Improving alert acceptance with context specific drug-drug interaction screening

Background and Objective Clinical decision support systems (CDSS) have the potential to reduce unwanted DDIs but often result in alert fatigue. The objective of this study was to investigate whether a newly developed context-specific DDI alerting system would improve alert acceptance. Setting and Method This was a controlled pre-post intervention study conducted at the UZ Brussel hospital in Brussels, Belgium. The intervention was the implementation of a new context-specific DDI alerting system for physicians. Intervention cases consisted of all patients admitted to the 29-bed acute geriatric and 21-bed infectiology department. The control cases consisted of all patients admitted to the 29-bed cardiology and 29-bed neurology department. After a 7-month pre-intervention period, the new system was activated in the intervention departments, while the old system remained activated in the control departments. Post-intervention data was collected for a 7-month period. The new CDSS included a follow-up system for real-time evaluation of the alerts by a clinical pharmacist. Main outcome measures Alert acceptance rate of the new versus the old system. Results A significant increase of the overall acceptance rate was observed between the pre- and post-intervention period (2.2% versus 52.4%; p < 0.001) for the intervention departments and between the control and intervention departments (2.5% versus 52.4%; p < 0.001) in the post-intervention period. There were no significant differences in acceptance rates between the pre- and post-intervention period in the control departments and also not between the control and intervention departments in the pre-intervention period. Based on the real-time evaluation of the alerts and override reasons of the new system, the clinical pharmacist conducted 10 interventions for 10 overridden alerts. Conclusions The improvement was probably related to several optimization strategies including the customization of the severity classification, the creation of individual screening intervals, the inclusion of context factors for risk assessment, the new alert design and the creation of a follow-up system. System aspects that require further optimization were identified and will be developed. Further research is warranted to develop context-aware algorithms for complex class-class interactions. The follow-up of alerts by a clinical pharmacist seems important because interventions were conducted for high risk situations.