Machine Learning in Differentiated Thyroid Cancer Recurrence and Risk Prediction
Bibliographic record
Abstract
Differentiated thyroid cancer (DTC) poses significant management challenges due to the variable risk of recurrence. This study uses a dataset comprising clinical, pathological, and treatment data from 383 patients to develop and validate machine learning models, combined with feature selection algorithms, for predicting differentiated thyroid cancer recurrence. We evaluated models based on a variety of machine learning technologies (light gradient boosting machine, random forest, k-nearest neighbor, logistic regression, stochastic gradient descent, and an emerging deep learner optimized for tabular data: Gandalf) combined with several feature selection methods. Our feature selection technologies include an emerging redundancy-aware wrapper-based feature selection technique, achieving thyroid cancer recurrence prediction accuracy of 94.8 to 95.9% across two validation methods, based only on whether the patient’s tumor’s response was structurally incomplete, whether their tumor’s stage was advanced (III, IVA, or IVB), and the patient’s age. The results underline the potential for machine learning to enhance the precision of recurrence prediction in DTC while developing technologies whose predictive capacity is more easily explained. Using the same dataset, machine learning and feature selection techniques, this study also provides an analysis on predicting American Thyroid Association (ATA) risk scores. The technologies developed as part of this study have potential for improving the personalization of healthcare through the creation of models based on detailed patient-specific clinical attributes.
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 | 0.006 | 0.013 |
| 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) | 0.000 | 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".