Posture Detection for Pressure Injury Prevention
The Wounds Canada Virtual 2020 Fall Conference took place on October 15 to 18, 2020, and Curiato was pleased to present our second ever poster presentation. The poster was written by an esteemed panel of healthcare practitioners featuring Kevin Woo, PhD, RN, NSWOCC WOCC FAPWCA as the lead author. In this poster, we discuss our findings related to posture detection for pressure injury prevention from our initial trial conducted at Toronto Grace Health Centre.
The Wounds Canada Virtual 2020 Fall Conference took place on October 15 to 18, 2020, and Curiato was pleased to present our second ever poster presentation. The poster was written by an esteemed panel of healthcare practitioners featuring Kevin Woo, PhD, RN, NSWOCC WOCC FAPWCA as the lead author. In this poster, we discuss our findings related to posture detection for pressure injury prevention from our initial trial conducted at Toronto Grace Health Centre.
Healthcare-acquired pressure injuries have an immense impact on patient outcomes, their length of stay, and of course hospital costs, and patient repositioning by means of caregiver assisted posture change is the gold standard of care for pressure injury prevention. However, evidence-based advice about the optimal repositioning of patients remains inconsistent.
To demonstrate the effectiveness of a smart surface system designed to monitor multiple risk factors for healthcare-acquired pressure injuries among patients, we set out on our first single-site trial at the Toronto Grace Health Centre.
Over 100 patients, with a mean age of 59, were recruited for the trial from complex continuing care and post-acute care rehabilitation settings. About 1,400 sensor monitoring hours generated over one million frames of data, this compared to the 600 patient postures manually recorded by the nurses. While there was a strong correlation with the nurse collected data, the large volume of data collected via the smart surface system forms a substantial basis for artificial intelligence applications. For a more detailed account of this study, download the conference poster below.
Over 100 patients, with a mean age of 59, were recruited for the trial from complex continuing care and post-acute care rehabilitation settings. About 1,400 sensor monitoring hours generated over one million frames of data, this compared to the 600 patient postures manually recorded by the nurses. While there was a strong correlation with the nurse collected data, the large volume of data collected via the smart surface system forms a substantial basis for artificial intelligence applications. For a more detailed account of this study, download the conference poster below.
“The smart bed itself allows staff to be able to make changes to patient positioning or changes as a result of pressure, moisture or temperature as they need to. And this is important because the current standard is to turn the patient every two to four hours. The technology allows staff to be able to turn the patients when they need to.”
~ Jake Tran, President & CEO, Toronto Grace Health Centre
SHARE THIS POST
