JMIR Publications

ABSTRACT

Background:

Antidepressants are a type of medication used to treat clinical depression or prevent it recurring. Antidepressants exert an anticholinergic effect in varying degrees and various classes of antidepressants also can produce a different effect on immune function. While early usage of antidepressants has notional role on COVID-19 outcomes, the relationship between the risk of COVID-19 severity and the use of all kind of antidepressants is not properly investigated before due to the exceeding cost involved with clinical trials. Large-scale observational data such as electronic health records and recent advancement of statistical analysis provide ample opportunity to virtualize clinical trial to discover detrimental effects of early usage of these drugs.

Objective:

By mining a large-scale electronic health record data set of COVID-19 positive patients, we aim to identify common drugs that are associated with COVID-19 outcome. However, whereas the statisticians have made great progress toward using such rich association estimation methods for risk estimation, precision medicine requires causal models. Thus our central aim of this paper lies on investigating electronic health record analytic for causal effect estimation and utilize that in discovering causal effects of early antidepressants use on COVID-19 outcomes. As a secondary aim, we develop methods for validating our causal effect estimation pipeline.

Methods:

We focus on antidepressants, a commonly used category of drugs that have been linked to unexpected effects on diverse inflammatory and cardiovascular outcomes, and infer early use of such drug use effects on COVID-19 outcomes. However, whereas the machine learning and statistics community have made great progress toward using rich inference models, precision medicine requires causal models, for which there is significantly less theoretical and practical guidance available. We used National COVID Cohort Collaborative (N3C), a database aggregating health history for over 12+ million people in the USA, including 3+ million with a positive COVID-19 test. We selected 241,952 COVID-19 positive patients with at least one year of medical history and age>13 that included 18,584-dimensional covariate vector for each person and 16 different antidepressants usage histories. We used propensity score weighting based on logistic regression method to estimate causal effect on whole data. Then we used Node2Vec embedding method to encode SNOMED medical code and apply random forest regression to estimate causal effect. We use both of the methods to estimate causal effects of antidepressants on COVID-19 outcome. We also selected few negatively effective conditions on COVID-19 outcomes and estimated their effects using our proposed methods to validate their efficacy.

Results:

Average Treatment Effect (ATE) of using any one of the antidepressants is -0.076 with 95% CI from -0.082 to - 0.069 with propensity score weighting method. The result is statistically significant at p<0.0001. In case of the method using SNOMED medical embedding, the ATE of using any one of the antidepressants is -0.423 with 95% CI from -0.382 to -0.463. This result is also statistically significant at p<0.0001.

Conclusions:

In this study, we apply multiple causal inference methods incorporating with a novel application of health embeddings to investigate the effects of antidepressants on COVID-19 outcome. Additionally, we propose a novel non-affecting drug effect analysis-based evaluation technique to justify the efficacy of proposed method. This study offers causal inference methods on large-scale EHR data to discover common antidepressants’ effects on COVID-19 hospitalization, or a worse outcome. The study finds that common antidepressants may increase risk of COVID-19 complications and uncovers a pattern where certain antidepressants are associated with lower risk of hospitalization. While discovering detrimental effects of these drugs on outcome could guide preventive care, identification of beneficial effects would allow us to propose drug repurposing for COVID-19 treatment.