Statistical approach to mediastinal staging in NSCLC with M.E.S.S.i.a. software
Bibliographic record
Abstract
The exclusion of pathological involvement of mediastinal lymph nodes in patients affected by NSCLC plays a central role in assessing their prognosis and operability. Ceron et al. developed a software - called M.E.S.S.i.a (Mediastinal Evaluation with Statistical Support; instan approach) - that allows the calculation of the residual probability of lymph node involvement after a certain number of tests has been done, by integrating every test result with the pre-test prevalence. M.E.S.S.i.a. bridges a gap of current American College of Chest Physicians (ACCP) guidelines, providing probability values of mediastinal metastasis for a correct clinical decision. We conducted a preliminary retrospective study in a series of 108 patients affected by non small cell lung cancer (NSCLC). Pathological staging was compared to the probability of nodal involvement calculated by M.E.S.S.i.a. software. Forty-two out of 108 subjects (39%) had a calculated post-test probability <8%; none of these had proven N2/N3 metastasis at surgical staging (negative predictive value, NPV: 100%). In 12/41 cases M.E.S.S.i.a. was able to avoid invasive procedures. The remaining 66 (61%) patients did not reach the surgical threshold; among these, 11 displayed N2 positivity at pathological staging. Receiving operator curve (ROC) analysis produced an area under curve (AUC) value of 0.773 (p<0.001). These preliminary data show high accuracy of M.E.S.S.i.a. software in excluding N2/N3 lymph node involvement in NSCLC. We have therefore promoted a prospective multicenter study in order to to get a validation of the calculator at different levels of probability of lymph node involvement. The recruitable subjects are potentially operable NSCLC patients; the gold standard for detection of mediastinal disease is the surgical lymph node dissection.
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 | 0.030 | 0.080 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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".