Prognostic Impact of Myosteatosis on Mortality in Hospitalized Patients with COVID-19.

Body composition, including sarcopenia, adipose tissue, and myosteatosis, is associated with unfavorable clinical outcomes in patients with coronavirus disease (COVID-19). However, few studies have identified the impact of body composition, including pre-existing risk factors, on COVID-19 mortality. Therefore, this study aimed to evaluate the effect of body composition, including pre-existing risk factors, on mortality in hospitalized patients with COVID-19. This two-center retrospective study included 127 hospitalized patients with COVID-19 who underwent unenhanced chest computed tomography (CT) between February and April 2020. Using the cross-sectional CT images at the L2 vertebra level, we analyzed the body composition, including skeletal muscle mass, visceral to subcutaneous adipose tissue ratio (VSR), and muscle density using the Hounsfield unit (HU). Of 127 patients with COVID-19, 16 (12.6%) died. Compared with survivors, non-survivors had low muscle density (41.9 vs. 32.2 HU, p < 0.001) and high proportion of myosteatosis (4.5 vs. 62.5%, p < 0.001). Cox regression analyses revealed diabetes (hazard ratio [HR], 3.587), myosteatosis (HR, 3.667), and a high fibrosis-4 index (HR, 1.213) as significant risk factors for mortality in patients with COVID-19. Myosteatosis was associated with mortality in hospitalized patients with COVID-19, independent of pre-existing prognostic factors.

Deep Learning-Based Four-Region Lung Segmentation in Chest Radiography for COVID-19 Diagnosis.

Imaging plays an important role in assessing the severity of COVID-19 pneumonia. Recent COVID-19 research indicates that the disease progress propagates from the bottom of the lungs to the top. However, chest radiography (CXR) cannot directly provide a quantitative metric of radiographic opacities, and existing AI-assisted CXR analysis methods do not quantify the regional severity. In this paper, to assist the regional analysis, we developed a fully automated framework using deep learning-based four-region segmentation and detection models to assist the quantification of COVID-19 pneumonia. Specifically, a segmentation model is first applied to separate left and right lungs, and then a detection network of the carina and left hilum is used to separate upper and lower lungs. To improve the segmentation performance, an ensemble strategy with five models is exploited. We evaluated the clinical relevance of the proposed method compared with the radiographic assessment of the quality of lung edema (RALE) annotated by physicians. Mean intensities of segmented four regions indicate a positive correlation to the regional extent and density scores of pulmonary opacities based on the RALE. Therefore, the proposed method can accurately assist the quantification of regional pulmonary opacities of COVID-19 pneumonia patients.

Federated learning for predicting clinical outcomes in patients with COVID-19.

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

Multicenter Analysis of Clinical Features and Prognosis of COVID-19 Patients with Hepatic Impairment.

Background/Aims: Recent data indicate the presence of liver enzyme abnormalities in patients with coronavirus disease 2019 (COVID-19). We aimed to evaluate the clinical features and treatment outcomes of COVID-19 patients with abnormal liver enzymes. Methods: We performed a retrospective, multicenter study of 874 COVID-19 patients admitted to five tertiary hospitals from February 20 to April 14, 2020. Data on clinical features, laboratory parameters, medications, and treatment outcomes were collected until April 30, 2020, and compared between patients with normal and abnormal aminotransferases. Results: Abnormal aminotransferase levels were observed in 362 patients (41.1%), of which 94 out of 130 (72.3%) and 268 out of 744 (36.0%) belonged to the severe and non-severe COVID- 19 categories, respectively. The odds ratios (95% confidence interval) for male patients, patients with a higher body mass index, patients with severe COVID-19 status, and patients with lower platelet counts were 1.500 (1.029 to 2.184, p=0.035), 1.097 (1.012 to 1.189, p=0.024), 2.377 (1.458 to 3.875, p=0.001), and 0.995 (0.993 to 0.998, p>0.001), respectively, indicating an independent association of these variables with elevated aminotransferase levels. Lopinavir/ ritonavir and antibiotic use increased the odds ratio of abnormal aminotransferase levels after admission (1.832 and 2.646, respectively, both p<0.05). The median time to release from quarantine was longer (22 days vs 26 days, p=0.001) and the mortality rate was higher (13.0% vs 2.9%, p<0.001) in patients with abnormal aminotransferase levels. Conclusions: Abnormal aminotransferase levels are common in COVID-19 patients and are associated with poor clinical outcomes. Multivariate analysis of patients with normal aminotransferase levels on admission showed that the use of lopinavir/ritonavir and antibiotics was associated with abnormal aminotransferase levels; thus, careful monitoring is needed.

A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records.

PURPOSE: As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease of 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based on their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients' electronic health records (EHR), which included vital signs and laboratory data, with deep learning- and CT-based severity prediction. METHOD: We first developed a CT segmentation network using datasets from multiple institutions worldwide. Two biomarkers were extracted from the CT images: total opacity ratio (TOR) and consolidation ratio (CR). After obtaining TOR and CR, further prognosis analysis was conducted on datasets from INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3. For each data cohort, generalized linear model (GLM) was applied for prognosis prediction. RESULTS: For the deep learning model, the correlation coefficient of the network prediction and manual segmentation was 0.755, 0.919, and 0.824 for the three cohorts, respectively. The AUC (95 % CI) of the final prognosis models was 0.85(0.77,0.92), 0.93(0.87,0.98), and 0.86(0.75,0.94) for INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3 cohorts, respectively. Either TOR or CR exist in all three final prognosis models. Age, white blood cell (WBC), and platelet (PLT) were chosen predictors in two cohorts. Oxygen saturation (SpO2) was a chosen predictor in one cohort. CONCLUSION: The developed deep learning method can segment lung infection regions. Prognosis results indicated that age, SpO2, CT biomarkers, PLT, and WBC were the most important prognostic predictors of COVID-19 in our prognosis model.

Deep metric learning-based image retrieval system for chest radiograph and its clinical applications in COVID-19.

In recent years, deep learning-based image analysis methods have been widely applied in computer-aided detection, diagnosis and prognosis, and has shown its value during the public health crisis of the novel coronavirus disease 2019 (COVID-19) pandemic. Chest radiograph (CXR) has been playing a crucial role in COVID-19 patient triaging, diagnosing and monitoring, particularly in the United States. Considering the mixed and unspecific signals in CXR, an image retrieval model of CXR that provides both similar images and associated clinical information can be more clinically meaningful than a direct image diagnostic model. In this work we develop a novel CXR image retrieval model based on deep metric learning. Unlike traditional diagnostic models which aim at learning the direct mapping from images to labels, the proposed model aims at learning the optimized embedding space of images, where images with the same labels and similar contents are pulled together. The proposed model utilizes multi-similarity loss with hard-mining sampling strategy and attention mechanism to learn the optimized embedding space, and provides similar images, the visualizations of disease-related attention maps and useful clinical information to assist clinical decisions. The model is trained and validated on an international multi-site COVID-19 dataset collected from 3 different sources. Experimental results of COVID-19 image retrieval and diagnosis tasks show that the proposed model can serve as a robust solution for CXR analysis and patient management for COVID-19. The model is also tested on its transferability on a different clinical decision support task for COVID-19, where the pre-trained model is applied to extract image features from a new dataset without any further training. The extracted features are then combined with COVID-19 patient's vitals, lab tests and medical histories to predict the possibility of airway intubation in 72 hours, which is strongly associated with patient prognosis, and is crucial for patient care and hospital resource planning. These results demonstrate our deep metric learning based image retrieval model is highly efficient in the CXR retrieval, diagnosis and prognosis, and thus has great clinical value for the treatment and management of COVID-19 patients.

Severity and Consolidation Quantification of COVID-19 From CT Images Using Deep Learning Based on Hybrid Weak Labels.

Early and accurate diagnosis of Coronavirus disease (COVID-19) is essential for patient isolation and contact tracing so that the spread of infection can be limited. Computed tomography (CT) can provide important information in COVID-19, especially for patients with moderate to severe disease as well as those with worsening cardiopulmonary status. As an automatic tool, deep learning methods can be utilized to perform semantic segmentation of affected lung regions, which is important to establish disease severity and prognosis prediction. Both the extent and type of pulmonary opacities help assess disease severity. However, manually pixel-level multi-class labelling is time-consuming, subjective, and non-quantitative. In this article, we proposed a hybrid weak label-based deep learning method that utilize both the manually annotated pulmonary opacities from COVID-19 pneumonia and the patient-level disease-type information available from the clinical report. A UNet was firstly trained with semantic labels to segment the total infected region. It was used to initialize another UNet, which was trained to segment the consolidations with patient-level information using the Expectation-Maximization (EM) algorithm. To demonstrate the performance of the proposed method, multi-institutional CT datasets from Iran, Italy, South Korea, and the United States were utilized. Results show that our proposed method can predict the infected regions as well as the consolidation regions with good correlation to human annotation.

Fibrosis-4 index as a predictor for mortality in hospitalised patients with COVID-19: a retrospective multicentre cohort study.

OBJECTIVE: The reliable risk factors for mortality of COVID-19 has not evaluated in well-characterised cohort. This study aimed to identify risk factors for in-hospital mortality within 56 days in patients with severe infection of COVID-19. DESIGN: Retrospective multicentre cohort study. SETTING: Five tertiary hospitals of Daegu, South Korea. PARTICIPANTS: 1005 participants over 19 years old confirmed COVID-19 using real-time PCR from nasopharyngeal and oropharyngeal swabs. METHODS: The clinical and laboratory features of patients with COVID-19 receiving respiratory support were analysed to ascertain the risk factors for mortality using the Cox proportional hazards regression model. The relationship between overall survival and risk factors was analysed using the Kaplan-Meier method. OUTCOME: In-hospital mortality for any reason within 56 days. RESULTS: Of the 1005 patients, 289 (28.8%) received respiratory support, and of these, 70 patients (24.2%) died. In multivariate analysis, high fibrosis-4 index (FIB-4; HR 2.784), low lymphocyte count (HR 0.480), diabetes (HR 1.917) and systemic inflammatory response syndrome (HR 1.714) were found to be independent risk factors for mortality in patients with COVID-19 receiving respiratory support (all p<0.05). Regardless of respiratory support, survival in the high FIB-4 group was significantly lower than in the low FIB-4 group (28.8 days vs 44.0 days, respectively, p<0.001). A number of risk factors were also significantly related to survival in patients with COVID-19 regardless of respiratory support (0-4 risk factors, 50.2 days; 49.7 days; 44.4 days; 32.0 days; 25.0 days, respectively, p<0.001). CONCLUSION: FIB-4 index is a useful predictive marker for mortality in patients with COVID-19 regardless of its severity.

Clinical outcomes of coronavirus disease 2019 in patients with pre-existing liver diseases: A multicenter study in South Korea.

BACKGROUND/AIMS: Although coronavirus disease 2019 (COVID-19) has spread rapidly worldwide, the implication of pre-existing liver disease on the outcome of COVID-19 remains unresolved.
. METHODS: A total of 1,005 patients who were admitted to five tertiary hospitals in South Korea with laboratory-confirmed COVID-19 were included in this study. Clinical outcomes in COVID-19 patients with coexisting liver disease as well as the predictors of disease severity and mortality of COVID-19 were assessed.
. RESULTS: Of the 47 patients (4.7%) who had liver-related comorbidities, 14 patients (1.4%) had liver cirrhosis. Liver cirrhosis was more common in COVID-19 patients with severe pneumonia than in those with non-severe pneumonia (4.5% vs. 0.9%, P=0.006). Compared to patients without liver cirrhosis, a higher proportion of patients with liver cirrhosis required oxygen therapy; were admitted to the intensive care unit; had septic shock, acute respiratory distress syndrome, or acute kidney injury; and died (P<0.05). The overall survival rate was significantly lower in patients with liver cirrhosis than in those without liver cirrhosis (log-rank test, P=0.003). Along with old age and diabetes, the presence of liver cirrhosis was found to be an independent predictor of severe disease (odds ratio, 4.52; 95% confidence interval [CI], 1.20-17.02;P=0.026) and death (hazard ratio, 2.86; 95% CI, 1.04-9.30; P=0.042) in COVID-19 patients.
. CONCLUSION: This study suggests liver cirrhosis is a significant risk factor for COVID-19. Stronger personal protection and more intensive treatment for COVID-19 are recommended in these patients.