Automated detection of look-alike/sound-alike medication errors

Abstract

Purpose: The development and evaluation of an algorithm for detecting potential medication errors due to look-alike/sound-alike (LASA) drug names are described.

Summary: A computer algorithm that detects potential LASA errors by analyzing medication orders and diagnostic claims data was developed. The algorithm flags a potential error when (1) a medication order is not justified by a diagnosis documented in the patient's record, (2) another medication whose orthographic similarity to the index drug exceeds a specified threshold exists, and (3) the latter drug has an indication that matches an active documented diagnosis. A review of medication orders and diagnostic claims at a large health system identified cases in which cycloserine was ordered but cyclosporine was the intended treatment. Subsequent review of all cycloserine orders over a 7-year period indicated that 11 of 16 orders were erroneous, prompting placement of an alert regarding the potential for LASA errors involving cycloserine and cyclosporine in the electronic order-entry system. Automated detection and confirmation of LASA errors via chart review can be used retrospectively to identify problematic pairs of drug names and to assess associated error rates within a healthcare system. The same techniques can be used to prevent errors in real time through indication alerts if accurate diagnostic information is available at the time of order entry.

Conclusion: Automated methods involving the use of medication orders, diagnostic claims, and indications can be used to detect and prevent LASA errors.

Keywords: Systematized Nomenclature of Medicine; cycloserine; cyclosporine; electronic prescribing; medication errors; patient harm.