Real-world comparison of counterfactual inference methods for evaluating impact of antidepressants on COVID outcomes
Kleper, S.; Habib, M.; Vashnav, A.; Ge, T.; Melamed, R. D.
Show abstract
In order to discover drugs that could be repurposed for a public health emergency like the COVID-19 pandemic, the National COVID Cohort Collaborative (N3C) database compiles health records including 22 millions individuals and 8.9 million cases of COVID-19. Here, we sought to use this data to systematically investigate whether antidepressants could impact COVID-19 outcomes, adjusting for known risk factors for severe outcome. We conducted large scale target trial emulation, comparing all pairs of 18 antidepressants to each other. Because the best approach for discovering such drug effects from observational data is not known, we applied a series of methods for identifying drug effects by estimating the counterfactual outcome that would be observed in a randomized trial. We found that all methods for counterfactual outcome estimation were prone to bias due to poorly controlled unmeasured confounding. We describe this bias, which appears to be induced partly by conditioning on treatment exposure, opening a back door path, via collider effects, between treatment and exposure via unmeasured confounders. Via empirical simulations, we show that our approach is able to detect this bias. In result, we state that we are not able to confidently identify any antidepressant impacting COVID-19 outcomes.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Alpha-1 blockers and susceptibility to COVID-19 in benign prostate hyperplasia patients : an international cohort study 93%
- Emulated Clinical Trials from Longitudinal Real-World Data Efficiently Identify Candidates for Neurological Disease Modification: Examples from Parkinson’s Disease 91%
- Near, far, wherever you are: Phenotype-related variation in pharmacogenomic effect sizes across the psychiatric drug literature. 90%
Similar papers in this journal
- Systematic analysis of electronic health records identifies drugs reducing risk of COVID-19 hospitalization and severity 91%
- Pathway activation model for personalized prediction of drug synergy 90%
- Dopamine enhances model-free credit assignment through boosting of retrospective model-based inference 90%
Similar papers in this journal
- Calcium Channel Blockers: clinical outcome associations with reported pharmacogenetics variants in 32,000 patients 91%
- People exposed to proton pump inhibitors shortly preceding COVID-19 diagnosis are not at an increased risk of subsequent hospitalizations and mortality: a nation-wide matched cohort study 91%
- Statin treatment effectiveness and the SLCO1B1 *5 reduced function genotype: long-term outcomes in women and men 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.