Drug-related errors are a leading cause of preventable patient harm in the clinical setting, with up to 12% of these errors resulting in serious harm or death. There is a need for automating medication checks in real-time prior to administration that fits into the current clinical environment.
We present the first wearable camera system using deep learning algorithms to automatically detect potential errors, prior to medication delivery. The video system does not directly read the wording on each vial, but scans for other visual cues: vial and syringe size and shape, vial cap color, label print size.
Our dataset was collected from February 2021 to July 2023 across two clinical sites at the University of Washington. Our dataset contains video footage of 13 anesthesiology providers, and 17 operating locations over 55 days.
The system was evaluated on 418 drug draw events in routine patient care and a controlled environment and achieved 99.6% sensitivity and 98.8% specificity at detecting vial swap errors.
These results suggest that our wearable camera system has the potential to provide a secondary check when a medication is selected for a patient, and a chance to intervene before a potential medical error.
【MORE】