Clinical Utility of Lymph Node Features during EBUS
Bibliographic record
Abstract
Background: At the time of endobronchial ultrasound (EBUS) staging, ultrasonographic features can be used to predict mediastinal lymph node (LN) malignancy. Predictive tools have been developed, however they have not gained widespread use due to lack of research demonstrating validity and reliability. We sought to develop a novel predictive tool, the Canada Score, capable of predicting malignancy and potentially guide LN biopsy decision making. Methods: We prospectively analyzed the ultrasonographic features of LNs from patients with NSCLC. Ultrasonographic features were identified by a single experienced endoscopist, this data was used to develop the Canada Score. Pathological specimens were used as the gold standard for determination of malignancy. Videos were then circulated to endoscopists across Canada, who were also asked to identify ultrasonographic features for each LN. Hosmer- Lemeshow test, logistic regression, receiver operator characteristic (ROC) curve, and Gwet’s AC1 analyses were used to test the performance, discriminatory capacity, and inter-rater reliability of the Canada Score. Results: A total of 300 LNs from 140 patients were analyzed by 12 endoscopists across 7 Canadian centres. Backwards elimination was used to create a multivariate model. Hosmer-Lemeshow test and ROC curves indicated the model was well-calibrated (chi2=11.86, p=0.1567) with good discriminatory power (c- statistic= 0.72 ±0.042, 95%CI: 0.64-0.80). Beta-coefficients were used to create a simplified score out of four. Evaluation of the tool showed that LNs scoring 3 or 4 had odds ratios of 15.17 (p<0.0001) and 50.56 (p=0.001), respectively for predicting malignancy. A score of 4/4 was associated with 99.59% specificity and a positive likelihood ratio of 22.78. Inter-rater reliability for a score ≥ 3 was 0.81 ± 0.02 (95%CI: 0.77-0.85). Conclusions: The Canada Score shows excellent performance in identifying malignant LN at the time of EBUS. A cut-off of ≥ 3 has the potential to inform decision-making regarding biopsy or repeat/mediastinoscopy if the initial results are inconclusive.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".