Impact of a Bayesian approach on the diagnosis of Interstitial Lung Diseases
Bibliographic record
Abstract
Introduction: Current guidelines recommend a multi-disciplinary team (MDT) approach involving experienced pulmonologists, radiologists and pathologists in improving the confidence in diagnosing various interstitial lung diseases (ILD). However, accurately diagnosing fibrotic ILD remains a challenge with significant diagnostic heterogeneity, impacting the management and prognosis of patients. Aims: We evaluate the effects of implementing a Bayesian approach, incorporating clinical judgment, pre-test probability and radiological features, in improving the diagnosis of fibrotic ILD and reducing the number of unclassifiable ILD without the need for a surgical lung biopsy.(1) Methods: This is a prospective study of consecutive patients referred for MDT assessment from April 2015 to December 2018. We compared diagnostic categories and level of confidence between 2 groups of patients before and after the implementation of a Bayesian approach in ILD diagnosis.(1) Results: We report on the first 125 patients. The Bayesian approach was used in 46 (37%) patients. The proportion of cases with a confident diagnosis of idiopathic pulmonary fibrosis (IPF) was 25% and 22%, before and after the use of the approach, respectively (p=0.65). There was a trend towards a decrease in the proportion of cases with unclassifiable ILD, from 17% to 7% (p=0.11). Conclusion: A Bayesian approach in MDT discussion may reduce the number of cases with unclassifiable disease and improve the diagnostic classification of fibrotic ILD without the need for surgical biopsy. Further studies are needed on the utility and impact of this approach on subsequent management and patient-related outcomes. Reference: (1)Ryerson et al. Am J Respir Crit Care Med. 2017;196:1249
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 | 0.019 | 0.111 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".