A new colorectal cancer risk prediction model incorporating family history, personal and environmental factors
Bibliographic record
Abstract
Abstract Purpose Reducing colorectal cancer (CRC) incidence and mortality through early detection would improve efficacy if targeted. A CRC risk-prediction model incorporating personal, family, genetic and environmental risk factors could enhance prediction. Methods We developed risk-prediction models using population-based CRC cases (N=4,445) and controls (N=3,967) recruited by the Colon Cancer Family Registry Cohort (CCFRC). A familial risk profile (FRP) was calculated to summarize individuals’ risk based on their CRC family history, family structure, germline mutation probability in major susceptibility genes, and a polygenic component. Using logistic regression, we developed risk models including individuals’ FRP or a binary CRC family-history (FH), and risk factors collected at recruitment. Model validation used follow-up data for population-(N=12,052) and clinic-based (N=5,584) relatives with no cancer history at recruitment, assessing calibration (E/O) and discrimination (AUC). Results The E/O (95% confidence interval [CI]) for FRP models for population-based relatives were 1.04 (0.74-1.45) and 0.86 (0.64-1.20) for men and women, and for clinic-based relatives 1.15 (0.87-1.58) and 1.04 (0.76-1.45). The age-adjusted AUC (95% CI) for FRP models in population-based relatives were 0.69 (0.60-0.78) and 0.70 (0.62-0.77), and for clinic-based relatives 0.77 (0.69-0.84) and 0.68 (0.60-0.76). The incremental values of AUC (95% CI) for FRP over FH models for population-based relatives were 0.08 (0.01-0.15) and 0.10 (0.04-0.16), and for clinic-based relatives 0.11 (0.05-0.17) and 0.11 (0.06-0.17). Conclusion The FRP-based model and FH-based model calibrate well in both settings. The FRP-based model provided better risk-prediction and discrimination than the FH-based model. A detailed family history may be useful for targeted risk-based screening and clinical management.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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) | 0.002 | 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".