Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study.

BACKGROUND: An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19. OBJECTIVE: We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19. METHODS: This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration. RESULTS: The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859). CONCLUSIONS: The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.

Different treatment response to systemic corticosteroids according to white blood cell counts in severe COVID-19 patients.

BACKGROUND: Limited data are available in COVID-19 patients on the prediction of treatment response to systemic corticosteroid therapy based on systemic inflammatory markers. There is a concern whether the response to systemic corticosteroid is different according to white blood cell (WBC) counts in COVID-19 patients. We aimed to assess whether WBC count is related with the clinical outcomes after treatment with systemic corticosteroids in severe COVID-19. METHODS: We conducted a retrospective cohort study and analysed the patients hospitalised for severe COVID-19 and received systemic corticosteroids between July 2020 and June 2021. The primary endpoint was to compare the composite poor outcome of mechanical ventilation, extracorporeal membrane oxygenation, and mortality among the patients with different WBC counts. RESULTS: Of the 585 COVID-19 patients who required oxygen supplementation and systemic corticosteroids, 145 (24.8%) belonged to the leukopoenia group, 375 (64.1%) belonged to the normal WBC group, and 65 (11.1%) belonged to the leukocytosis group. In Kaplan-Meier curve, the composite poor outcome was significantly reduced in leukopoenia group compared to leukocytosis group (log-rank p-value < 0.001). In the multivariable Cox regression analysis, leukopoenia group was significantly associated with a lower risk of the composite poor outcome compared to normal WBC group (adjusted hazard ratio [aHR] = 0.32, 95% CI 0.14-0.76, p-value = 0.009) and leukocytosis group (aHR = 0.30, 95% CI = 0.12-0.78, p-value = 0.013). There was no significant difference in aHR for composite poor outcome between leukocytosis and normal WBC group. CONCLUSION: Leukopoenia may be related with a better response to systemic corticosteroid therapy in COVID-19 patients requiring oxygen supplementation.KEY MESSAGESIn severe COVID-19 treated with systemic corticosteroids, patients with leukopoenia showed a lower hazard for composite poor outcome compared to patients with normal white blood cell counts or leukocytosis.Leukopoenia may be a potential biomarker for better response to systemic corticosteroid therapy in COVID-19 pneumonia.

Deep Learning-Based Automatic CT Quantification of Coronavirus Disease 2019 Pneumonia: An International Collaborative Study.

OBJECTIVE: We aimed to develop and validate the automatic quantification of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) images. METHODS: This retrospective study included 176 chest CT scans of 131 COVID-19 patients from 14 Korean and Chinese institutions from January 23 to March 15, 2020. Two experienced radiologists semiautomatically drew pneumonia masks on CT images to develop the 2D U-Net for segmenting pneumonia. External validation was performed using Japanese (n = 101), Italian (n = 99), Radiopaedia (n = 9), and Chinese data sets (n = 10). The primary measures for the system's performance were correlation coefficients for extent (%) and weight (g) of pneumonia in comparison with visual CT scores or human-derived segmentation. Multivariable logistic regression analyses were performed to evaluate the association of the extent and weight with symptoms in the Japanese data set and composite outcome (respiratory failure and death) in the Spanish data set (n = 115). RESULTS: In the internal test data set, the intraclass correlation coefficients between U-Net outputs and references for the extent and weight were 0.990 and 0.993. In the Japanese data set, the Pearson correlation coefficients between U-Net outputs and visual CT scores were 0.908 and 0.899. In the other external data sets, intraclass correlation coefficients were between 0.949-0.965 (extent) and between 0.978-0.993 (weight). Extent and weight in the top quartile were independently associated with symptoms (odds ratio, 5.523 and 10.561; P = 0.041 and 0.016) and the composite outcome (odds ratio, 9.365 and 7.085; P = 0.021 and P = 0.035). CONCLUSIONS: Automatically quantified CT extent and weight of COVID-19 pneumonia were well correlated with human-derived references and independently associated with symptoms and prognosis in multinational external data sets.

[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.

KSR/KSTR Guidelines for the Use of Diagnostic Imaging for COVID-19.

The Korean Society of Radiology and the Korean Society of Thoracic Radiology have prepared recommendations for the use of diagnostic imaging for COVID-19 in various clinical scenarios. We have tried to grasp the situation in the real world, aggregated opinions from the chest radiologists, and reviewed available references, in order to suggest the most reasonable recommendations possible at this moment. As circumstances change and new evidences emerge, the recommendations should immediately be modified accordingly.