Refining Adverse Drug Reactions using Association Rule Mining for Electronic Healthcare Data

TL;DR

This paper introduces a novel method using association rule mining to refine adverse drug reaction signals in electronic healthcare data by reducing confounding effects and providing a more accurate risk measure.

Contribution

It proposes a new approach that automatically filters likely confounded side effect signals and calculates a confounding-adjusted risk value, improving signal accuracy.

Findings

Successfully filtered most unlikely true side effect signals

The method shows promise in refining adverse drug reaction detection

Potential for further improvement with parameter tuning

Abstract

Side effects of prescribed medications are a common occurrence. Electronic healthcare databases present the opportunity to identify new side effects efficiently but currently the methods are limited due to confounding (i.e. when an association between two variables is identified due to them both being associated to a third variable). In this paper we propose a proof of concept method that learns common associations and uses this knowledge to automatically refine side effect signals (i.e. exposure-outcome associations) by removing instances of the exposure-outcome associations that are caused by confounding. This leaves the signal instances that are most likely to correspond to true side effect occurrences. We then calculate a novel measure termed the confounding-adjusted risk value, a more accurate absolute risk value of a patient experiencing the outcome within 60 days of the exposure. Tentative results suggest that the method works. For the four signals (i.e. exposure-outcome associations) investigated we are able to correctly filter the majority of exposure-outcome instances that were unlikely to correspond to true side effects. The method is likely to improve when tuning the association rule mining parameters for specific health outcomes. This paper shows that it may be possible to filter signals at a patient level based on association rules learned from considering patients' medical histories. However, additional work is required to develop a way to automate the tuning of the method's parameters.