Tailoring surveillance imaging in uveal melanoma based on individual metastatic risk
Bibliographic record
Abstract
Objective To develop surveillance programs for uveal melanoma patients, tailored to metastatic risk. Methods Surveillance schedules were developed using the number needed to scan (NNS) concept, based on weighted average metastasis-free survival (MFS) rates from systematic review data of 18 prognostic groups (Disomy 3 (D3), Monosomy 3 (M3), EIF1AX -mutation, SF3B1 -mutation, BAP1 -mutation, high or low nBAP-1 immunohistochemistry, gene expression profiling classes (1;1A;1B;1 PRAME− ;1 PRAME+ ;2;2 PRAME− ;2 PRAME+ ), and V stages I–III). Results In a typical surveillance schedule, involving biannual examinations years 1–5 and annual examinations years 6–10, the NNS varies dramatically from 1 to nearly infinity, underscoring the necessity for personalized surveillance approaches. On the basis of MFS data from 12 articles ( n = 8046) and the targeted NNS level, the first surveillance examination under our model is recommended from 3 months to 5 years postdiagnosis. Specifically, the NNS 20 strategy requires an average of 10 examinations (SD 7), with D3 patients needing only two examinations (at 2- and 5-years' postdiagnosis), while those in GEP class 2 PRAME+ require up to 17 examinations, scheduled between year 1 and 8. Under an NNS 20 protocol, we anticipate that 1–2% of examinations will lead to the use of effective treatments for metastatic disease, such as tebentafusp. The study presents customized surveillance schedules for all prognostic groups across various NNS levels, accompanied by a methodology for adapting surveillance to any desired NNS target. Conclusion Customizing uveal melanoma surveillance to match metastatic risks could transform current practices, ensuring more precise protocols, reducing unnecessary examinations, and directing health care resources to those in greatest need.
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 | 0.017 | 0.057 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| 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) | 0.003 | 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".