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 6 of 6 Research Studies DisplayedWolfson J, Bandyopadhyay S, Elidrisi M
A Naive Bayes machine learning approach to risk prediction using censored, time-to-event data.
This paper proposed an adaptation of the well-known Naive Bayes machine learning approach to time-to-event outcomes subject to censoring. It compared the predictive performance of that method with the Cox proportional hazards model which is commonly used for risk prediction in healthcare populations, and illustrated its application to prediction of cardiovascular risk using an electronic health record dataset from a large Midwest integrated healthcare system.
AHRQ-funded; HS017622.
Citation: Wolfson J, Bandyopadhyay S, Elidrisi M .
A Naive Bayes machine learning approach to risk prediction using censored, time-to-event data.
Stat Med 2015 Sep 20;34(21):2941-57. doi: 10.1002/sim.6526..
Keywords: Risk, Electronic Health Records (EHRs), Health Information Technology (HIT), Cardiovascular Conditions
Amarasingham R, Velasco F, Xie B
Electronic medical record-based multicondition models to predict the risk of 30 day readmission or death among adult medicine patients: validation and comparison to existing models.
The purpose of this study was to evaluate the degree to which electronic medical record-based risk models for 30-day readmission or mortality accurately identify high risk patients and to compare these models with published claims-based models. The researchers found that a new electronic multicondition model based on information derived from the electronic medical record predicted mortality and readmission at 30 days, and was superior to previously published claims-based models
AHRQ-funded; HS022418.
Citation: Amarasingham R, Velasco F, Xie B .
Electronic medical record-based multicondition models to predict the risk of 30 day readmission or death among adult medicine patients: validation and comparison to existing models.
BMC Med Inform Decis Mak 2015 May 20;15:39. doi: 10.1186/s12911-015-0162-6.
.
.
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Mortality, Hospital Readmissions, Risk
LaFleur J, Steenhoek CL, Horne J
Comparing fracture absolute risk assessment (FARA) tools: an osteoporosis clinical informatics tool to improve identification and care of men at high risk of first fracture.
The researchers compared 2 fracture absolute risk assessment (FARA) tools for use with electronic health records (EHRs) to determine which would more accurately identify patients known to be high risk for fracture. They found that absolute fracture risk estimation with the VA-FARA is more predictive of a first fracture than the WHO’s eFRAX in male veterans when used in an EHR-based population screening tool.
AHRQ-funded; HS018582.
Citation: LaFleur J, Steenhoek CL, Horne J .
Comparing fracture absolute risk assessment (FARA) tools: an osteoporosis clinical informatics tool to improve identification and care of men at high risk of first fracture.
Ann Pharmacother 2015 May;49(5):506-14. doi: 10.1177/1060028015572819..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Injuries and Wounds, Osteoporosis, Risk
Unni S, Yao Y, Milne N
An evaluation of clinical risk factors for estimating fracture risk in postmenopausal osteoporosis using an electronic medical record database.
The researchers sought to identify variables in an EMR database for calculating fracture risk Assessment (FRAX) score in a cohort of postmenopausal women, to estimate absolute fracture risk. They found that mean 10-year risk for any major fracture was 11.1 percent when bone mineral density (BMD) was used and 11.2 percent when BMI was used.
AHRQ-funded; HS0018582.
Citation: Unni S, Yao Y, Milne N .
An evaluation of clinical risk factors for estimating fracture risk in postmenopausal osteoporosis using an electronic medical record database.
Osteoporos Int 2015 Feb;26(2):581-7. doi: 10.1007/s00198-014-2899-7..
Keywords: Electronic Health Records (EHRs), Injuries and Wounds, Risk, Osteoporosis, Health Information Technology (HIT)
Faerber AE, Horvath R, Stillman C
Development and pilot feasibility study of a health information technology tool to calculate mortality risk for patients with asymptomatic carotid stenosis: the Carotid Risk Assessment Tool (CARAT).
The researchers describe the development of the CArotid Risk Assessment Tool (CARAT) into a 2-year mortality risk calculator within the electronic medical record. They integrated the tool into the clinical workflow, trained the clinical team to use the tool, and assessed the feasibility and acceptability of the tool in one clinic setting.
AHRQ-funded; HS021581.
Citation: Faerber AE, Horvath R, Stillman C .
Development and pilot feasibility study of a health information technology tool to calculate mortality risk for patients with asymptomatic carotid stenosis: the Carotid Risk Assessment Tool (CARAT).
BMC Med Inform Decis Mak 2015;15:20. doi: 10.1186/s12911-015-0141-y..
Keywords: Health Information Technology (HIT), Electronic Health Records (EHRs), Mortality, Risk
Panahiazar M, Taslimitehrani V, Pereira N
Using EHRs and machine learning for heart failure survival analysis.
This study assessed the performance of the Seattle Heart Failure Model using EHRs at Mayo Clinic, and sought to develop a risk prediction model using machine learning techniques that applied routine clinical care data. Its results showed the models which were built using EHR data are more accurate (11 percent improvement in AUC) with the convenience of being more readily applicable in routine clinical care.
AHRQ-funded; HS023077.
Citation: Panahiazar M, Taslimitehrani V, Pereira N .
Using EHRs and machine learning for heart failure survival analysis.
Stud Health Technol Inform 2015;216:40-4..
Keywords: Electronic Health Records (EHRs), Heart Disease and Health, Risk, Data