Cardiometabolic risks of SARS-CoV-2 hospitalization using Mendelian Randomization

Abstract

Many cardiometabolic conditions have demonstrated associative evidence with COVID-19 hospitalization risk. However, the observational designs of the studies in which these associations are observed preclude causal inferences of hospitalization risk. Mendelian Randomization (MR) is an alternative risk estimation method more robust to these limitations that allows for causal inferences. We applied four MR methods (MRMix, IMRP, IVW, MREgger) to publicly available GWAS summary statistics from European (COVID-19 GWAS n = 2956) and multi-ethnic populations (COVID-19 GWAS n = 10,908) to better understand extant causal associations between Type II Diabetes (GWAS n = 659,316), BMI (n = 681,275), diastolic and systolic blood pressure, and pulse pressure (n = 757,601 for each) and COVID-19 hospitalization risk across populations. Although no significant causal effect evidence was observed, our data suggested a trend of increasing hospitalization risk for Type II diabetes (IMRP OR, 95% CI 1.67, 0.96-2.92) and pulse pressure (OR, 95% CI 1.27, 0.97-1.66) in the multi-ethnic sample. Type II diabetes and Pulse pressure demonstrates a potential causal association with COVID-19 hospitalization risk, the proper treatment of which may work to reduce the risk of a severe COVID-19 illness requiring hospitalization. However, GWAS of COVID-19 with large sample size is warranted to confirm the causality.

Figure 1

Exposure, COVID-19 Effect size associations—mixed ethnicity sample. These figures display the effect size associations between each exposure (Type II Diabetes, BMI, diastolic and systolic blood pressure, and pulse pressure) and COVID-19 hospitalization risk. Overlaid on the scatterplots are univariate linear regression fitted values and their associated 95% confidence intervals.

Figure 2

IMRP Pleitropy evidence—mixed ethnicity sample. Displayed are those SNPs demonstrating evidence of pleiotropic effects for pulse pressure and Type II Diabetes in the multi-ethnicity sample as estimated by IMRP. The horizontal dash line represents Bonferroni-adjusted Type I Error rate of p = 0.05.

Figure 3

MRMix estimation performance—mixed ethnicity sample. These two plots display the estimated causal effect (theta, $\widehat{\mathrm{\theta }}$) during maximum likelihood estimation for diastolic and systolic blood pressure by MRMix in the multi-ethnicity sample. A clear, sharp peak indicates stable performance in the estimation of theta. The dotted red lines indicate the ML estimates of theta ($\mathrm{\theta }$) reported in the Results section, respectively for each exposure.