Inappropriate prescribing predicts adverse drug events in older adults

Abstract

Background: Explicit measures of potentially inappropriate prescribing, such as the Beers criteria, have been associated with risk for adverse drug events (ADEs). However, no such link has been established for actual inappropriate prescribing using implicit measures.

Objective: To determine whether an implicit measure of inappropriate prescribing can predict ADE risk.

Methods: Patients were veterans aged 65 years and older who were seen in primary care clinics and participated in a randomized controlled trial of a pharmacist-physician collaborative intervention. Inappropriate prescribing was determined at baseline, using the 2003 Beers criteria as an explicit measure and the Medication Appropriateness Index (MAI) as an implicit measure. A modified MAI scoring approach was designed to target ADE risk and was used in addition to standard scoring. ADEs that occurred during the 3 months following baseline were assessed by patient interview and plausibility verification by blinded pharmacist review. Logistic regression analysis was used to determine whether inappropriate prescribing predicted risk for an ADE, controlling for potential confounding factors.

Results: Of 236 patients, 34 (14.4%) experienced an ADE. Inappropriate prescribing was common at baseline, with 48.7% of patients receiving a Beers criteria drug and 98.7% of patients having an inappropriate rating on at least 1 MAI criterion. Modified MAI scoring, but not other measures of inappropriate prescribing, significantly predicted ADE risk. For every unit increase in modified MAI score (3.1 +/- 3.5; mean +/- SD), the adjusted 3-month odds of an ADE increased 13% (OR 1.13; 95% CI 1.02 to 1.26). For example, patients with a modified MAI score of 3, near the precise mean score of 3.1, were at a nearly 40% greater risk for an ADE compared with patients with a score of zero.

Conclusions: Implicit measurement of actual inappropriate prescribing predicted ADE risk, an important clinical outcome. This finding helps confirm the validity of prior studies that have relied on explicit measures to link potentially inappropriate prescribing to adverse health outcomes.