Clinical decision support (CDS) tools help identify and reduce medication errors but are limited by the rules and types of errors programmed into their alerting logic and their high alerting rates and false positives, which can contribute to alert fatigue. This retrospective study evaluates the clinical validity and value of using a machine learning system (MedAware) for CDS as compared to an existing CDS system. Chart-reviewed MedAware alerts were accurate (92%) and clinically valid (79.7%). Overall, 68.2% of MedAware alerts would not have been generated by the CDS tool and estimated cost savings associated with the adverse events potentially prevented via MedAware alerts were substantial ($60/drug alert).

Misinterpretation of medication instructions can lead to medication administration errors and patient harm. Current computerized provider order entry for medications does not support best practices for medication instructions. This study describes an expert panel process to delineate how to include the indication—the reason for prescribing the medication—in the medication instructions. Experts recommend that prescribing begin with the indication for the medication, with decision support that promotes selection of the optimal medication. The authors emphasize the importance of a streamlined electronic prescribing process. A past PSNet perspective discussed integrating clinician decision support systems to improve medication safety.

This experimental study found that including the approved indication along with the generic name reduced medication errors associated with look-alike and sound-alike drug pairs. The authors advocate for incorporating this information into medication prescribing.

Clear communication during medication prescribing can enhance safety. This commentary advocates for indications-based prescribing coupled with health information technology as a way to improve team communication, medication reconciliation, and patient education and compliance.

Despite the growing use of technological approaches to reduce medication errors, such as automated dispensing systems, this study found that patients remain vulnerable to medication errors during scheduled and unscheduled system downtime.

This survey of pediatric pharmacists found only moderate satisfaction with existing computerized provider order entry (CPOE) systems, although respondents agreed that CPOE did reduce medication errors.

Medication errors may originate at each step of the prescribing process, and a prior study conducted in the inpatient setting demonstrated that nearly 4% of medication orders may be dispensed incorrectly. In this study, community pharmacists were surveyed regarding their perceptions of the frequency of dispensing errors and factors contributing to errors. Respondents felt that dispensing errors were relatively frequent and were more likely when pharmacists were overworked, a sentiment supported by prior research. Bar coding has been advocated as one means of potentially reducing drug dispensing errors.