Skip to main navigation Skip to search Skip to main content

Bodypart localization for pressure ulcer prevention

  • Jason J. Liu
  • , Ming Chun Huang
  • , Wenyao Xu
  • , Majid Sarrafzadeh
  • University of California at Los Angeles

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

28 Scopus citations

Abstract

Pressure ulcers, commonly called bedsores, are defined as injuries to the skin and underlying tissue resulting from prolonged pressure usually on bony areas of the body, such as heels and hips. In order to alleviate pressure accumulation at high-risk regions, the current practice in clinics requires caregivers to reposition their patients every two hours. This relies on the engagement of nursing services and places large burdens on the caregivers. In this study, a bedsore monitoring method using Pictorial Structure models is introduced to localize pressure distributions of the body. A pilot study including 12 subjects reveals that the proposed method enables reliable localization of bodyparts with 89.8% accuracy in common lying postures.

Original languageEnglish
Title of host publication2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages766-769
Number of pages4
ISBN (Electronic)9781424479290
DOIs
StatePublished - Nov 2 2014
Event2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 - Chicago, United States
Duration: Aug 26 2014Aug 30 2014

Publication series

Name2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

Conference

Conference2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
Country/TerritoryUnited States
CityChicago
Period08/26/1408/30/14

Fingerprint

Dive into the research topics of 'Bodypart localization for pressure ulcer prevention'. Together they form a unique fingerprint.

Cite this