Abstract 4523: Personalized risk prediction for treatment intolerance in operable HPV-negative head and neck cancer: Beyond the eyeball test
Bibliographic record
Abstract
Abstract Introduction: Head and neck cancer (HNC) treatment is highly complex, with substantial toxicity risks from curative therapies, often including surgery, radiation, and chemotherapy. Poor treatment tolerance can hinder optimal recovery, impacting patient outcomes. Current predictive tools lack precision in forecasting treatment intolerance for HNC patients undergoing curative surgery. Frailty and sarcopenia, especially muscle quantity biomarkers, are increasingly recognized as crucial predictive factors. This study aims to develop a comprehensive risk index incorporating sarcopenia, frailty, and patient-specific factors to better predict intolerance. Methods: An ambispective observational study was conducted with 542 patients undergoing curative-intent HNC surgery from 2015 to 2024. Patient data on demographics, frailty, sarcopenia (via cervical paraspinal muscle index or CPSMI), tumor staging, and planned adjuvant therapy were collected. Using logistic regression, we evaluated predictive factors for treatment intolerance, defined as major adverse events (MAEs) or incomplete treatment. Risk model performance was validated internally and externally and compared against ASA, mFI, and RAI. Results: In 542 patients, lower CPSMI (first tertile) correlated significantly with intolerance (OR 1.85, 95% CI 1.10-3.13). High-density muscle was protective, while low-density muscle predicted intolerance (OR 1.88, 95% CI 1.18-2.99). Sarcopenia and frailty were independently predictive, with the mFI also strongly correlating with intolerance (OR 4.92, 95% CI 1.88-12.9). The new risk index demonstrated superior predictive accuracy, showing a 0.04 increase in the C-statistic compared to existing indices (p=0.02). Conclusion: The multimodal risk index effectively predicts treatment intolerance in HNC surgery patients. By integrating sarcopenia, frailty, and patient-specific factors, the tool enables better preoperative counseling and intervention planning, with particular utility for high-risk individuals. Further research on prehabilitation strategies may enhance treatment tolerance in vulnerable patients, supporting a proactive approach to HNC care. Citation Format: Marco Antonio Mascarella, Keith Richardson, Nader Sadeghi, Alex Mlynarek, Michael Hier, Khalil Sultanem, Christina Tsien, Khashayar Esfahani, Marie-Jeanne Kergoat. Personalized risk prediction for treatment intolerance in operable HPV-negative head and neck cancer: Beyond the eyeball test [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 4523.
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 | 0.003 | 0.011 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".