MétaCan
Menu
← Back to cohort

Implementation of a Data-Driven Learning Health System in Rheumatology: A Novel Application of Dashboard Quality Reporting to Support Optimal Rheumatoid Arthritis Care

2025· article· en· W4411884091 on OpenAlexaffvenueabout
Racheal Githumbi, Kevin Lonergan, Steven J. Katz, Ania Kania‐Richmond, Kim Giroux, Yvonne Wallace, C Allyson Jones, Amanda Steiman, Anshula Ambasta, Cheryl Barnabé, Elaine Yacyshyn, Diane Lacaille, Glen Hazlewood, Jessica Widdifield, Tyler Williamson, Claire Barber

Bibliographic record

VenueThe Journal of Rheumatology · 2025
Typearticle
Languageen
FieldMedicine
TopicRheumatoid Arthritis Research and Therapies
Canadian institutionsSunnybrook Health Science CentreSunnybrook HospitalMount Sinai HospitalResearch CanadaNorth American Construction Group (Canada)Calgary Laboratory ServicesAlberta Health ServicesRed Deer PolytechnicArthritis Research Centre of CanadaUniversity of CalgaryUniversity of Alberta
Fundersnot available
KeywordsOperationalizationMedicineHealth careQuality managementDashboardData qualityLeverage (statistics)Data scienceComputer scienceOperations managementArtificial intelligence

Abstract

fetched live from OpenAlex

Objectives Learning Health Systems (LHS) leverage healthcare data to drive cycles of knowledge generation for continuous care quality improvement. In Alberta, the recent launch of a provincial health information system (Connect Care, Epic Corporation) that interfaces with analytical and reporting tools, supports the use of routinely collected regional clinical data for care quality improvement efforts. As such, this project aims to implement a provincial LHS to support optimal care for Albertans with rheumatoid arthritis (RA). Methods This was a multiphase project. In Phase 1, we identified a starter set of quality measures. Candidate measures were reviewed for feasibility of operationalization using structured data in Connect Care along with linkage to other administrative datasets (physician billing, pharmacy data, discharge abstract database). In Phase 2, a shortlist of eligible measures that aligned with national measurement priorities were ranked by panelists including providers, field-experts and patient partners. In Phase 3, we operationalized and reported on these measures as dashboards. To do so, a case definition of RA and a list of eligible providers were identified. These definitions were validated by chart reviews completed by 2 rheumatologists and an analyst. The resulting data were reported as dynamic and interactive dashboards on Tableau using near to real-time data from the linked datasets. Dashboards allow providers to access patient-level data on their practice to support quality improvement. Results From a shortlist of eighteen measures, 9 were prioritized by a panel of providers, experts and patient partners (n=7). We developed the following dashboards to display an initial set of measures: 1) number of RA patients followed per practice/site; 2) wait times to first rheumatology consult; 3) RA disease activity assessment (process and outcome measures); 4) gaps in care (lost to follow-up, treatment, or lab monitoring). As of 09/20/2024 there were 8059 individuals with RA under rheumatology care at 4 sites. Only 44% of 6668 encounters had a documented joint count, and 24% had a composite disease activity score calculated. Of the 1600 encounters with a composite score, 17% of patients were in low disease activity/remission. We identified 1,770 individuals with >12 months between rheumatology visits. Only 24% of individuals with RA were seen by a rheumatologist within 6 weeks of referral. Conclusion Using an LHS approach, we aim to shorten and streamline the cycles of transforming data into actionable knowledge for optimized care. We are working with our provincial partners to identify appropriate strategies to address the identified gaps. Practice Reflection Award

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.022
metaresearch head score (Gemma)0.040
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.022
Threshold uncertainty score0.118

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0220.040
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0010.001
Scholarly communication0.0060.003
Open science0.0040.005
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.042
GPT teacher head0.405
Teacher spread0.363 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes3
Has abstractyes

Explore more

Same venueThe Journal of Rheumatology→Same topicRheumatoid Arthritis Research and Therapies→French-language works237,207→