ABSTRACT
This study aimed to build an machine learning based model to predict the COVID-19 severity and reveal risk factors related to COVID-19 severity based on laboratory testing and clinical data for 420 participants, using tree-based models such as XGBoost, LightGBM, random forest. We calculated the Odds Ratios (OR) to investigate whether the top-ranked features were statistically significant for severity classification, turning out that high sensitivity C-reactive protein (hs-CRP) was the most important feature for determining of COVID-19 severity and XGBoost model showed the highest performance in classifying COVID-19 severity and healthy controls with F1score (0.84) and AUC (0.87). We expect that our results are of considerable significance for early screening for diagnosing COVID-19 severity, which, in turn, assist in further retrospective research for uncommon infectious diseases. © 2023 IEEE.
ABSTRACT
Recent advances in single-cell RNA sequencing (scRNA-seq) technology have enabled the acquisition of RNA at the single-cell level, which showed that the expression level of genes is highly variable across and within the cell types. Even well-known housekeeping genes showed high expression variance in a single condition and within the same cell types. Previous studies made efforts to identify stably expressed genes and use them as a yardstick for robust gene expression normalization. On the other hand, drugs were shown to be less effective on genes with high expression variance. Thus, identifying both stably and variably expressed genes is an important task, especially at the single-cell level. In this study, using the Kullback-Leibler divergence method, we proposed a metric to measure the expression stability of each gene. Using private scRNA-seq data composed of 25 severe COVID-19 patients and 40 healthy individuals, we identified variably expressed genes specific to COVID-19-infected patients and healthy cohorts. © 2022 IEEE.