Can current guidelines improve the diagnosis of a usual interstitial pneumonia among general radiologists?
Bibliographic record
Abstract
Current ATS/ERS/JRS/ALAT guidelines on Idiopathic Pulmonary Fibrosis propose criteria to diagnose Usual Interstitial Pneumonia (UIP) on a chest High Resolution Computed Tomography (HRCT); and state that a definite UIP pattern on HRCT obviates the need for surgical biopsy. However, these criteria have not been prospectively validated. Objective: To assess the impact of applying current guidelines in the agreement of UIP diagnosis between general radiologists. Methods: Two general radiologists at a tertiary care academic center in Canada reviewed 128 HRCTs of patients with Interstitial Lung Diseases before and after applying current guidelines to determine the diagnosis of UIP. Results: Before applying the guidelines, the agreement between radiologists of definite UIP was 75% (Kappa 0.475); possible UIP 66% (Kappa 0.126) and inconsistent UIP pattern 78% (Kappa 0.516). After applying the guidelines, the agreement between radiologists of definite UIP was 78% (Kappa 0.525); possible UIP 72% (Kappa 0.378) and inconsistent UIP 88% (Kappa 0.709). The agreement for the presence of reticulation was 95% (Kappa 0.640); honeycombing 85% (Kappa 0.697); subpleural predominance of abnormalities 82% (Kappa 0.385); basilar predominance 73% (Kappa 0.463). Conclusions: Applying the guidelines improved the agreement in the diagnosis of possible UIP and inconsistent UIP, but not of definite UIP. Disagreement in the diagnosis of a definite UIP pattern between radiologists could results in an important variation in the number of patients requiring surgical biopsy to confirm the diagnosis (up to 1 in 4 patients).
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 | 0.065 | 0.328 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.006 | 0.004 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.007 | 0.007 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.009 | 0.005 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".