Prediction Models for the Clinical Severity of Patients With COVID-19 in Korea: Retrospective Multicenter Cohort Study.

BACKGROUND: Limited information is available about the present characteristics and dynamic clinical changes that occur in patients with COVID-19 during the early phase of the illness. OBJECTIVE: This study aimed to develop and validate machine learning models based on clinical features to assess the risk of severe disease and triage for COVID-19 patients upon hospital admission. METHODS: This retrospective multicenter cohort study included patients with COVID-19 who were released from quarantine until April 30, 2020, in Korea. A total of 5628 patients were included in the training and testing cohorts to train and validate the models that predict clinical severity and the duration of hospitalization, and the clinical severity score was defined at four levels: mild, moderate, severe, and critical. RESULTS: Out of a total of 5601 patients, 4455 (79.5%), 330 (5.9%), 512 (9.1%), and 301 (5.4%) were included in the mild, moderate, severe, and critical levels, respectively. As risk factors for predicting critical patients, we selected older age, shortness of breath, a high white blood cell count, low hemoglobin levels, a low lymphocyte count, and a low platelet count. We developed 3 prediction models to classify clinical severity levels. For example, the prediction model with 6 variables yielded a predictive power of >0.93 for the area under the receiver operating characteristic curve. We developed a web-based nomogram, using these models. CONCLUSIONS: Our prediction models, along with the web-based nomogram, are expected to be useful for the assessment of the onset of severe and critical illness among patients with COVID-19 and triage patients upon hospital admission.

Integrative Pathway Analysis of SNP and Metabolite Data Using a Hierarchical Structural Component Model.

Integrative multi-omics analysis has become a useful tool to understand molecular mechanisms and drug discovery for treatment. Especially, the couplings of genetics to metabolomics have been performed to identify the associations between SNP and metabolite. However, while the importance of integrative pathway analysis is increasing, there are few approaches to utilize pathway information to analyze phenotypes using SNP and metabolite. We propose an integrative pathway analysis of SNP and metabolite data using a hierarchical structural component model considering the structural relationships of SNPs, metabolites, pathways, and phenotypes. The proposed method utilizes genome-wide association studies on metabolites and constructs the genetic risk scores for metabolites referred to as genetic metabolomic scores. It is based on the hierarchical model using the genetic metabolomic scores and pathways. Furthermore, this method adopts a ridge penalty to consider the correlations between genetic metabolomic scores and between pathways. We apply our method to the SNP and metabolite data from the Korean population to identify pathways associated with type 2 diabetes (T2D). Through this application, we identified well-known pathways associated with T2D, demonstrating that this method adds biological insights into disease-related pathways using genetic predispositions of metabolites.