National Healthcare Quality and Disparities Report
Latest available findings on quality of and access to health care
Data
- Data Infographics
- Data Visualizations
- Data Tools
- Data Innovations
- All-Payer Claims Database
- Healthcare Cost and Utilization Project (HCUP)
- Medical Expenditure Panel Survey (MEPS)
- AHRQ Quality Indicator Tools for Data Analytics
- State Snapshots
- United States Health Information Knowledgebase (USHIK)
- Data Sources Available from AHRQ
Search All Research Studies
AHRQ Research Studies Date
AHRQ Research Studies
Sign up: AHRQ Research Studies Email updates
Research Studies is a compilation of published research articles funded by AHRQ or authored by AHRQ researchers.
Results
1 to 2 of 2 Research Studies DisplayedMilliren CE, Ozonoff A, Fournier KA
Enhancing pressure injury surveillance using natural language processing.
This study’s goal was to assess the feasibility of using nursing handoff notes to identify underreported hospital-acquired pressure injury (HAPI) events. The authors established a natural language processing-assisted manual review process and workflow for data extraction from a corpus of nursing notes across all medical inpatient and intensive care units in a tertiary care pediatric center. Their workflow started with keywords around HAPI and treatments, then regular expressions, distributive semantics, and finally a document classifier. They generated 3 models: a tri-gram classifier, binary logistic regression model using the regular expressions as predictors, and a random forest model using both models together. Their final output was generated using a random forest model validated using derivation and validation sets. Their initial data set involved 70,981 notes during a 1-year period from 5484 unique admissions for 4220 patients. Their interrater human reviewer agreement on identifying HAPI was high. Their random forest model had 95% sensitivity, 71.2% specificity, and 78.7% accuracy. A total of 264 notes from 148 unique admissions were identified describing likely HAPI, with 61 describing new injuries, and 64 describing known yet possibly evolving injuries. HAPI incidence was 11.9 per 1000 discharges, and incidence rate was 1.2 per 1000 bed-days.
AHRQ-funded; HS026246.
Citation: Milliren CE, Ozonoff A, Fournier KA .
Enhancing pressure injury surveillance using natural language processing.
J Patient Saf 2024 Mar 1; 20(2):119-24. doi: 10.1097/pts.0000000000001193.
Keywords: Pressure Ulcers, Healthcare-Associated Infections (HAIs), Health Information Technology (HIT)
Sharkey S, Hudak S, Horn SD
AHRQ Author: Spector W
Exploratory study of nursing home factors associated with successful implementation of clinical decision support tools for pressure ulcer prevention.
The researchers determined those factors that are associated with nursing homes' success in implementing the On-Time quality improvement (QI) for pressure ulcer prevention program and integrating health information technology (HIT) tools into practice at the unit level. They found that after at least 9 months of implementation effort, 36% of the nursing homes achieved level III of the On-Time QI-HIT program. They concluded that the learning from On-Time QI offers several lessons associated with facility factors that contribute to high level of implementation of a QI-HIT program in a nursing home.
AHRQ-authored; AHRQ-funded; 29020050020.
Citation: Sharkey S, Hudak S, Horn SD .
Exploratory study of nursing home factors associated with successful implementation of clinical decision support tools for pressure ulcer prevention.
Adv Skin Wound Care 2013 Feb;26(2):83-92; quiz p.93-4. doi: 10.1097/01.ASW.0000426718.59326.bb.
.
.
Keywords: Health Information Technology (HIT), Nursing Homes, Pressure Ulcers, Prevention, Quality Improvement