AI may help detect ICU patient mobility, study shows

Machine vision technology may serve as a new method to monitor patient mobility in intensive care units, according to a study published in Nature.

Researchers at Stanford (Calif.) University and Intermountain LDS Hospital in Salt Lake City added machine vision technology sensors to seven ICU rooms at Intermountain LDS Hospital between August and October 2017.

The study aimed to analyze ICU patients' mobility during day-to-day tasks. Researchers installed depth sensors, which capture 3D volumetric images of humans and objects, in the ICU rooms to collect image data 24-hours per day for the two-month period.

Results showed the mobility-activity detecting algorithm correctly identified the patients' activities in 87 percent of cases. The algorithm was able to track four separate patient mobilization activities: patient getting into bed, patient getting out of bed, patient getting into chair and patient getting out of chair. Researchers also developed an algorithm to track healthcare personnel movement in the ICU rooms, which recorded 68 percent accuracy.

Study authors concluded that with more research and development, the algorithm could support early mobility protocols for critically ill patients by tracking a patient's movement and alerting healthcare personnel when the individual appears to have fallen or when they are having trouble moving.

To access the full report, click here.

More articles on artificial intelligence:
Microsoft, DNA analysis startup to develop algorithm to predict heart disease
Health Quest, IBM partner on AI tech to boost clinical trial participation
White House unveils new website to showcase AI initiatives

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.


Featured Webinars

Featured Whitepapers