Eight-Signature Classifier for Prediction of Nasopharyngeal Carcinoma Survival
Bibliographic record
Abstract
PURPOSE: Currently, nasopharyngeal carcinoma (NPC) prognosis evaluation is based primarily on the TNM staging system. This study aims to identify prognostic markers for NPC. PATIENTS AND METHODS: We detected expression of 18 biomarkers by immunohistochemistry in NPC tumors from 209 patients and evaluated the association between gene expression level and disease-specific survival (DSS). We used support vector machine (SVM)--based methods to develop a prognostic classifier for NPC (NPC-SVM classifier). Further validation of the NPC-SVM classifier was performed in an independent cohort of 1,059 patients. RESULTS: The NPC-SVM classifier integrated patient sex and the protein expression level of seven genes, including Epstein-Barr virus latency membrane protein 1, CD147, caveolin-1, phospho-P70S6 kinase, matrix metalloproteinase 11, survivin, and secreted protein acidic and rich in cysteine. The NPC-SVM classifier distinguished patients with NPC into low- and high-risk groups with significant differences in 5-year DSS in the evaluated patients (87% v 37.7%; P < .001) in the validation cohort. In multivariate analysis adjusted for age, TNM stage, and histologic subtype, the NPC-SVM classifier was an independent predictor of 5-year DSS in the evaluated patients (hazard ratio, 4.9; 95% CI, 3.0 to 7.9) in the validation cohort. CONCLUSION: As a powerful predictor of 5-year DSS among patients with NPC, the newly developed NPC-SVM classifier based on tumor-associated biomarkers will facilitate patient counseling and individualize management of patients with NPC.
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 | 0.001 | 0.004 |
| 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 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".