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.

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

[This corrects the article DOI: 10.2196/42717.].

Erratum: Correction of Affiliations in the Article "Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019".

This corrects the article on p. e413 in vol. 35, PMID: 33258333.

Establishment of a Nationwide Korean Imaging Cohort of Coronavirus Disease 2019.

BACKGROUND: The Korean Society of Thoracic Radiology (KSTR) recently constructed a nation-wide coronavirus disease 2019 (COVID-19) database and imaging repository, referred to the Korean imaging cohort of COVID-19 (KICC-19) based on the collaborative efforts of its members. The purpose of this study was to provide a summary of the clinico-epidemiological data and imaging data of the KICC-19. METHODS: The KSTR members at 17 COVID-19 referral centers retrospectively collected imaging data and clinical information of consecutive patients with reverse transcription polymerase chain reaction-proven COVID-19 in respiratory specimens from February 2020 through May 2020 who underwent diagnostic chest computed tomography (CT) or radiograph in each participating hospital. RESULTS: The cohort consisted of 239 men and 283 women (mean age, 52.3 years; age range, 11-97 years). Of the 522 subjects, 201 (38.5%) had an underlying disease. The most common symptoms were fever (n = 292) and cough (n = 245). The 151 patients (28.9%) had lymphocytopenia, 86 had (16.5%) thrombocytopenia, and 227 patients (43.5%) had an elevated CRP at admission. The 121 (23.4%) needed nasal oxygen therapy or mechanical ventilation (n = 38; 7.3%), and 49 patients (9.4%) were admitted to an intensive care unit. Although most patients had cured, 21 patients (4.0%) died. The 465 (89.1%) subjects underwent a low to standard-dose chest CT scan at least once during hospitalization, resulting in a total of 658 CT scans. The 497 subjects (95.2%) underwent chest radiography at least once during hospitalization, which resulted in a total of 1,475 chest radiographs. CONCLUSION: The KICC-19 was successfully established and comprised of 658 CT scans and 1,475 chest radiographs of 522 hospitalized Korean COVID-19 patients. The KICC-19 will provide a more comprehensive understanding of the clinical, epidemiological, and radiologic characteristics of patients with COVID-19.

Clinical characteristics and treatment outcomes of patients with pneumonia caused by Raoultella planticola.

BACKGROUND: Raoultella planticola, considered to be an environmental organism, is a rare cause of human infections. Although in recent years the frequency of R. planticola infections reported in the literature has increased, few cases of pneumonia caused by R. planticola have been described. Here, we investigate the clinical characteristics, management, and clinical outcomes of pneumonia caused by R. planticola. METHODS: Consecutive patients with pneumonia caused by R. planticola were included. The medical records of patients with R. planticola pneumonia treated at Dankook University Hospital from January 2011 to December 2017 were collected. RESULTS: A total of 11 adult patients with R. planticola pneumonia were diagnosed and treated [10 males and 1 female; median age, 70 years (range: 51-79 years)]; 5 patients had underlying malignant conditions (45.5%). Antibacterial susceptibility testing showed that all isolates of R. planticola were susceptible to cephalosporins, carbapenems, fluoroquinolones, aminoglycosides, and beta-lactams/beta-lactamase inhibitors. Chest imaging revealed consolidation (8/11, 72.7%), ground-glass opacity (5/11, 45.5%), pleural effusion (5/11, 45.5%), and micronodules (3/11, 27.3%). Four patients (36.4%) required mechanical ventilation; three survived but one died of multiple organ dysfunction syndrome (principally pneumonia and septic shock). CONCLUSIONS: R. planticola pneumonia occurred mainly in patients with underlying risk factors such as malignant disease, cerebral infarction or hemorrhage, and chronic obstructive pulmonary disease. The organism was sensitive to most antibiotics, and the clinical outcomes were favorable after empirical antibiotic therapy.

Multidetector CT diagnosis of non-traumatic gastroduodenal perforation.

INTRODUCTION: To identify reliable CT features and assess the diagnostic performance of 64-multidetector CT (MDCT) in diagnosing non-traumatic gastroduodenal perforation (GDP). METHODS: We retrospectively reviewed 136 CT scans of patients with surgically proven non-traumatic gastrointestinal perforation during 7 years. 92 patients had GDP and 44 patients had other sites of perforation. CT features of perforation were evaluated and the sensitivity, specificity and likelihood ratios of each CT feature were estimated. RESULTS: The cause of GDP was peptic ulcer in 90 patients, gastric cancer in one patient, and foreign body of duodenal diverticulum in one patient. Extraluminal gas (97%) was most common CT feature of GDP, following by fluid or fat strand along gastroduodenum (89%), ascites (89%), wall defect and/or ulcer (84%), and wall thickening (72%). Of CT features, wall defect and/or ulcer showed the best positive likelihood ratios for GDP (36.83). Wall thickening also showed high positive likelihood ratios (10.52). Combined, these CT features showed 95% sensitivity and 93% specificity for localization of perforation site of GDP. CONCLUSION: MDCT is useful in diagnosis of presence and site of GDP. Wall defect and/or ulcer and wall thickening have a high positive predictive value for localization of perforation site.