The International Association for the Study of Lung Cancer Pleural Mesothelioma Staging Project: Updated Modeling of Prognostic Factors in Pleural Mesothelioma
Bibliographic record
Abstract
INTRODUCTION: The International Association for the Study of Lung Cancer developed an international pleural mesothelioma database to improve staging. Data entered from 1995 to 2009 (training data set) were analyzed previously to evaluate supplemental prognostic factors. We evaluated these factors with new clinical data to determine whether the previous models could be improved. METHODS: Patients entered into the database from 2009 to 2019 (validation cohort) were assessed for the association between previous prognosticators and overall survival using Cox proportional hazards regression with bidirectional stepwise selection. Additional variables were analyzed and models were compared using Harrell's C-index. RESULTS: The training data set included 3101 patients and the validation cohort, 1733 patients. For the multivariable pathologic staging model applied to the training cohort, C-index was 0.68 (95% confidence interval [CI]: 0.656-0.705). For the validation data set (n = 497), C-index was 0.650 (95% CI: 0.614-0.685), and pathologic stage, histologic diagnosis, sex, adjuvant therapy, and platelet count were independently associated with survival. Adding anemia to the model increased the C-index to 0.652 (95% CI: 0.618-0.686). A basic presentation model including all parameters before staging yielded a C-index of 0.668 (95% CI: 0.641-0.695). In comparison, the European Organization for Research and Treatment of Cancer model yielded C-indices of 0.550 (95% CI: 0.511-0.589) and 0.577 (95% CI: 0.550-0.604) for pathologic staging and presentation models, respectively. CONCLUSIONS: Although significant predictors differed slightly, the International Association for the Study of Lung Cancer training model performed well in the validation set and better than the model of the European Organization for Research and Treatment of Cancer. International collaboration is critical to improve outcomes in this rare disease.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".