Two Years of Experience and Methodology of Korean COVID-19 Living Clinical Practice Guideline Development.

BACKGROUND: In Korea, during the early phase of the coronavirus disease 2019 (COVID-19) pandemic, we responded to the uncertainty of treatments under various conditions, consistently playing catch up with the speed of evidence updates. Therefore, there was high demand for national-level evidence-based clinical practice guidelines for clinicians in a timely manner. We developed evidence-based and updated living recommendations for clinicians through a transparent development process and multidisciplinary expert collaboration. METHODS: The National Evidence-based Healthcare Collaborating Agency (NECA) and the Korean Academy of Medical Sciences (KAMS) collaborated to develop trustworthy Korean living guidelines. The NECA-supported methodological sections and 8 professional medical societies of the KAMS worked with clinical experts, and 31 clinicians were involved annually. We developed a total of 35 clinical questions, including medications, respiratory/critical care, pediatric care, emergency care, diagnostic tests, and radiological examinations. RESULTS: An evidence-based search for treatments began in March 2021 and monthly updates were performed. It was expanded to other areas, and the search interval was organized by a steering committee owing to priority changes. Evidence synthesis and recommendation review was performed by researchers, and living recommendations were updated within 3-4 months. CONCLUSION: We provided timely recommendations on living schemes and disseminated them to the public, policymakers and various stakeholders using webpages and social media. Although the output was successful, there were some limitations. The rigor of development issues, urgent timelines for public dissemination, education for new developers, and spread of several new COVID-19 variants have worked as barriers. Therefore, we must prepare systematic processes and funding for future pandemics.

[Korean Clinical Imaging Guidelines for Justification of Diagnostic Imaging Study for COVID-19]. / 한국형 COVID-19 흉부영상 진단 시행 가이드라인.

To develop Korean coronavirus disease (COVID-19) chest imaging justification guidelines, eight key questions were selected and the following recommendations were made with the evidence-based clinical imaging guideline adaptation methodology. It is appropriate not to use chest imaging tests (chest radiograph or CT) for the diagnosis of COVID-19 in asymptomatic patients. If reverse transcription-polymerase chain reaction testing is not available or if results are delayed or are initially negative in the presence of symptoms suggestive of COVID-19, chest imaging tests may be considered. In addition to clinical evaluations and laboratory tests, chest imaging may be contemplated to determine hospital admission for asymptomatic or mildly symptomatic unhospitalized patients with confirmed COVID-19. In hospitalized patients with confirmed COVID-19, chest imaging may be advised to determine or modify treatment alternatives. CT angiography may be considered if hemoptysis or pulmonary embolism is clinically suspected in a patient with confirmed COVID-19. For COVID-19 patients with improved symptoms, chest imaging is not recommended to make decisions regarding hospital discharge. For patients with functional impairment after recovery from COVID-19, chest imaging may be considered to distinguish a potentially treatable disease.

Deep convolution neural networks to differentiate between COVID-19 and other pulmonary abnormalities on chest radiographs: Evaluation using internal and external datasets.

We aimed to evaluate the performance of convolutional neural networks (CNNs) in the classification of coronavirus disease 2019 (COVID-19) disease using normal, pneumonia, and COVID-19 chest radiographs (CXRs). First, we collected 9194 CXRs from open datasets and 58 from the Korea University Anam Hospital (KUAH). The number of normal, pneumonia, and COVID-19 CXRs were 4580, 3884, and 730, respectively. The CXRs obtained from the open dataset were randomly assigned to the training, tuning, and test sets in a 70:10:20 ratio. For external validation, the KUAH (20 normal, 20 pneumonia, and 18 COVID-19) dataset, verified by radiologists using computed tomography, was used. Subsequently, transfer learning was conducted using DenseNet169, InceptionResNetV2, and Xception to identify COVID-19 using open datasets (internal) and the KUAH dataset (external) with histogram matching. Gradient-weighted class activation mapping was used for the visualization of abnormal patterns in CXRs. The average AUC and accuracy of the multiscale and mixed-COVID-19Net using three CNNs over five folds were (0.99 ± 0.01 and 92.94% ± 0.45%), (0.99 ± 0.01 and 93.12% ± 0.23%), and (0.99 ± 0.01 and 93.57% ± 0.29%), respectively, using the open datasets (internal). Furthermore, these values were (0.75 and 74.14%), (0.72 and 68.97%), and (0.77 and 68.97%), respectively, for the best model among the fivefold cross-validation with the KUAH dataset (external) using domain adaptation. The various state-of-the-art models trained on open datasets show satisfactory performance for clinical interpretation. Furthermore, the domain adaptation for external datasets was found to be important for detecting COVID-19 as well as other diseases.