Researchers at the University of Missouri are currently investigating the technology used in video games in an effort to prevent falls among hospital patients. The team has been assessing strategies to detect and prevent falls by older adults living in independent apartments since 2008, explains Marilyn Rantz, PhD, RN, a leader of the MU research team and a professor in the MU Sinclair School of Nursing and the department of Family and Community Medicine in the MU School of Medicine.

“Because falls are a concern in hospitals, we thought much of what we learned regarding older people could apply to protecting hospital patients,” Rantz adds.

Marjorie Skubic, PhD, the LaPierre Professor of Electrical and Computer Engineering, and professor of computer science at the MU College of Engineering, states in a university news release that during the past several years the team has explored a variety of technologies in its work with older adults, including Doppler radar, sound sensors, and video cameras. While Doppler radar and sound sensors can detect an individual’s fall, Skubic says, they cannot show what happened leading up to the fall.

Rantz expands upon Skubic’s sentiment, noting, “By seeing what happened before a fall, we can better understand what caused it. The more we know about what causes falls, the more effectively we can prevent them.”

Upon the release of video-game motion-capture technology, the university says, the MU team gained a tool that avoided limitations of other technologies, and unlike video cameras, portrayed individuals as three-dimensional silhouettes, protecting their privacy. The release states that the system resembles a thin black box, featuring black glass on one side that covers the sensors, which are engineered to pick up movements of the video-game players or patients in a hospital room. The university adds that one sensor, a depth camera, is designed to measure the distances to objects in its view. A cord connects the system to a small computer.

The system, the university states, operates by sending a grid pattern of infrared light into a room, and then analyzing how objects and individuals in the room distort the pattern. The machine analyzes these distortions in order to produce a 3D map, showing patients, their bed and tray table, and all other objects in the room.

Once a person is detected on the floor, the system is engineered to automatically review the preceding events as the person moved to the floor. By applying a precise algorithm created by Skubic, Erik Stone, doctoral graduate, and an interdisciplinary team, the computer calculates the probability that the changes represent a person’s fall.

During the study, the release notes, the research team installed a motion-capture device in each of six patient rooms at University Hospital in Columbia, Mo. Researchers then trained nursing staff to explain the study to patients. The devices were designed to collect data continuously, monitoring the rooms 24 hours a day. The research article, which appears in the Journal of Gerontological Nursing, reportedly documents the first 8 months of the study. The researchers say that during the time, the sensors did not record any patient falls. However stunt actors simulated 50 falls in the rooms, providing more data for the algorithm.

According to Rantz, the researchers believe the technology is promising, “because it accurately identified falls and may eventually help prevent falls. We are now in the process of installing the sensors in more patient rooms to learn more about its effectiveness.”

A key result of the work, the researchers add, was the reduction of falls in the six patient rooms during the study.

A potential cause behind this result, Skubic says, may be that the devices “have brought more attention to the issue of falls. It could have made patients more aware of the risks and more likely to ask their nurses for help getting out of bed.”

[Source(s): University of Missouri-Columbia, Science Daily]