A Risk Score to Detect Subclinical Rheumatoid Arthritis–Associated Interstitial Lung Disease
Bibliographic record
Abstract
OBJECTIVE: Patients at high risk of rheumatoid arthritis-associated interstitial lung disease (RA-ILD) would benefit from being identified before the onset of respiratory symptoms; this can be done by screening patients with the use of chest high-resolution computed tomography (HRCT). Our objective was to develop and validate a risk score for patients who have subclinical RA-ILD. METHODS: Our study included a discovery population and a replication population from 2 prospective RA cohorts (ESPOIR and TRANSLATE2, respectively) without pulmonary symptoms who had received chest HRCT scans. All patients were genotyped for MUC5B rs35705950. After multiple logistic regression, a risk score based on independent risk factors for subclinical RA-ILD was developed in the discovery population and tested for validation in the replication population. RESULTS: The discovery population included 163 patients with RA, and the replication population included 89 patients with RA. The prevalence of subclinical RA-ILD was 19.0% and 16.9%, respectively. In the discovery population, independent risk factors for subclinical RA-ILD were presence of the MUC5B rs35705950 T allele (odds ratio [OR] 3.74 [95% confidence interval (95% CI) 1.37, 10.39]), male sex (OR 3.93 [95% CI 1.40, 11.39]), older age at RA onset (for each year, OR 1.10 [95% CI 1.04, 1.16]), and increased mean Disease Activity Score in 28 joints using the erythrocyte sedimentation rate (for each unit, OR 2.03 [95% CI 1.24, 3.42]). We developed and validated a derived risk score with receiver operating characteristic areas under the curve of 0.82 (95% CI 0.70-0.94) for the discovery population and 0.78 (95% CI 0.65-0.92) for the replication population. Excluding MUC5B rs35705950 from the model provided a lower goodness of fit (likelihood ratio test, P = 0.01). CONCLUSION: We developed and validated a risk score that could help identify patients at high risk of subclinical RA-ILD. Our findings support an important contribution of MUC5B rs35705950 to subclinical RA-ILD risk.
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 | 0.005 | 0.013 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 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) | 0.002 | 0.001 |
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.
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".