Individualizing Follow-Up Strategies in High-Grade Soft Tissue Sarcoma with Flexible Parametric Competing Risk Regression Models
Bibliographic record
Abstract
Currently, patients with extremity soft tissue sarcoma (eSTS) who have undergone curative resection are followed up by a heuristic approach, not covering individual patient risks. The aim of this study was to develop two flexible parametric competing risk regression models (FPCRRMs) for local recurrence (LR) and distant metastasis (DM), aiming at providing guidance on how to individually follow-up patients. Three thousand sixteen patients (1931 test, 1085 validation cohort) with high-grade eSTS were included in this retrospective, multicenter study. Histology (9 categories), grading (time-varying covariate), gender, age, tumor size, margins, (neo)adjuvant radiotherapy (RTX), and neoadjuvant chemotherapy (CTX) were used in the FPCRRMs and performance tested with Harrell-C-index. Median follow-up was 50 months (interquartile range: 23.3-95 months). Two hundred forty-two (12.5%) and 603 (31.2%) of test cohort patients developed LR and DM. Factors significantly associated with LR were gender, size, histology, neo- and adjuvant RTX, and margins. Parameters associated with DM were margins, grading, gender, size, histology, and neoadjuvant RTX. C-statistics was computed for internal (C-index for LR: 0.705, for DM: 0.723) and external cohort (C-index for LR: 0.683, for DM: 0.772). Depending on clinical, pathological, and patient-related parameters, LR- and DM-risks vary. With the present model, implemented in the updated Personalised Sarcoma Care (PERSARC)-app, more individualized prediction of LR/DM-risks is made possible.
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 | 0.023 | 0.038 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".