Heterogeneous Causal Effect of Polysubstance Usage on Drug Overdose (Preprint)

BACKGROUND Drug overdose has become a public health crisis in United States with devastating consequences. However, most of the drug overdose incidences are the consequence of recitative polysubstance usage over a defined period of time which can be happened by either the intentional usage of required drug with other drugs or by accident. Thus, predicting the effects of polysubstance usage is extremely important for clinicians to decide which combination of drugs should be prescribed. Although, machine learning community has made great progress toward using such rich models for supervised prediction, precision medicine problem such as polysubstance usage effects on drug overdose requires heterogeneous causal models, for which there is significantly less theoretical and practical guidance available. Recent advancement of structural causal models can provide ample insights of causal effects from observational data via identifiable causal directed graphs. OBJECTIVE Develop a system to identify heterogeneous causal effect of polysubstance usage from large electronic health record data METHODS We propose a system to estimate heterogeneous concurrent drug usage effects on overdose estimation, that consists of efficient co-variate selection, subgroup selection, generation of and heterogeneous causal effect estimation. Although, there has been several association studies have been proposed in the state-of-art methods, heterogeneous causal effects have never been studied in concurrent drug usage and drug overdose problem. We apply our framework to answer a critical question, ”can concurrent usage of benzodiazepines and opioids has heterogeneous causal effects on opioid overdose epidemic?” RESULTS Using Truven MarketScan claim data collected from 2001 to 2013 have shown significant promise of our proposed framework’s efficacy. Our efficient causal inference model estimated that the causal effect is higher (19%) than the regression studies (15%) to estimate the risks associated with the concurrent usage of opioid and benzodiazepines on opioid overdose. CONCLUSIONS Our generic framework can be a foundation of investigating concurrent events’ causal effects on any outcome that involves heterogeneity