Falls in the hospital rooms are considered a huge burden on healthcare costs. They can lead to injuries, extended length of stay, and increase in cost for both the patients and the hospital. It can also lead to emotional trauma for the patients and their families . Having Microsoft Kinects installed in the hospital rooms to capture and process every movement in the room, we deployed our previously developed fall-detection system to detect naturally occurring falls, generate a real-time fall alarm and broadcast it to hospital nurses for immediate intervention. These systems also store a processed and reduced version of the 3D depth videos on a central file storage to provide information to the dedicated nursing team for post-fall quality improvement process. The compression technique that helps reducing video size by omitting non-movement frames from it also makes it almost impossible for the hospital staff to find the event that led to a fall alarm. There was a need to visualize fall events and the video contents accordingly. In this paper, we describe a web-application with a handy user interface to easily search among terabytes of depth videos to facilitate the finding and reviewing of the chain of events that lead to a patient fall. We will also discuss the improvements in the new version of the application which reduced the size of transferred videos by converting them to MP4 videos and makes the application platform free. This improvements in speed and compatibility on different browsers, caused more user satisfaction and more frequent use of the web-application.
& Rantz, M. J.
(2014). A Novel Web-Based Depth Video Rewind Approach toward Fall Preventive Interventions in Hospitals. 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 4511-4514.