Related Experiment Video
Updated: Mar 8, 2026
06:51
Mouse Model of Pressure Ulcers After Spinal Cord Injury
Published on: March 9, 2019
10.2K
Leveraging Electronic Health Care Record Information to Measure Pressure Ulcer Risk in Veterans With Spinal Cord
Stephen L Luther1,2, Susan S Thomason1,3, Sunil Sabharwal4
1Center of Innovation on Disability and Rehabilitation Research, Health Services Research and Development, Department of Veterans Affairs, Tampa, FL, United States.
JMIR Research Protocols
|January 21, 2017
Summary
This study aims to develop a reliable risk assessment tool for pressure ulcers (PrUs) in veterans with spinal cord injury (SCI). Utilizing a large cohort and advanced text mining, it seeks to improve PrU prevention through electronic health record integration.
Area of Science:
- Medical Informatics
- Clinical Epidemiology
- Health Services Research
Background:
- Pressure ulcers (PrUs) are a significant and costly complication for veterans with spinal cord injury (SCI).
- Existing risk assessment tools lack the reliability, validity, and sensitivity needed for this specific population.
- There is a critical need for an effective PrU risk identification method in SCI veterans.
Purpose of the Study:
- To develop a validated risk assessment model for predicting PrU development in veterans with SCI.
- To create an automated system for PrU risk assessment integrated into electronic health records (EHR).
- To ultimately assist healthcare teams in preventing PrUs among SCI veterans.
Main Methods:
- A 5-year longitudinal, retrospective cohort study of 12,344 veterans with SCI within the Veterans Health Administration (VHA).
- Utilized data from the VHA Corporate Data Warehouse (FY 2009-2013), including structured and unstructured EHR data.
- Employed an expert panel to identify and refine potential risk factors, incorporating natural language processing (NLP) and statistical text mining.
Main Results:
- The study is ongoing, with final results anticipated in 2017.
- An expert panel refined the list of potential PrU risk factors based on literature review and EHR data formats.
- Data extraction, annotation schema development, and creation of an analytic dataset are in progress.
Conclusions:
- This study represents the largest cohort to date for identifying PrU risk factors in US veterans with SCI.
- It is the first study to leverage NLP and statistical text mining to expand the analysis of EHR data for PrU risk factors.
- The findings will lead to a reliable and valid PrU risk prediction tool tailored for the SCI veteran population.
