One Hundred Consecutive Granulomas in a Pulmonary Pathology Consultation Practice
Bibliographic record
Abstract
Lung biopsies showing granulomatous disease are commonly sent for expert pathology consultation. On the basis of features we and others have identified, an algorithmic approach to diagnosis of these cases was developed. We hypothesized that applying this approach would increase the likelihood of rendering a more specific diagnosis, or by rendering either a narrower or broader differential diagnosis, offer a more clinically useful diagnosis. One hundred consecutive lung biopsies from patients with granulomatous and giant cell reactions were retrieved from our consultation files. Cases were categorized into those in which a confident diagnosis was made at sign out, ones in which a specific diagnosis was strongly favored, and those in which a differential diagnosis was suggested. One year later follow-up information was obtained and consultation diagnoses were compared with clinical diagnoses to determine the reliability of the approach. A confident diagnosis was rendered in 27 cases, a specific diagnosis was strongly favored in 34, and in 39 a differential diagnosis was provided. Consultant diagnoses were more specific in 47 of 75 (63 %) cases. In 15 cases, the differential diagnosis was expanded. The most common unrecognized diagnosis was aspiration pneumonia and the most common diagnosis omitted from the differential diagnosis by the primary pathologist was hypersensitivity pneumonia. Follow-up in 49% of cases in which it was sought, confirmed the consultant's diagnosis or was inconclusive in 97% of cases. The use of a standardized algorithmic approach to the interpretation of granulomatous disease in lung biopsies yields more specific and clinically useful diagnoses for consideration.
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 | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".