Activity recognition for emergency care using RFID

We present a system that recognizes human activities during trauma resuscitation, the fast-paced and team-based initial management of injured patients in the emergency department. Most objects used in trauma resuscitation are uniquely associated with tasks. To detect object use, we employed passive radio frequency identification (RFID) for their size and cost advantages. We designed the system setup to ensure the effectiveness of passive tags in such a complex setting, which includes various objects and significant human motion. Through our studies conducted at a Level 1 trauma center, we learned that objects used in trauma resuscitation need to be tagged differently because of their size, shape, and material composition. Based on this insight, we classified the medical items into groups based on usage and other characteristics. Objects in different groups are tagged differently and their data is processed differently. We applied machine-learning algorithms to identify object-state changes and process the RFID data using algorithms specific to object groups. Our results show that RFID has significant potential for automatic detection of object usage in complex and fast-paced settings.