Combined clinical and genetic risk prediction of central nervous system subsequent neoplasms (CNS SNs) in childhood cancer survivors (CCS): A report from the COG ALTE03N1 study.
Bibliographic record
Abstract
10511 Background: CCS are at a 10-fold increased risk of CNS SNs. Cranial radiation (CRT) for primary cancer increases the risk; dose-risk relation with CRT is linear. The substantial burden of CNS SN-related morbidity presents an unmet need for identifying high-risk patients to guide targeted interventions. We present a risk prediction model to address this gap. Methods: CCS with CNS SNs (cases: n=82) matched to CCS without CNS SNs (controls: n=228; matched on primary cancer diagnosis (dx), year of dx, race/ethnicity and follow-up), contributed germline DNA for genotyping 43 previously published candidate genes (97 SNPs). Risk prediction models were derived sequentially: Base Model (age at primary cancer dx, gender), Clinical Model (Base Model + CRT [Y/No]), Final Model (Clinical Model + SNPs). Receiver operating characteristic analysis was used to evaluate predictive utility of Final Model in assessing CNS SN risk. Two risk groups were derived using predicted values (high risk: ≥0.1; low risk: <0.1). Results: Median age at primary cancer dx was 3.5y (cases) and 5.0y (controls); time to CNS SNs was 13.2y; 91.5% of cases and 39.5% of controls had received CRT (p<0.001). Clinical Model (area under curve [AUC] = 0.82, 95%CI: 0.8-0.9) performed better than Base Model (AUC = 0.58, 95%CI, 0.5-0.7, p=0.001). Final Model performed best when five SNPs involved in DNA repair (forward stepwise selection: rs1805389 [LIG4], rs15869 [BRCA2], rs8079544 [TP53], rs498872 [PHLDB1], rs1673041 [POLD1]) were included (AUC = 0.86, 95%CI, 0.8-0.9, p = 0.04; reference: Clinical Model). Using high vs. low risk group as risk classifier, the accuracy of the prediction model was 91.7%, with a sensitivity of 96.3% and specificity of 57%. Similar observations emerged in analyses stratified by CNS SN type (meningioma [n=46]/ glioma [n=28]) and analyses restricted to CCS with CRT. Conclusions: We have developed a combined clinical and genetic risk prediction model that accurately identifies CCS at high and low risk of CNS SNs. This model, when validated externally, could serve as a useful risk classifier to assess the risk of CNS SNs when CRT is being considered.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".