Simple falls are a serious danger for elderly folks, as they lead to fractured hips and other trauma that can seriously damage people’s lifestyles. Being able to predict that a geriatric patient is particularly prone to losing balance can help to prevent injury. Now the researchers at the University of Missouri have collected and processed an immense amount of information about the movement of seniors and looked how changes correlate with subsequent falls.
The team collected 66 terabytes of data over 10 years from video cameras installed in people’s homes. Various parameters, including walking speed, was measured and any falls were recorded. Some people were watched for three months while data on others gathered for four years. All this helped them to identify that folks who slow down in their walking over a relatively short period of time are more than four times as likely to experience a fall and that a shorter stride length also led to considerably increased chances.
To verify their predictive abilities, the team partnered with TigerPlace, a retirement home, where Microsoft Kinect 3D cameras were installed to watch over the elderly people living there.
Here’s a short video demonstrating the kind of imaging the team analyzed:
From the study abstract:
Over a period of 3 to 48 months, we analyzed gait parameters continuously collected for residents who actually fell (n = 13) and those who did not fall (n = 10). We analyzed associations between participants’ fall events (n = 69) and pre-fall changes in in-home gait speed and stride length (n = 2,070). Preliminary results indicate that a cumulative change in speed over time is associated with the probability of a fall (p < .0001). The odds of a resident falling within 3 weeks after a cumulative change of 2.54 cm/s is 4.22 times the odds of a resident falling within 3 weeks after no change in in-home gait speed.
Study in Western Journal of Nursing Research: Using Embedded Sensors in Independent Living to Predict Gait Changes and Falls…