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
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 3 of 3 Research Studies DisplayedPatterson BW, Jacobsohn GC, Shah MN
Development and validation of a pragmatic natural language processing approach to identifying falls in older adults in the emergency department.
This study examined development and validation of a pragmatic natural language processing (NLP) approach to identify fall risk in older adults after emergency department (ED) visits. A single center retrospective review using data from 500 emergency department provider notes on older adults age 65 and older were random selected for analysis. The NLP algorithm successfully identified falls in ED notes with over 90% precision, and looks promising to reduce labor-intensive manual abstraction.
AHRQ-funded; HS024558.
Citation: Patterson BW, Jacobsohn GC, Shah MN .
Development and validation of a pragmatic natural language processing approach to identifying falls in older adults in the emergency department.
BMC Med Inform Decis Mak 2019 Jul 22;19(1):138. doi: 10.1186/s12911-019-0843-7..
Keywords: Adverse Events, Elderly, Emergency Department, Falls, Risk, Patient Safety
Patterson BW, Engstrom CJ, Sah V
Training and interpreting machine learning algorithms to evaluate fall risk after emergency department visits.
This study examined the potential of using machine learning algorithms to evaluate fall risk after an emergency department (ED) visit. They compared several machine learning methodologies for creation of a risk stratification algorithm to predict the outcome of a return visit for a fall within 6 months of an ED visit.
AHRQ-funded; HS024558; HS024342.
Citation: Patterson BW, Engstrom CJ, Sah V .
Training and interpreting machine learning algorithms to evaluate fall risk after emergency department visits.
Med Care 2019 Jul;57(7):560-66. doi: 10.1097/mlr.0000000000001140..
Keywords: Adverse Events, Elderly, Emergency Department, Falls, Risk, Patient Safety
Griffey RT, Schneider RM, Todorov AA
Critical review, development, and testing of a taxonomy for adverse events and near misses in the emergency department.
Researchers created and tested a taxonomy for adverse events (AEs) and near misses for use in the emergency department (ED). This taxonomy is patient-centered, as opposed to most taxonomies which fail to describe harm experienced by patients and focus instead on errors and uses too broad categorizations. The authors reviewed candidate taxonomies using an iterative process and selected the Adventist Health Systems AE taxonomy and modified it for use in the ED. After testing with reviewers, agreement with the criterion standard was 92% at the category level and 88% at the subcategory level. Performance from individual raters ranged from very good (88%) to near perfect (98%) at the main category level.
AHRQ-funded; HS025052.
Citation: Griffey RT, Schneider RM, Todorov AA .
Critical review, development, and testing of a taxonomy for adverse events and near misses in the emergency department.
Acad Emerg Med 2019 Jun;26(6):670-79. doi: 10.1111/acem.13724..
Keywords: Adverse Events, Emergency Department, Medical Errors, Patient Safety, Risk