Prediction of COVID-19 Severity Using Chest Computed Tomography and Laboratory Measurements: Evaluation Using a Machine Learning Approach.

BACKGROUND: Most of the mortality resulting from COVID-19 has been associated with severe disease. Effective treatment of severe cases remains a challenge due to the lack of early detection of the infection. OBJECTIVE: This study aimed to develop an effective prediction model for COVID-19 severity by combining radiological outcome with clinical biochemical indexes. METHODS: A total of 46 patients with COVID-19 (10 severe, 36 nonsevere) were examined. To build the prediction model, a set of 27 severe and 151 nonsevere clinical laboratory records and computerized tomography (CT) records were collected from these patients. We managed to extract specific features from the patients' CT images by using a recently published convolutional neural network. We also trained a machine learning model combining these features with clinical laboratory results. RESULTS: We present a prediction model combining patients' radiological outcomes with their clinical biochemical indexes to identify severe COVID-19 cases. The prediction model yielded a cross-validated area under the receiver operating characteristic (AUROC) score of 0.93 and an F1 score of 0.89, which showed a 6% and 15% improvement, respectively, compared to the models based on laboratory test features only. In addition, we developed a statistical model for forecasting COVID-19 severity based on the results of patients' laboratory tests performed before they were classified as severe cases; this model yielded an AUROC score of 0.81. CONCLUSIONS: To our knowledge, this is the first report predicting the clinical progression of COVID-19, as well as forecasting severity, based on a combined analysis using laboratory tests and CT images.

Single Cell RNA-seq Data Analysis Reveals the Potential Risk of SARS-CoV-2 Infection Among Different Respiratory System Conditions.

COVID-19 (Coronavirus Disease 2019) has been an ongoing pandemic, resulting in an increase in people being infected globally. Understanding the potential risk of infection for people under different respiratory system conditions is important and will help prevent disease spreading. We explored and collected five published and one unpublished single-cell respiratory system tissue transcriptome datasets, including idiopathic pulmonary fibrosis (IPF), aging lungs (mouse origin data), lung cancers, and smoked branchial epithelium, for specifically reanalyzing the ACE2 and TMPRSS2 expression profiles. Compared to normal people, we found that smoking and lung cancer increase the risk for COVID-19 infection due to a higher expression of ACE2 and TMPRSS2 in lung cells. Aged lung does not show increased risk for infection. IPF patients may have a lower risk for original COVID-19 infection due to lower expression in AT2 cells but may have a higher risk for severity due to a broader expression spectrum of TMPRSS2. Further investigation and validation on these cell types are required. Nonetheless, this is the first report to predict the risk and potential severity for COVID-19 infection for people with different respiratory system conditions. Our analysis is the first systematic description and analysis to illustrate how the underlying respiratory system conditions contribute to a higher infection risk.