Development of a prediction model for tube feeding dependence in HPV-associated oropharyngeal cancer patients undergoing chemoradiotherapy
Bibliographic record
Abstract
OBJECTIVES: This study aimed to develop a prediction model for feeding tube dependence in a large homogenous cohort of HPV-associated oropharyngeal squamous cell carcinoma (HPV + OPSCC) patients receiving chemoradiotherapy (CRT). We further aimed to externally validate three previously published feeding tube prediction models on this cohort. MATERIALS AND METHODS: p16-confirmed HPV + OPSCC patients treated with definitive CRT at a tertiary cancer centre between April 2017 and February 2022 were identified. The primary endpoint was G-tube dependence, defined as enteral feeding for ≥ 4 weeks following CRT. Clinical and dosimetric data were extracted from electronic patient records. Multivariable analyses (MVA) assessed the associations of potential predictors with G-tube dependence. The discriminatory performance of three previously published models was assessed on this cohort using the area under the receiver operating curve (AUC), and calibration was evaluated with calibration plots. RESULTS: A total of 291 patients were included (TNM8 stage I: 129; II:67; III: 95). MVA identified Dmean to the superior pharyngeal constrictor muscle, D70% to the middle pharyngeal constrictor muscle, and modified diet texture at baseline as predictive for G-tube dependence, with the AUC of 0.68. External validation of three existing models yielded an AUC of 0.60, 0.63, and 0.67, with no evidence of good calibration. CONCLUSION: Despite a sizable cohort and comprehensive capture of dosimetric information, our prediction model, and external validation of previously published models, showed moderate performance. This suggests that additional factors beyond disease and treatment may need to be considered in future models to refine nutrition support decisions.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".