Researchers have recently assessed the specificity of an algorithm to detect look-alike/sound-alike (LASA) medication prescribing errors in electronic health record (EHR) data: data derived from eight years of medication orders and diagnostic claims were analysed. The approach involved the use of a database of medication indications applied over the medication data, and development of an algorithm that identified LASA errors based on name similarity, the frequency with which a patient received a medication and whether the medication was justified by diagnosis. 2404 triggers were generated from 488 481 orders, (0.5% error rate). Clinicians reviewed 506 cases and confirmed the presence of 61 errors (positive predictive value of 12.1%, 95% CI 10.7% to 13.5%). The methodology did not allow for measurement of sensitivity or the false-negative rate. The specificity of the algorithm varied, depending upon name similarity and whether the intended and dispensed drugs shared the same route of administration. The authors comment that a lack of accurate diagnostic information hampers the clinical utility of this type of approach, but there is potential for this kind of system to facilitate real time detection of errors. The study, published in BMJ Safety and Quality, can be read here.