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 3 of 3 Research Studies DisplayedMarshall IJ, Noel-Storr A, Kuiper J
Machine learning for identifying randomized controlled trials: an evaluation and practitioner's guide.
The purpose of this study was to evaluate machine learning models for RCT classification. Models were evaluated on an external dataset. The authors demonstrate that machine learning approaches are better able to discriminate between RCTs and non-RCTs than traditional database search filters, and also provide practical guidance on the role of machine learning in systematic reviews, and rapid reviews and clinical question answering as well as an open-source software.
AHRQ-funded; HS025024.
Citation: Marshall IJ, Noel-Storr A, Kuiper J .
Machine learning for identifying randomized controlled trials: an evaluation and practitioner's guide.
Res Synth Methods 2018 Dec;9(4):602-14. doi: 10.1002/jrsm.1287..
Keywords: Evidence-Based Practice, Health Services Research (HSR), Research Methodologies
Surian D, Dunn AG, Orenstein L
A shared latent space matrix factorisation method for recommending new trial evidence for systematic review updates.
The purpose of this study was to evaluate a new method to partially automate the identification of trial registrations that may be relevant for systematic review updates. After identifying 179 systematic reviews of drug interventions for type 2 diabetes, researchers tested a matrix factorization approach that ranks relevant trial registrations for each review. Text from the trial registrations were also used as features. These two approaches were tested on a holdout set of the newest trials. The authors conclude that this matrix was useful in ranking trial registrations and could be used as part of a semi-automated pipeline.
AHRQ-funded; HS024798.
Citation: Surian D, Dunn AG, Orenstein L .
A shared latent space matrix factorisation method for recommending new trial evidence for systematic review updates.
J Biomed Inform 2018 Mar;79:32-40. doi: 10.1016/j.jbi.2018.01.008..
Keywords: Evidence-Based Practice, Health Services Research (HSR), Research Methodologies
Thorlacius L, Garg A, Ingram JR
Towards global consensus on core outcomes for hidradenitis suppurativa research: an update from the HISTORIC consensus meetings I and II.
This article describes the outcome of two in-person consensus meetings to create a core outcomes set (COS) for hidradenitis suppurative (HS) research. Forty-one individuals from 13 countries and 4 continents were included. The list of items discussed had been developed from patient interviews, a systematic literature review and a healthcare professional survey. Nine items were excluded and seven domains were approved which included: disease course, physical signs, HS-specific quality of life, satisfaction, symptoms, pain and global assessments.
AHRQ-funded; HS024585.
Citation: Thorlacius L, Garg A, Ingram JR .
Towards global consensus on core outcomes for hidradenitis suppurativa research: an update from the HISTORIC consensus meetings I and II.
Br J Dermatol 2018 Mar;178(3):715-21. doi: 10.1111/bjd.16093..
Keywords: Evidence-Based Practice, Health Services Research (HSR), Outcomes, Research Methodologies, Skin Conditions