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
Topics
- Adverse Drug Events (ADE) (1)
- Adverse Events (2)
- Cancer (1)
- Cardiovascular Conditions (1)
- Clinical Decision Support (CDS) (3)
- Clinician-Patient Communication (1)
- Communication (1)
- Dementia (1)
- Diabetes (1)
- (-) Diagnostic Safety and Quality (12)
- Electronic Health Records (EHRs) (9)
- Emergency Department (1)
- (-) Health Information Technology (HIT) (12)
- Heart Disease and Health (1)
- Imaging (2)
- Medical Errors (2)
- Medication (1)
- Medication: Safety (1)
- Neurological Disorders (1)
- Patient Safety (5)
- Primary Care (1)
- Quality Improvement (1)
- Quality of Care (1)
- Shared Decision Making (3)
- Surgery (1)
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 12 of 12 Research Studies DisplayedSalmasian H, Blanchfield BB, Joyce K
Association of display of patient photographs in the electronic health record with wrong-patient order entry errors.
Wrong-patient order entry (WPOE) errors have a high potential for harm; these errors are particularly frequent wherever workflows are complex and multitasking and interruptions are common, such as in the emergency department (ED). The purpose of this study was to evaluate whether the use of noninterruptive display of patient photographs in the banner of the electronic health record (EHR) is associated with a decreased rate of WPOE errors.
AHRQ-funded; HS024713.
Citation: Salmasian H, Blanchfield BB, Joyce K .
Association of display of patient photographs in the electronic health record with wrong-patient order entry errors.
AMA Netw Open 2020 Nov 2;3(11):e2019652. doi: 10.1001/jamanetworkopen.2020.19652..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Medical Errors, Adverse Drug Events (ADE), Adverse Events, Medication, Medication: Safety, Patient Safety, Diagnostic Safety and Quality
Yang J, Wang L, Phadke
Development and validation of a deep learning model for detection of allergic reactions using safety event reports across hospitals,
Although critical to patient safety, health care-related allergic reactions are challenging to identify and monitor. The purpose of this study was to develop a deep learning model to identify allergic reactions in the free-text narrative of hospital safety reports and evaluate its generalizability, efficiency, productivity, and interpretability. The investigators concluded that their study showed that a deep learning model could accurately and efficiently identify allergic reactions using free-text narratives written by a variety of health care professionals.
AHRQ-funded; HS025375.
Citation: Yang J, Wang L, Phadke .
Development and validation of a deep learning model for detection of allergic reactions using safety event reports across hospitals,
JAMA Netw Open 2020 Nov 2;3(11):e2022836. doi: 10.1001/jamanetworkopen.2020.22836..
Keywords: Diagnostic Safety and Quality, Health Information Technology (HIT), Patient Safety
Rogith D, Satterly T, Singh H
Application of human factors methods to understand missed follow-up of abnormal test results.
This study demonstrated application of human factors methods for understanding causes for lack of timely follow-up of abnormal test results ("missed results") in outpatient settings. The investigators identified 30 cases of missed test results by querying electronic health record data, developed a critical decision method based interview guide to understand decision-making processes, and interviewed physicians who ordered these tests. They analyzed transcribed responses, developed a CI-based flow model, and conducted a fault tree analysis to identify hierarchical relationships between factors that delayed action.
AHRQ-funded; HS022087; HS022901.
Citation: Rogith D, Satterly T, Singh H .
Application of human factors methods to understand missed follow-up of abnormal test results.
Appl Clin Inform 2020 Oct;11(5):692-98. doi: 10.1055/s-0040-1716537..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Shared Decision Making, Diagnostic Safety and Quality, Communication, Clinician-Patient Communication
Shah RU, Mutharasan RK, Ahmad FS
Development of a portable tool to identify patients with atrial fibrillation using clinical notes from the electronic medical record.
The electronic medical record contains a wealth of information buried in free text. In this study, the investigators created a natural language processing algorithm to identify patients with atrial fibrillation (AF) using text alone. The authors concluded that this approach allowed better use of the clinical narrative and created an opportunity for precise, high-throughput cohort identification.
AHRQ-funded; HS026385.
Citation: Shah RU, Mutharasan RK, Ahmad FS .
Development of a portable tool to identify patients with atrial fibrillation using clinical notes from the electronic medical record.
Circ Cardiovasc Qual Outcomes 2020 Oct;13(10):e006516. doi: 10.1161/circoutcomes.120.006516..
Keywords: Heart Disease and Health, Cardiovascular Conditions, Electronic Health Records (EHRs), Health Information Technology (HIT), Diagnostic Safety and Quality
Misra-Hebert AD, Milinovich A, Zajichek A
Natural language processing improves detection of nonsevere hypoglycemia in medical records versus coding alone in patients with type 2 diabetes but does not improve prediction of severe hypoglycemia events: an analysis using the electronic medical record
The purpose of this study was to determine if natural language processing (NLP) improves detection of non-severe hypoglycemia (NSH) in patients with type 2 diabetes and no NSH documentation by diagnosis codes and to measure if NLP detection improves the prediction of future severe hypoglycemia (SH). The authors identified NSH events by diagnosis codes and NLP 2005 to 2017 and built an SH prediction model. Their findings showed that detection of NSH improved with NLP in patients with type 2 diabetes without improving SH prediction.
AHRQ-funded; HS024128.
Citation: Misra-Hebert AD, Milinovich A, Zajichek A .
Natural language processing improves detection of nonsevere hypoglycemia in medical records versus coding alone in patients with type 2 diabetes but does not improve prediction of severe hypoglycemia events: an analysis using the electronic medical record
Diabetes Care 2020 Aug;43(8):1937-40. doi: 10.2337/dc19-1791..
Keywords: Diabetes, Electronic Health Records (EHRs), Health Information Technology (HIT), Diagnostic Safety and Quality
Bronsert M, Singh AB, Henderson WG
Identification of postoperative complications using electronic health record data and machine learning.
Investigators developed a machine learning algorithm for identifying patients with one or more complications using data from the electronic health record (EHR). They concluded that using machine learning on EHR postoperative data linked to American College of Surgeons National Surgical Quality Improvement Program outcomes data, a model with 163 predictors from the EHR identified complications well at their institution.
AHRQ-funded; HS026019.
Citation: Bronsert M, Singh AB, Henderson WG .
Identification of postoperative complications using electronic health record data and machine learning.
Am J Surg 2020 Jul;220(1):114-19. doi: 10.1016/j.amjsurg.2019.10.009..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Surgery, Quality Improvement, Quality of Care, Diagnostic Safety and Quality
Lacson R, Healey MJ, Cochon LR
Unscheduled radiologic examination orders in the electronic health record: a novel resource for targeting ambulatory diagnostic errors in radiology.
The purpose of this study was to assess the prevalence of unscheduled radiologic examination orders in an electronic health record and to assess the proportion of unscheduled orders that are clinically necessary. Unscheduled radiologic examination orders were retrieved for seven modalities: computed tomography, magnetic resonance imaging, ultrasound, obstetric ultrasound, bone densitometry, mammography, and fluoroscopy. Findings showed that large numbers of radiologic examination orders remain unscheduled in the electronic health record. Identifying and performing clinically necessary unscheduled radiologic examination orders may help reduce diagnostic errors related to diagnosis and treatment delays and enhance patient safety.
AHRQ-funded; HS024722.
Citation: Lacson R, Healey MJ, Cochon LR .
Unscheduled radiologic examination orders in the electronic health record: a novel resource for targeting ambulatory diagnostic errors in radiology.
J Am Coll Radiol 2020 Jun;17(6):765-72. doi: 10.1016/j.jacr.2019.12.021..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Diagnostic Safety and Quality, Imaging, Patient Safety
Zhou Y, Abel GA, Hamilton W
Imaging activity possibly signalling missed diagnostic opportunities in bladder and kidney cancer: a longitudinal data-linkage study using primary care electronic health records.
Sub-optimal use or interpretation of imaging investigations prior to diagnosis of certain cancers may be associated with less timely diagnosis, but pre-diagnostic imaging activity for urological cancer is unknown. In this study, the investigators analysed linked data derived from primary and secondary care records and cancer registration to evaluate the use of clinically relevant imaging tests pre-diagnosis, in patients with bladder and kidney cancer diagnosed in 2012-15 in England.
AHRQ-funded; HS022087.
Citation: Zhou Y, Abel GA, Hamilton W .
Imaging activity possibly signalling missed diagnostic opportunities in bladder and kidney cancer: a longitudinal data-linkage study using primary care electronic health records.
Cancer Epidemiol 2020 Jun;66:101703. doi: 10.1016/j.canep.2020.101703..
Keywords: Cancer, Diagnostic Safety and Quality, Imaging, Primary Care, Electronic Health Records (EHRs), Health Information Technology (HIT)
Soleimani J, Pinevich Y, Barwise AK
Feasibility and reliability testing of manual electronic health record reviews as a tool for timely identification of diagnostic error in patients at risk.
Although diagnostic error (DE) is a significant problem, it remains challenging for clinicians to identify it reliably and to recognize its contribution to the clinical trajectory of their patients. The purpose of this work was to evaluate the reliability of real-time electronic health record (EHR) reviews using a search strategy for the identification of DE as a contributor to the rapid response team (RRT) activation. Early and accurate recognition of critical illness is of paramount importance.
AHRQ-funded; HS026609.
Citation: Soleimani J, Pinevich Y, Barwise AK .
Feasibility and reliability testing of manual electronic health record reviews as a tool for timely identification of diagnostic error in patients at risk.
Appl Clin Inform 2020 May;11(3):474-82. doi: 10.1055/s-0040-1713750..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Diagnostic Safety and Quality, Medical Errors, Adverse Events, Patient Safety
Carayon P, Hoonakker P, Hundt AS
Application of human factors to improve usability of clinical decision support for diagnostic decision-making: a scenario-based simulation study.
This study used a scenario-based simulation to compare a human factor (HF)-based clinician decision support (CDS) with a web-based CDS (MDCalc) for clinicians to diagnose pulmonary embolism (PE) in the emergency department. A total of 32 emergency physicians participated using both CDS types. Emergency physicians made more appropriate diagnoses decisions with the PE-Dx CDS (94%) than with the web-based CDS (84%). Experimental tasks were also performed faster (average 96 seconds per scenario versus 117 seconds). They also reported lower workload and higher satisfaction with the HF-based CDS.
AHRQ-funded; HS024342; HS024558; HS022086.
Citation: Carayon P, Hoonakker P, Hundt AS .
Application of human factors to improve usability of clinical decision support for diagnostic decision-making: a scenario-based simulation study.
BMJ Qual Saf 2020 Apr;29(4):329-40. doi: 10.1136/bmjqs-2019-009857..
Keywords: Clinical Decision Support (CDS), Shared Decision Making, Health Information Technology (HIT), Diagnostic Safety and Quality, Emergency Department
Meyer AND, Giardina TD, Spitzmueller C
Patient perspectives on the usefulness of an artificial intelligence-assisted symptom checker: cross-sectional survey study.
This study examined patients’ experiences using an artificial intelligence (AI)-assisted online symptom checker and their doctors’ reactions to that use. From March 2 through March 15, 2018 an online survey was conducted of US users of the Isabel Symptom Checker within 6 months of their use. The majority of users were women, white, and had a mean age of 48. Overall, patients had a positive experience with the symptom checker and felt they would use it again (91.4%). About 48% discussed the findings with their physician and felt about 40% of their physicians were interested. Patients who had previously experienced diagnostic errors were more likely to use the symptom checker to determine if they should seek care.
AHRQ-funded; HS025474; HS027363.
Citation: Meyer AND, Giardina TD, Spitzmueller C .
Patient perspectives on the usefulness of an artificial intelligence-assisted symptom checker: cross-sectional survey study.
J Med Internet Res 2020 Jan 30;22(1):e14679. doi: 10.2196/14679..
Keywords: Clinical Decision Support (CDS), Health Information Technology (HIT), Diagnostic Safety and Quality, Patient Safety
Barnes DE, Zhou J, Walker RL
Development and validation of eRADAR: a tool using EHR Data to detect unrecognized dementia.
The goal of this retrospective cohort study was to develop and validate an electronic health record (EHR)-based tool to help detect patients with unrecognized dementia. The tool was named EHR Risk of Alzheimer’s and Dementia Assessment Rule (eRADAR). This study was conducted at Kaiser Permanente Washington (KPWA) using participants in the Adult Changes in Thought (ACT) study who undergo comprehensive testing every 2 years to detect and diagnose dementia and have linked KPWA EHR data. Overall, 1015 ACT visits resulted in a diagnosis of incident dementia, of which 49% were previously unrecognized in the EHR. The final 31-predictor model included markers of dementia-related symptoms, healthcare utilization patterns, and dementia risk factors. The study showed good discrimination in the development interval and validation samples.
AHRQ-funded; HS022982.
Citation: Barnes DE, Zhou J, Walker RL .
Development and validation of eRADAR: a tool using EHR Data to detect unrecognized dementia.
J Am Geriatr Soc 2020 Jan;68(1):103-11. doi: 10.1111/jgs.16182..
Keywords: Electronic Health Records (EHRs), Health Information Technology (HIT), Dementia, Neurological Disorders, Diagnostic Safety and Quality, Clinical Decision Support (CDS), Shared Decision Making