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
- Arthritis (1)
- Behavioral Health (1)
- Blood Thinners (1)
- Cardiovascular Conditions (1)
- Chronic Conditions (1)
- Clinical Decision Support (CDS) (12)
- COVID-19 (1)
- Elderly (3)
- Electronic Health Records (EHRs) (2)
- Emergency Department (2)
- Evidence-Based Practice (2)
- Falls (2)
- (-) Health Information Technology (HIT) (13)
- Heart Disease and Health (1)
- Implementation (1)
- Medication (3)
- Medication: Safety (1)
- Opioids (1)
- Orthopedics (1)
- Pain (1)
- Patient-Centered Healthcare (2)
- Patient-Centered Outcomes Research (3)
- Patient Safety (1)
- Prevention (1)
- Risk (1)
- (-) Shared Decision Making (13)
- Substance Abuse (1)
- 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 13 of 13 Research Studies DisplayedNg MY, Kapur S, Blizinsky KD
The AI life cycle: a holistic approach to creating ethical AI for health decisions.
This article provides an overview of the reimagined artificial intelligence (AI) lifecycle to create ethical AI for health decisions. The lifecycle is data creation, data acquisition, model development, model evaluation, and model deployment. AI biases in each phase are described and recommendations are made to address each one.
AHRQ-funded; HS027434.
Citation: Ng MY, Kapur S, Blizinsky KD .
The AI life cycle: a holistic approach to creating ethical AI for health decisions.
Nat Med 2022 Nov;28(11):2247-49. doi: 10.1038/s41591-022-01993-y..
Keywords: Health Information Technology (HIT), Shared Decision Making
Gomez Lumbreras A, Reese TJ, Del Fiol G
Shared decision-making for drug-drug interactions: formative evaluation of an anticoagulant drug interaction.
This study evaluated a tool called DDInteract that was developed to enhance and support shared decision-making (SDM) between patients and physicians when both warfarin and NSAIDs are used concurrently. The study used case vignettes with physicians and patients on warfarin to conduct simulated virtual clinical encounters where they discussed the use of taking ibuprofen and warfarin concurrently and determined an appropriate therapeutic plan based on the patient’s individualized risk. Participants completed a postsession interview and SDM process survey, including the 9-item Shared Decision-Making Questionnaire (SDM-Q-9), tool usability and workload National Aeronautics and Space Administration (NASA) Task Load Index, Unified Theory of Acceptance and Use of Technology (UTAUT), Perceived Behavioral Control (PBC) scale, System Usability Scale (SUS), and Decision Conflict Scale (DCS). A total of 12 physician-patient dyads were used, with over 91% of the patients over 50 and 75% had been taking warfarin for over 2 years. Most participants rated DDInteract higher than usual care (UC) and would be willing to use the tool for an interaction involving warfarin and NSAIDs.
AHRQ-funded; HS027099.
Citation: Gomez Lumbreras A, Reese TJ, Del Fiol G .
Shared decision-making for drug-drug interactions: formative evaluation of an anticoagulant drug interaction.
JMIR Form Res 2022 Oct 19;6(10):e40018. doi: 10.2196/40018..
Keywords: Shared Decision Making, Medication, Blood Thinners, Clinical Decision Support (CDS), Health Information Technology (HIT), Medication: Safety, Patient Safety
Weiner SJ, Schwartz A, Weaver F
Effect of electronic health record clinical decision support on contextualization of care: a randomized clinical trial.
Researchers sought to determine whether contextualized clinical decision support (CDS) tools in the electronic health record (EHR) improve clinician contextual probing, attention to contextual factors in care planning, and the presentation of contextual red flags. In this randomized clinical trial, they found that contextualized CDS did not improve patients' outcomes but did increase contextualization of their care, suggesting that use of this technology could ultimately help to improve outcomes.
AHRQ-funded; HS025374.
Citation: Weiner SJ, Schwartz A, Weaver F .
Effect of electronic health record clinical decision support on contextualization of care: a randomized clinical trial.
JAMA Netw Open 2022 Oct;5(10):e2238231. doi: 10.1001/jamanetworkopen.2022.38231..
Keywords: Electronic Health Records (EHRs), Clinical Decision Support (CDS), Health Information Technology (HIT), Shared Decision Making
Kagarmanova A, Sparkman H, Laiteerapong N
Improving the management of chronic pain, opioid use, and opioid use disorder in older adults: study protocol for i-cope study.
This article describes a protocol for an upcoming study on the planned implementation and evaluation of I-COPE (Improving Chicago Older Adult Opioid and Pain Management through Patient-centered Clinical Decision Support and Project ECHO®) to improve care for older adults with chronic pain, opioid use, and opioid use disorder (OUD). The study will be implemented in 35 clinical sites across the metropolitan Chicago area for patients aged ≥ 65 with chronic pain, opioid use, or OUD who receive primary care at one of the clinics. I-COPE includes the integration of patient-reported data on symptoms and preferences, clinical decision support tools and shared decision making into routine primary care. Primary care providers will be trained on the tools through web-based videos and an optional Project ECHO® course, entitled "Pain Management and OUD in Older Adults." A framework called RE-AIM will be used to assess the I-COPE implementation. Outcomes considered effective include an increased variety of recommended pain treatments, decreased prescriptions of higher-risk pain treatments, and decreased patient pain scores. Outcomes will be evaluated at 6 and 12 months after implementation, and PCPs participating in Project ECHO® will be evaluated on changes in knowledge, attitudes, and self-efficacy using pre- and post-course surveys.
AHRQ-funded; HS027910.
Citation: Kagarmanova A, Sparkman H, Laiteerapong N .
Improving the management of chronic pain, opioid use, and opioid use disorder in older adults: study protocol for i-cope study.
Trials 2022 Jul 27;23(1):602. doi: 10.1186/s13063-022-06537-w..
Keywords: Elderly, Pain, Chronic Conditions, Opioids, Medication, Substance Abuse, Behavioral Health, Clinical Decision Support (CDS), Shared Decision Making, Health Information Technology (HIT)
Hinson JS, Klein E, Smith A
Multisite implementation of a workflow-integrated machine learning system to optimize COVID-19 hospital admission decisions.
This study’s objective was to develop, implement, and evaluate an electronic health record (EHR) embedded clinical decision support (CDS) system that leveraged machine learning (ML) to estimate short-term risk for clinical deterioration in patients with or under investigation for COVID-19. The system translates model-generated risk for critical care needs within 24 hours and inpatient care needs within 72 hours into rapidly interpretable COVID-19 Deterioration Risk Levels made viewable within ED clinician workflow. A retrospective cohort of 21,452 ED patients who visited one of five ED study sites was used to derive ML models and were prospectively validated in 15,670 ED visits that occurred before (n = 4322) or after (n = 11,348) CDS implementation. Model performance and numerous patient-oriented outcomes including in-hospital mortality were measured across study periods. ML model performance was excellent under all conditions. AUC ranged from 0.85 to 0.91 for prediction of critical care needs and 0.80-0.90 for inpatient care needs. Total mortality was unchanged across study periods but was reduced among high-risk patients after the implementation.
AHRQ-funded; HS026640.
Citation: Hinson JS, Klein E, Smith A .
Multisite implementation of a workflow-integrated machine learning system to optimize COVID-19 hospital admission decisions.
NPJ Digit Med 2022 Jul 16;5(1):94. doi: 10.1038/s41746-022-00646-1..
Keywords: COVID-19, Clinical Decision Support (CDS), Health Information Technology (HIT), Implementation, Electronic Health Records (EHRs), Emergency Department, Shared Decision Making
Nanji KC, Garabedian PM, Langlieb ME
Usability of a perioperative medication-related clinical decision support software application: a randomized controlled trial.
The purpose of this study was assess the usability of a newly developed, comprehensive, medication-related operating room clinical decision support (CDS) software and compare it with the standard electronic health record (EHR) medication workflow. Forty participants were randomized to a CDS group (n=20) or a control group (n=20) and asked to complete 7 simulation tasks. The study found that in a simulation setting the new CDS software improved efficiency and quality of care and reduced task time, excelling over the current EHR workflow.
AHRQ-funded; HS024764.
Citation: Nanji KC, Garabedian PM, Langlieb ME .
Usability of a perioperative medication-related clinical decision support software application: a randomized controlled trial.
J Am Med Inform Assoc 2022 Jul 12;29(8):1416-24. doi: 10.1093/jamia/ocac035..
Keywords: Medication, Clinical Decision Support (CDS), Health Information Technology (HIT), Surgery, Shared Decision Making
Dullabh P, Sandberg SF, Heaney-Huls K
AHRQ Author: Berliner E, Dymek C, Harrison MI, Swiger J
Challenges and opportunities for advancing patient-centered clinical decision support: findings from a horizon scan.
This AHRQ-authored horizon scan identified challenges and opportunities for advancing patient-centered clinical decision support (PC CDS) and future directions for PC CDS. The authors engaged a technical expert panel, conducted a scoping literature review, and interviewed key informants. They quantitatively analyzed literature and interview transcripts and mapped the findings to the 4 phases translating evidence into PC CDS interventions (Prioritizing, Authoring, Implementing, and Measuring) and to external factors. Twelve challenges were identified for PC CDS development with lack of patient input identified as a critical challenge. Lack of patient-centered terminology standards was viewed as a challenge in authoring PC CDS. They also found a dearth of CDS studies that measured clinical outcomes, creating significant gaps in the understanding of PC CDS’ impact.
AHRQ-authored; AHRQ-funded; 233201500023I.
Citation: Dullabh P, Sandberg SF, Heaney-Huls K .
Challenges and opportunities for advancing patient-centered clinical decision support: findings from a horizon scan.
J Am Med Inform Assoc 2022 Jun 14;29(7):1233-43. doi: 10.1093/jamia/ocac059.
.
.
Keywords: Clinical Decision Support (CDS), Patient-Centered Healthcare, Health Information Technology (HIT), Shared Decision Making, Patient-Centered Outcomes Research, Evidence-Based Practice
Gallo T, Heise CW, Woosley RL
Clinician responses to a clinical decision support advisory for high risk of Torsades de pointes.
The purpose of this study was to assess provider actions taken in response to a Clinical decision support (CDS) advisory for Torsade de pointes (TdP) that uses a modified Tisdale QT risk score and presents single click management options. The researchers implemented an inpatient TdP risk advisory across a large, 30 hospital health care system. The CDS advisory was programmed to appear when prescribers attempted to order medications with a known risk of TdP in a patient. The CDS advisory displayed patient-specific information and offered related management options including canceling the requested medication and ordering relevant protocols. The study found that 7794 TdP risk advisories were issued during an 8-month period. The most frequent advisory trigger was antibiotics (33.1%.) The most frequent action taken as a result of the advisory was ordering an ECG (20.3%). Incoming medication orders were canceled in 10.2% of the advisories. The researchers concluded that a single-click, modified Tisdale QT risk score-based CDS resulted in a high action/response rate.
AHRQ-funded; HS026662.
Citation: Gallo T, Heise CW, Woosley RL .
Clinician responses to a clinical decision support advisory for high risk of Torsades de pointes.
J Am Heart Assoc 2022 Jun 7;11(11):e024338. doi: 10.1161/jaha.122.024338..
Keywords: Clinical Decision Support (CDS), Shared Decision Making, Health Information Technology (HIT), Heart Disease and Health, Cardiovascular Conditions
Dullabh P, Heaney-Huls K, Hovey L
The technology landscape of patient-centered clinical decision support - where are we and what is needed?
This paper explores the technology landscape for patient-centered clinical decision support (PC CDS) and what has come out of Patient Centered Outcomes Research (PCOR) and health care delivery system transformation efforts. The authors explore what is needed to make it more shareable, standards-based, and publicly available with the goal of improving patient care and clinical outcomes. Three sources of information were used: (1) a 22-member technical expert panel; (2) a literature review of peer-reviewed and grey literature; and (3) key informant interviews with PC CDS stakeholders. Ten salient technical considerations that span all phases of PC CDS development were identified. Although significant progress has been made, challenges remain.
AHRQ-funded; 233201500023I.
Citation: Dullabh P, Heaney-Huls K, Hovey L .
The technology landscape of patient-centered clinical decision support - where are we and what is needed?
Stud Health Technol Inform 2022 Jun 6;290:350-53. doi: 10.3233/shti220094..
Keywords: Clinical Decision Support (CDS), Health Information Technology (HIT), Patient-Centered Outcomes Research, Shared Decision Making
Dullabh P, Heaney-Huls K, Lobach DF
AHRQ Author: Lomotan E, Swiger J, Harrison MI, Dymek C
The technical landscape for patient-centered CDS: progress, gaps, and challenges.
The purpose of this study was to evaluate the technical landscape for patient-centered clinical decision support (PC CDS) methods to assess the gaps in making PC CDS more standard-based, publicly available, and with greater shareability. The researchers utilized qualitative data from a literature review, a panel of technical experts, and interviews with 18 CDS stakeholders to identify 7 technical considerations that span 5 phases of the development of PC CDS. The authors concluded that while there has been progress in the technical landscape, the field of CDS must focus on improving a number of CDS methods and processes, including standards for translating clinical guidelines into patient-centered clinical decision support, procedures to collect, standardize, and incorporate health data generated by patients, and other CDS processes.
AHRQ-authored; AHRQ-funded; 233201500023I.
Citation: Dullabh P, Heaney-Huls K, Lobach DF .
The technical landscape for patient-centered CDS: progress, gaps, and challenges.
J Am Med Inform Assoc 2022 May 11;29(6):1101-05. doi: 10.1093/jamia/ocac029..
Keywords: Clinical Decision Support (CDS), Shared Decision Making, Patient-Centered Healthcare, Health Information Technology (HIT)
Rice H, Garabedian PM, Shear K
Clinical decision support for fall prevention: defining end-user needs.
The purpose of this study was to identify patient and primary care staff needs for development of a tool that will generate clinical decision support (CDS) to prevent falls and injuries in older adults. Community-dwelling patients aged 60 and over and primary care clinic staff were eligible to participate in the study; all were affiliated with the University of Florida Health Archer Family Health Care primary care clinic and the Brigham & Women's Hospital-affiliated primary care clinics. Through qualitative interviews with patients (n=18) and primary care clinic staff (n=24) user needs were identified and then categorized into the following themes: evidence-based safe exercises; expert guidance; individualized resources; in-person assessment of patient condition; motivational tools; patient understanding of fall risk; personal support networks; systematic communication and workload burden. The study concluded that personalized, actionable, and evidence-based clinical decision support may be able to address some of the many gaps that exist in fall prevention management in older adults.
AHRQ-funded; HS027557.
Citation: Rice H, Garabedian PM, Shear K .
Clinical decision support for fall prevention: defining end-user needs.
Appl Clin Inform 2022 May;13(3):647-55. doi: 10.1055/s-0042-1750360..
Keywords: Elderly, Falls, Prevention, Clinical Decision Support (CDS), Shared Decision Making, Health Information Technology (HIT)
Jacobsohn GC, Leaf M, Liao F
Collaborative design and implementation of a clinical decision support system for automated fall-risk identification and referrals in emergency departments.
The authors used a collaborative and iterative approach to design and implement an automated clinical decision support system (CDS) for Emergency Department (ED) providers to identify and refer older adult ED patients at high risk of future falls. The system was developed using collaborative input from an interdisciplinary design team and integrated seamlessly into existing ED workflows. A key feature of development was the unique combination of patient experience strategies, human-centered design, and implementation science, which allowed for the CDS tool and intervention implementation strategies to be designed simultaneously. Challenges included: usability problems, data inaccessibility, time constraints, low appointment availability, high volume of patients, and others. The study concluded that using the collaborative, iterative approach was successful in achieving all project goals, and could be applied to other cases.
AHRQ-funded; HS024558.
Citation: Jacobsohn GC, Leaf M, Liao F .
Collaborative design and implementation of a clinical decision support system for automated fall-risk identification and referrals in emergency departments.
Healthc 2022 Mar;10(1):100598. doi: 10.1016/j.hjdsi.2021.100598..
Keywords: Elderly, Clinical Decision Support (CDS), Shared Decision Making, Falls, Risk, Emergency Department, Health Information Technology (HIT)
Lin E, Uhler LM, Finley EP
Incorporating patient-reported outcomes into shared decision-making in the management of patients with osteoarthritis of the knee: a hybrid effectiveness-implementation study protocol.
This article describes a US-based 2-year, two-site hybrid type 1 study to assess clinical effectiveness and implementation of a machine learning-based patient decision aid integrating patient-reported outcomes and clinical variables to support shared decision-making for patients with knee osteoarthritis considering total knee replacement. Study results will be disseminated through conference presentations, publications and professional societies.
AHRQ-funded; HS027037.
Citation: Lin E, Uhler LM, Finley EP .
Incorporating patient-reported outcomes into shared decision-making in the management of patients with osteoarthritis of the knee: a hybrid effectiveness-implementation study protocol.
BMJ Open 2022 Feb 21;12(2):e055933. doi: 10.1136/bmjopen-2021-055933..
Keywords: Clinical Decision Support (CDS), Shared Decision Making, Arthritis, Patient-Centered Outcomes Research, Orthopedics, Health Information Technology (HIT), Evidence-Based Practice