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

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.

[1]  Jie Chen,et al.  Mining Unexpected Associations for Signalling Potential Adverse Drug Reactions from Administrative Health Databases , 2006, PAKDD.

[2]  W. Bilker,et al.  The relationship between time since registration and measured incidence rates in the General Practice Research Database , 2005, Pharmacoepidemiology and drug safety.

[3]  W. Bilker,et al.  Validation studies of the health improvement network (THIN) database for pharmacoepidemiology research , 2007, Pharmacoepidemiology and drug safety.

[4]  Kurt Hornik,et al.  Introduction to arules – A computational environment for mining association rules and frequent item sets , 2009 .

[5]  Das Amrita,et al.  Mining Association Rules between Sets of Items in Large Databases , 2013 .

[6]  W. Amery.  Why there is a need for pharmacovigilance , 1999, Pharmacoepidemiology and drug safety.

[7]  Uwe Aickelin,et al.  Signalling Paediatric Side Effects using an Ensemble of Simple Study Designs , 2014, Drug Safety.

[8]  D. Madigan,et al.  Empirical assessment of methods for risk identification in healthcare data: results from the experiments of the Observational Medical Outcomes Partnership , 2012, Statistics in medicine.

[9]  Uwe Aickelin,et al.  Comparison of algorithms that detect drug side effects using electronic healthcare databases , 2013, Soft Comput..

[10]  G. Niklas Norén,et al.  Temporal pattern discovery in longitudinal electronic patient records , 2010, Data Mining and Knowledge Discovery.

[11]  A. B. Prasad,et al.  British National Formulary , 1994 .

[12]  C. Friedman,et al.  Detection of Pharmacovigilance‐Related Adverse Events Using Electronic Health Records and Automated Methods , 2012, Clinical pharmacology and therapeutics.

[13]  A. Wilson.  The British National Formulary. , 1963, The Practitioner.

[14]  D Madigan,et al.  Logistic Regression in Signal Detection: Another Piece Added to the Puzzle , 2013, Clinical pharmacology and therapeutics.