Using computable knowledge mined from the literature to elucidate confounders for EHR-based pharmacovigilance

Abstract

<jats:p>Introduction: Confounding bias threatens the reliability of observational studies and poses a significant scientific challenge. This paper introduces a framework for identifying confounding factors by exploiting literature-derived computable knowledge. In previous work, we have shown that semantic constraint search over computable knowledge extracted from the literature can be useful for reducing confounding bias in statistical models of EHR-derived observational clinical data. We hypothesize that adjustment sets of literature-derived confounders could also improve causal inference. Methods: We introduce two methods (semantic vectors and string-based confounder search) that query the literature for potential confounders and use this information to build models from EHR-derived data to more accurately estimate causal effects. These methods search SemMedDB for indications TREATED BY the drug that is also known to CAUSE the adverse event. For evaluation, we attempt to rediscover associations in a publicly available reference dataset containing expected pairwise relationships between drugs and adverse events from empirical data derived from a corpus of 2.2M EHR-derived clinical notes. For our knowledge-base, we use SemMedDB, a database of computable knowledge mined from the biomedical literature. Using standard adjustment and causal inference procedures on dichotomous drug exposures, confounders, and adverse event outcomes, varying numbers of literature-derived confounders are combined with EHR data to predict and estimate causal effects in light of the literature-derived confounders. We then compare the performance of the new methods with naive ($\chi^2$, reporting odds ratio) measures of association. Results and Conclusions: Logistic regression with ten vector space-derived confounders achieved the most improvement with AUROC of 0.628 (95\% CI: [0.556,0.720]), compared with baseline $\chi^2$ 0.507 (95\% CI: [0.431,0.583]). Bias reduction was improved more often in modeling methods using more rather than less information, and using semantic vector rather than string-based search. We found computable knowledge useful for improving automated causal inference, and identified opportunities for further improvement, including a role for adjudicating literature-derived confounders by subject matter experts.</jats:p>

Causal feature selection using a knowledge graph combining structured knowledge from the biomedical literature and ontologies: a use case studying depression as a risk factor for Alzheimer's disease

“…More recently, new applications for discovery patterns have been identified, and methods have been developed to infer discovery patterns automatically 163,164 . Discovery patterns can be and have been implemented in any query or knowledge representation language that considers how concepts relate to one another, including SPARQL 165 , SQL 166 , and advanced methods for querying distributed semantic representations 63,157,167,168 of structured knowledge.…”