Features | Partner Sites | Information | LinkXpress
Sign In
Fluke Biomedical
Schiller
Ampronix

Video Analytics Helps Monitor Bedridden Patients

By HospiMedica International staff writers
Posted on 05 Jun 2014
Image: Video technology recognizes patient status (Photo courtesy Fujitsu Laboratories).
Image: Video technology recognizes patient status (Photo courtesy Fujitsu Laboratories).
New technology uses a video camera to accurately recognize the status of hospital patients, detecting activities such as sitting up in bed, getting out of bed, or moving in bed.

Developed by Fujitsu Laboratories (Kawasaki, Japan), the technology is based on two modalities. The first recognizes the patient's head and tracks it to identify when the patient sits up or gets out of bed, which can be precursors to actions such as wandering, slipping, or falling. The second detects and visualizes conditions such as restiveness or sleeplessness, which demand further attention. The state of the patient in bed is then classified into five categories depending on posture, and defines a state-transition diagram that relates them to each other.

The recognition process also uses learned data, wherein next likely states are limited by the current state, based on the state-transition diagram. Selecting learned data in the recognition process aids in highly accurate patient head position state. But even with the selection of learned data based on patient status, the potential remains to incorrectly recognize pillows as heads. To correct for that, the technology observes points that will always move when the patient sits up or stands up, and will identify multiple regions in the image that might be the head to confirm if it really is the patient's head, or not.

With the cooperation of Tamagawa Hospital (Tokyo, Japan), Fujitsu Laboratories conducted a field trial to test sensing of sitting up and getting out of bed on several patients. The visualization of patient behaviors was found to perform with 91% accuracy. Behaviors demanding attention were displayed at the nursing station, allowing nurses to easily monitor patient movements without going on rounds, resulting in a high standard of patient protection for the hospital or care facility, while at the same time lightening the workload of the nurses.

Existing techniques to detect when a patient has sat up or gotten out of bed rely on pressure sensors that detect bodyweight; but this approach has some problems. Sometimes patients will intentionally avoid the sensor so that it does not react when they get out of bed. In addition, the sensor cannot distinguish when the patient is turning over while sleeping, or when movements by the nurse are triggering it, resulting in false alarms. And even with the sensors, nurses still need to make frequent checks, and if anything their workload may be higher.

Related Links:

Fujitsu Laboratories
Tamagawa Hospital



Cincinnati Sub-Zero
ACEM
ECR

Channels

Surgical Techniques

view channel
Image

Transport System Extends Utilization of Robotic Surgery

A new transport system will allow the Magellan robotic system to be a shared hospital resource, giving multiple physician specialties access in several settings. The Magellan Transport System, which... Read more

Women's Health

view channel

Aspirin Reduces Breast Cancer Recurrence in Overweight Women

The recurrence of hormone-related breast cancer was reduced by more than half in overweight and obese women who regularly used nonsteroidal anti-inflammatory drugs (NSAIDs), according to a new study. Researchers at the University of Texas (UT; Austin, USA) conducted a retrospective review of data from 440 women with... Read more

Business

view channel

Lloyds Bank Establishes Specialist Healthcare Teams

As part of a substantial restructure, Lloyds Bank Commercial Banking (London, United Kingdom) has launched two specialist healthcare relationship teams. Designated part of the small and medium enterprise (SME) commercial banking division, the two teams will offer industry-specific support for firms in London (United Kingdom).... Read more
 
Copyright © 2000-2014 Globetech Media. All rights reserved.