A novel framework for assessing causal effect of microbiome on health: long-term antibiotic usage as an instrument

Abstract

Assessing causality is undoubtedly one of the key questions in microbiome studies for the upcoming years. Since randomized trials in human subjects are often unethical or difficult to pursue, analytical methods to derive causal effects from observational data deserve attention. As simple covariate adjustment is not likely to account for all potential confounders, the idea of instrumental variable (IV) analysis is worth exploiting. Here we propose a novel framework of antibiotic instrumental variable regression (AB-IVR) for estimating the causal relationships between microbiome and various diseases. We rely on the recent studies showing that antibiotic treatment has a cumulative long-term effect on the microbiome, resulting in individuals with higher antibiotic usage to have a more perturbed microbiome. We apply the AB-IVR method on the Estonian Biobank data and show that the microbiome has a causal role in numerous diseases including migraine, depression and irritable bowel syndrome. We show with a plethora of sensitivity analyses that the identified causal effects are robust and propose ways for further methodological developments.

Keywords: antibiotics; causal inference; electronic health registries; gut microbiome.

Figure 1.

Graphical description of the study design. Upper panel (a) illustrates the instrumental variable regression and corresponding assumptions schematically in the context of our study. hAB - history of antibiotic usage; MB - microbiome; D - disease; C - confounder. Lower panel (b) illustrates the samples and data used. Sample 1 refers to the sample where disease follow-up data is recorded, EstBB in our case. Sample 2 refers to the sample where the microbiome is assessed, EstMB in our case. We recorded the AB usage as the number of AB prescribed (total and AB subgroups) during the 10-year period preceding the start of follow up in sample 1 and microbiome sampling in sample 2, whereas in both samples the individuals receiving AB during the last 6 months of the aforementioned period are excluded. Sample 1 was followed up for incident outcomes of 56 common diseases from 01.01.2015 until 31.12.2022, whereafter observations are right censored irrespective of the future outcomes. In sample 2 the microbiome was assessed on an arbitrary moment between November 2017 to July 2020. The causal effect of MB on disease (${\beta }_{\mathit{D},\mathit{MB}}$) in the two-sample setting is estimated as the ratio of the effect of ab-usage on disease (${\beta }_{\mathit{D},\mathit{hAB}}$) in Sample1 (EstBB) and the effect of ab-usage on MB (${\beta }_{\mathit{MB},\mathit{hAB}}$) in Sample2 (EstMB).

Figure 2.

Antibiotic usage in the EstMB cohort. Panel a shows the association between the number of different antibiotics used during the last 10 years before the sample collection and prevotella-bacteroides ratio. The total AB usage and usage of all AB subclasses were strongly associated with prevotella/bacteroides ratio (combined AB usage p = 2.04e-8, macrolides p = 0.0192, fluoroquinolones p = 3.03e-5, and penicillins p = 0.0026). Panel B shows the Spearman correlation between the number of different antibiotics classes used during the last 10 years before the sample collection. Panel C shows the unique and shared hits of the univariate analyses associating the antibiotics usage history with the abundance of microbial species. Panel D shows the proportion of cohort participants by the number of antibiotics used during the past 10 years.

Figure 3.

Results of the main AB-IVR analysis (a) and sensitivity analyses (b,c). On panels A,B, and C the causal effect estimate of Prevotella/Bacteroides ratio on a selection of diseases is presented (full results comprising all diseases analysed can be viewed in supplementary tables S1, S3-S5, and S6-S8). In panel a the age is filtered as 23–50, maximum number of AB prescribed is five, and minimum number of cases per disease is 50. Panel B represents the sensitivity analyses where sample formation varies, whereas the main analysis is depicted for comparison in red. Green shows the effect estimates, when age is filtered as 23–89; light-purple shows the effect estimates, when the maximum number of AB prescribed is 10; dark-purple describes the scenario where the first five years of incidence after the start of follow-up is considered as prevalent disease. Panel C represents the sensitivity analyses where information regarding subclasses of AB were used instead of the total amount of AB prescribed, whereas other settings were identical to the main analysis. Red corresponds to the main analysis (same as A), dark blue corresponds to the class of penicillins (J01CR), light-blue corresponds to the class of macrolides (J01FA) and light-green corresponds to the class of fluoroquinolones (J01MA).