Disease Activity Assessment Frequency in Rheumatoid Arthritis: A Retrospective Observational Study of the Medical Support System for Rheumatoid Arthritis System Implementation
Bibliographic record
Abstract
Background: Rheumatoid arthritis (RA) is a global health concern with increasing prevalence. Despite recommendations for regular disease activity assessments, their implementation in routine clinical practice remains challenging. The Medical Support System for Rheumatoid Arthritis (MiRAi) is an offline, semi-automated system that calculates disease activity indices by integrating patient and clinician inputs from electronic health records (EHRs). Objective: This study evaluated the association between MiRAi implementation and the frequency of disease activity assessments in patients with RA. Methods: We conducted a retrospective cohort study of patients with RA treated at a tertiary hospital in Japan between April 2022 and March 2023. We included all adult outpatients (aged ≥18 years) with RA diagnosed according to the 2010 ACR/EULAR [American College of Rheumatology/European Alliance of Associations for Rheumatology] classification criteria. The hospital introduced MiRAi in June 2022 and achieved full deployment by October 2022. MiRAi calculated the clinical disease activity index (CDAI) and the modified health assessment questionnaire (mHAQ) through automated extraction of joint counts, patient global assessment, and functional status from structured EHR fields. Primary outcomes included the frequency of CDAI and mHAQ assessments. We administered a structured post-implementation survey to assess rheumatologists' perceptions of MiRAi. Results: Physicians used MiRAi for 236/884 (26.7%) patients with RA. Patients with documented CDAI and mHAQ scores increased from 29 (5.9%) in June 2022 to 81 (19.0%) in November 2022, representing a 3.2-fold increase. Among surveyed rheumatologists (n=10), 5 (50%) reported the regular use of MiRAi. Physicians who regularly used MiRAi (n=5) cited improved accuracy in disease assessment and enhanced treatment decision-making. Non-users and occasional users (n=5) identified three primary barriers: limited familiarity with MiRAi, time constraints, and discrepancies between clinical judgment and MiRAi-generated outputs. Despite MiRAi's availability, only 168 (19%) patients underwent quantitative disease activity assessment by the study end. Among 15 patients with high disease activity (CDAI >22), physicians recorded 3 treatment modifications and 2 intra-articular steroid injections. Conclusions: MiRAi implementation increased disease activity assessment frequency by 3.2-fold over 6 months; however, physician adoption remained at 26.7%, below the 80% target for routine care. Future implementation strategies should address identified barriers through system integration, structured user training, and workflow optimization to achieve guideline-concordant care for patients with RA.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".