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 2 of 2 Research Studies DisplayedHobensack M, Song J, Chae S
Capturing concerns about patient deterioration in narrative documentation in home healthcare.
This study aimed to build machine learning algorithms to identify “concerning” narrative notes of home healthcare (HHC) patients and identify emergency themes to support early identification of patients at risk for deterioration. Six algorithms were applied to 4000 narrative notes from a HHC agency to classify notes as either "concerning" or "not concerning." Emerging themes were identified using Latent Dirichlet Allocation bag of words topic modeling. Emerging themes of concern included patient-clinician communication, HHC services provided, gait challenges, mobility concerns, wounds, and caregivers. Most of these themes had already been identified in previous literature as increasing risk for adverse events.
AHRQ-funded; HS027742.
Citation: Hobensack M, Song J, Chae S .
Capturing concerns about patient deterioration in narrative documentation in home healthcare.
AMIA Annu Symp Proc 2023 Apr 29; 2022:552-59..
Keywords: Home Healthcare, Electronic Health Records (EHRs), Health Information Technology (HIT)
Hobensack M, Song J, Scharp D
Machine learning applied to electronic health record data in home healthcare: a scoping review.
This literature review aimed to synthesize and appraise the literature describing the application of machine learning to predict adverse outcomes (e.g., hospitalization, mortality) using electronic health record (EHR) data in the home healthcare (HHC) setting. The secondary aim was to evaluate the comprehensiveness of predictors used in the machine learning algorithms guided by the Biopsychosocial Model. Studies were included if they 1) described services provided in the HHC setting, 2) applied machine learning algorithms to predict adverse outcomes, defined as outcomes related to patient deterioration, 3) used EHR data and, 4) focused on the adult population. Predictors were mapped to the Biopsychosocial Model. The final sample included 20 studies, of which 18 used predictors from standardized assessments integrated in the EHR. The most common outcome was hospitalization (55%), followed by mortality (25%). About 35% of studies excluded psychological predictors. Most studies (75%) demonstrated high or unclear risk of bias with tree based algorithms most frequently applied (75%).
AHRQ-funded; HS027742.
Citation: Hobensack M, Song J, Scharp D .
Machine learning applied to electronic health record data in home healthcare: a scoping review.
Int J Med Inform 2023 Feb; 170:104978. doi: 10.1016/j.ijmedinf.2022.104978..
Keywords: Home Healthcare, Electronic Health Records (EHRs), Health Information Technology (HIT)