Novel data-mining methodologies for adverse drug event discovery and analysis

Abstract

An important goal of the health system is to identify new adverse drug events (ADEs) in the postapproval period. Datamining methods that can transform data into meaningful knowledge to inform patient safety have proven essential for this purpose. New opportunities have emerged to harness data sources that have not been used within the traditional framework. This article provides an overview of recent methodological innovations and data sources used to support ADE discovery and analysis.

Figure 1

PhV DMA research evolution described by volume of publications per year indexed in PubMed. 2011 volume is effectively larger due to delayed indexing.

Figure 2

Bar-plot of drugs statistically associated with rhabdomyolysis in AERS as an example of DPA output. Bar colors and length reflect statistical association strength based on the EBGM score. Each bar also includes the 90% confidence interval (EB05-EB95) and report count (N) for the corresponding drug. The plot and underlying DPA were performed using Oracle’s Empirica Signal 7.3 based on AERS data up to and including the year 2011 Q2. Only the top 20 associations consisting of drugs reported as “suspected” with N ≥ 100 were selected for display. Expectedly, the majority of drugs come from the class of statins known to cause rhabdomyolysis as a rare ADE.

Figure 3

Patient timelines used to visualize and analyze healthcare data in drug safety. Each patient is represented by a horizontal line capturing time, and symbols on the line represent clinical events, e.g., diagnoses, test results, treatments, and drug eras. The figure shows timelines of patients experiencing various events such as headache (red triangle) within eligible periods of acetaminophen administration. The patients are sorted according to the first occurrence of an event (red triangle).