Real-world prognostic model for malignant pleural mesothelioma.
Bibliographic record
Abstract
e20562 Background: Two mesothelioma prognostic models have been suggested: European Organisation for Research and Treatment of Cancer (EORTC) and Cancer and Leukaemia Group B (CALGB) models. Both were based on clinical trial patients enrolled in the mid-1980s to early-1990s. Several changes to mesothelioma management have been adopted since publication of these models, including improved surgical and palliative interventions and changes to systemic therapy. Methods: With ethics approval, we collected and analyzed the health data of malignant pleural mesothelioma (MPM) patients with histologically confirmed diagnosis treated at our institution between January 1991 and March 2019. The primary endpoint was overall survival (OS). Univariate analysis was used to identify significant predictors of survival, which were then used to construct a multivariate survival tree with complete case-analysis and bootstrapping. Patients were then stratified into three prognostic groups based on their median OS. Results: 337 patients were included in the study; 309 (91.7%) were dead at last follow-up. The median OS was 9.4 (8.1-11.5) months for the entire population. Eastern Cooperative Oncology Group (ECOG) performance status (PS), histology, white blood count, platelets, International Mesothelioma Interest Group stage, age and hemoglobin were independent predictors of survival. The final pruned survival tree was based on 285 patients and incorporated the first five predictors. Good, intermediate and poor prognostic groups had median OS of > 12 months, 6-12 months, and < 6 months, respectively. Factors associated with the prognostic groups were: good prognosis: ECOG 0-1, normal platelets, stage 1, 2 and epithelioid histology; intermediate prognosis: ECOG 0-1 with either stage 3, 4 and/or sarcomatoid or biphasic histology; poor prognosis: ECOG 2-4 regardless of other factors. Conclusions: In contrast to EORTC/CALGB, real world evidence generates these prognostic groups with face validity but will need independent validation. Our data does not account for recent advances including immunotherapy, and thus patients with non-epithelioid histology may have better survival than predicted.[Table: see text]
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".