-19 and other pneumonias. However, it has not been implemented as a clinical decision-making tool. Future researchers should pay more attention to the quality of research methodology and further improve the generalizability of the developed predictive models.

Management in the paediatric wards facing novel coronavirus infection: a rapid review of guidelines and consensuses.

OBJECTIVES: Relevant guidelines and consensuses for COVID-19 contain recommendations aimed at optimising the management in paediatric wards. The goal of this study was to determine the quality of those recommendations and provide suggestions to hospital managers for the adjustment of existing hospital prevention and control strategies, and also to offer recommendations for further research. DESIGN: A rapid review of the guidelines and consensuses for the management in paediatric wards facing COVID-19. METHODS: PubMed, EMBASE, the Cochrane Library, UpToDate, China National Knowledge Infrastructure, the Wanfang database and relevant websites such as medlive.cn, dxy.cn, the National Health and Health Commission and the China Center for Disease Control and Prevention were systematically searched through late May 2020. The Appraisal of Guidelines for Research and Evaluation II (AGREE II) tool was then used to assess the quality of the selected articles and summarise the relevant evidence concerning management in paediatric wards. RESULTS: A total of 35 articles were included, composed of 3 consensus guidelines, 25 expert consensuses and 7 expert opinions. Of the 35 papers, 24 were from China, 2 from the USA, 1 from Spain, 1 from Brazil, 1 from Saudi Arabia and 6 from multinational cooperative studies. Scores for the six domains of the AGREE II tool (scope and purpose, stakeholder involvement, rigour of development, clarity of presentation, applicability and editorial independence) were 98.57%, 53.57%, 17.92%, 69.62%, 26.96% and 50.35%, respectively. Recommendations for nosocomial infection and control, human resource management as well as management of paediatric patients and their families were summarised. CONCLUSIONS: Due to the outbreak of COVID-19, the quality of rapid guidelines and consensuses for the management in paediatric wards affected by COVID-19 is unsatisfactory. In the future, it will be necessary to develop more high-quality guidelines or consensuses for the management in paediatric wards to deal with nosocomial outbreaks in order to fully prepare for emergency medical and health problems.

Bibliometric analysis of researches on traditional Chinese medicine for coronavirus disease 2019 (COVID-19).

BACKGROUND: The coronavirus disease 2019 (COVID-19) has caused a worldwide pandemic, and traditional Chinese medicine (TCM) has played an important role in response. We aimed to analyze the published literature on TCM for COVID-19, and provide reference for later research. METHODS: This study searched the CBM, CNKI, PubMed, and EMBASE from its establishment to March 11, 2020. VOSviewer 1.6.11 and gCLUTO 2.0 software were used to visually analyze the included studies. RESULTS: A total of 309 studies were included, including 61 journals, 1441 authors, 277 institutions, and 27 provinces. Research collaborations among regions were among those close in geographical distance. The collaborations of institutions and authors were more likely to be restricted to the same region. Among the authors with frequency greater than two (65 authors), only 19 authors had connection with others. More than 70% (358/491) of keywords were only presented once, and 20 keywords were shown more than 10 times. Five research topics were identified: Data mining method based analysis on the medication law of Chinese medicine in prevention and management of COVID-19; exploration of active compounds of Chinese medicine for COVID-19 treatment based on network pharmacology and molecular docking; expert consensus and interpretation of COVID-19 treatment; research on the etiology and pathogenesis of COVID-19; and clinical research of TCM for COVID-19 treatment. CONCLUSION: The research hotspots were scattered, and the collaboration between authors and institutions needed to be further strengthened. To improve the quality and efficiency of research output, the integration of scientific research and resources, as well as scientific collaboration are needed.

[Analysis of traditional Chinese medicine from patent information sharing platform of coronavirus disease 2019 (COVID-19)].

Coronavirus disease 2019(COVID-19) is a newly emerged and highly contagious respiratory disease. Traditional Chinese medicine(TCM) has both systematism theory knowledge and clinical practical value in the prevention and treatment of COVID-19. Therefore, it was particularly important to examine the effect of TCM in the prevention and treatment of COVID-19. The patents of TCM might reflect the latest progression of scientific research. We aimed to provide reference for the prevention and treatment of COVID-19 by extracting and analyzing the TCM patents from the Patent Information Sharing Platform of COVID-19. The antiviral TCM patents were screened and exported from the Patent Information Sharing Platform. VOSviewer 1.6.14 was used to visualize and analyze the network of TCM in these patents. There were total 292 TCM patents, including 52 patents for etiological treatment and 240 patents for symptomatic treatment. Thirty-two provinces and 1 076 inventors were involved, mainly from Beijing, Guangdong and Jiangsu. Overall, there were 356 TCMs, 71 single prescriptions, and 221 compound prescriptions. The patents for treatment of coronavirus mainly focused on the treatment of coronavirus, while the patents for symptomatic treatment mainly focuses on the improvement of respiratory symptoms, such as fever and cough. There were 14 highly frequently used TCMs, including Glycyrrhizae Radix et Rhizoma, Scutellariae Radix, Lonicerae Japonicae Flos, Forsythiae Fructus, Isatidis Radix, Astragali Radix, Menthae Haplocalycis Herba, Gypsum Fibrosum, Houttuyniae Herba, Isatidis Folium, Rhei Radix et Rhizoma, Gardeniae Fructus, Platycodonis Radix, Armeniacae Semen Amarum. The analyzed results of the TCM patents from the patent information sharing platform of COVID-19 were consistent with the Guideline of Diagnosis and Treatment of COVID-19(7th edition), and the combination of TCM in each cluster may also provide future directions for drug compatibility.