Pilot evaluation of a method to assess prescribers' information processing of medication alerts

- This method was feasible to evaluate users' information processing of alerts.
- This method detected significant differences between two alert displays.
- The study method may be useful for other health information technology displays.

BackgroundPrescribers commonly receive alerts during medication ordering. Prescribers work in a complex, time-pressured environment; to enhance the effectiveness of safety alerts, the effort needed to cognitively process these alerts should be minimized. Methods to evaluate the extent to which computerized alerts support prescribers' information processing are lacking.ObjectiveTo develop a methodological protocol to assess the extent to which alerts support prescribers' information processing at-a-glance; specifically, the incorporation of information into their working memory. We hypothesized that the method would be feasible and that we would be able to detect a significant difference in prescribers' information processing with a revised alert display that incorporates warning design guidelines compared to the original alert display.MethodsA counterbalanced, within-subject study was conducted with 20 prescribers in a human-computer interaction laboratory. We tested a single alert that was displayed in two different ways. Prescribers were informed that an alert would appear for 10 s. After the alert was shown, a white screen was displayed, and prescribers were asked to verbally describe what they saw; indicate how many total warnings; and describe anything else they remembered about the alert. We measured information processing via the accuracy of prescribers' free recall and their ability to identify that three warning messages were present. Two analysts independently evaluated participants' responses against a comprehensive catalog of alert elements and then discussed discrepancies until reaching consensus.ResultsThis feasibility study demonstrated that the method seemed to be effective for evaluating prescribers' information processing of medication alert displays. With this method, we were able to detect significant differences in prescribers' recall of alert information. The proportion of total data elements that prescribers were able to accurately recall was significantly greater for the revised versus original alert display (p = 0.006). With the revised display, more prescribers accurately reported that three warnings were shown (p = 0.002).ConclusionsThe methodological protocol was feasible for evaluating the alert display and yielded important findings on prescribers' information processing. Study methods supplement traditional usability evaluation methods and may be useful for evaluating information processing of other healthcare technologies.

170