Adults admitted to any of six ICUs from July 2016 to April 2017 at Brigham were analyzed for the study. Patients with provider-overridden CDS for dose, drug allergy, drug–drug interaction, geriatric and renal alerts were included.

Overall, a total of 2,448 override alerts were collected from 712 patient encounters. Results showed an 81.6 percent appropriateness rate for overrides. More ADEs followed inappropriate overrides compared to those that were appropriate. Inappropriate overrides were found to be linked to a six time increase in potential and definite ADEs when compared to appropriate overrides.

“Approximately four of five identified CDS overrides were appropriately overridden, though the rate varied substantially by alert type,” concluded first author Adrian Wong and colleagues. “Inappropriate overrides were six times as likely to be associated with an ADE (potential and definite) compared with appropriate overrides, confirming that decision support can identify clinically important situations. Further efforts should be targeted at improving the positive predictive value of CDS in a number of ways, including by following human factor principles in alert presentation, by suppressing alerts that are appropriately overridden, by using clinical information about individual patients to improve the likelihood that the alerts will be appropriate and by using techniques such as artificial intelligence to help determine which alerts to present.”