Type 2 diabetes and susceptibility to COVID-19: a machine learning analysis

Abstract

BackgroundType 2 diabetes mellitus (T2DM) was one of the most prevalent comorbidities among patients with coronavirus disease 2019 (COVID-19). Interactions between different metabolic parameters contribute to the susceptibility to the virus; thereby, this study aimed to rank the importance of clinical and laboratory variables as risk factors for COVID-19 or as protective factors against it by applying machine learning methods.MethodThis study is a retrospective cohort conducted at a single center, focusing on a population with T2DM. The patients attended the Yazd Diabetes Research Center in Yazd, Iran, from February 20, 2020, to October 21, 2020. Clinical and laboratory data were collected within three months before the onset of the COVID-19 pandemic in Iran. 59 patients were infected with COVID-19, while 59 were not. The dataset was split into 70% training and 30% test sets. Principal Component Analysis (PCA) was applied to the data. The most important components were selected using a ‘sequential feature selector’ and scored by a Linear Discriminant Analysis model. PCA loadings were then multiplied by the PCs’ scores to determine the importance of the original variables in contracting COVID-19.ResultsHDL-C, followed by eGFR, showed a strong negative correlation with the risk of contracting the virus. Higher levels of HDL-C and eGFR offer protection against COVID-19 in the T2DM population. But, the ratio of BUN to creatinine did not show any correlation. Conversely, the AIP, TyG index and TG showed the most positive correlation with susceptibility to COVID-19 in such a way that higher levels of these factors increase the risk of contracting the virus. The positive correlation of diastolic BP, TyG-BMI index, MAP, BMI, weight, TC, FPG, HbA1C, Cr, systolic BP, BUN, and LDL-C with the risk of COVID-19 decreased, respectively.ConclusionThe atherogenic index of plasma, triglyceride glucose index, and triglyceride levels are the most significant risk factors for COVID-19 contracting in individuals with T2DM. Meanwhile, high-density lipoprotein cholesterol is the most protective factor.