A Prognostic Model Generated from an Apparent Diffusion Coefficient Ratio Reliably Predicts the Outcomes of Oral Tongue Squamous Cell Carcinoma
Bibliographic record
Abstract
This study aimed to develop an apparent diffusion coefficient (ADC) ratio-based prognostic model to predict the recurrence and disease-free survival (DFS) of oral tongue squamous cell carcinoma (OTSCC). A total of 188 patients with cT1-2 oral tongue squamous cell carcinoma were enrolled retrospectively. Clinical and laboratory data were extracted from medical records. The ADC values were measured at the regions of interest of the tumor and non-tumor tissues of the MRI images, and the ADC ratio was used for comparison between the patient with recurrence (n = 83 case, 44%) and patients without recurrence (n = 105 cases, 56%). Cox proportional hazards models were generated to analyze the risk factors of cancer recurrence. A nomogram was developed based on significant risk factors to predict 1-, 5- and 10-year DFS. The receiver operator characteristic (ROC) curves of predictors in the multivariable Cox proportional hazards prognostic model were generated to predict the recurrence and DFS. The integrated areas under the ROC curve were calculated to evaluate discrimination of the models. The ADC ratio, tumor thickness and lymph node ratio were reliable predictors in the final prognostic model. The final model had a 71.1% sensitivity and an 81.0% specificity. ADC ratio was the strongest predictor of cancer recurrence in prognostic performance. Discrimination and calibration statistics were satisfactory with C-index above 0.7 for both model development and internal validation. The calibration curve showed that the 5- and 10-year DFS predicted by the nomogram agreed with actual observations.
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 | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".