EUVIMEDEUVIMED entdecken
Crossref

Redefining Prognostic Risk in Colorectal Cancer: Calibrated Deep Learning Reclassifies High-Risk Mortality and Mitigates Overtreatment

Fengmei Yi

Proceedings of Anticancer Research · 14.04.2026 · 10 (2) · 89-99

DOI: 10.26689/par.v10i2.14542 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of Anticancer Research, online erschienen am 14.04.2026. Verfasst von Fengmei Yi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prognostic risk stratification is critical for colorectal cancer (CRC), yet traditional linear models are limited by complex non-linear multi-omics interactions. We compared three mainstream survival models (regularized Cox, random survival forests [RSF], and DeepSurv) via multi-scenario simulations spanning linear to strongly non-linear risks, with rigorous validation in TCGA (n = 610) and independent GEO (n = 566) cohorts using a five-dimensional evaluation framework, plus blinded isotonic regression for model calibration. DeepSurv showed significant predictive superiority in non-linear scenarios, achieving a global C-index of 0.7820 in TCGA (vs 0.7610 for regularized Cox), 42.18% net reclassification improvement for high-risk mortality patients, and 20.60% reduced prediction error after calibration, with robust external validation performance. The regularized Cox model remained robust for linear low-dimensional data. In conclusion, calibrated DeepSurv is optimal for high-risk CRC identification in complex multi-omics data, providing a standardized paradigm for survival model selection.

Zitieren

APA

Yi, F. (2026). Redefining Prognostic Risk in Colorectal Cancer: Calibrated Deep Learning Reclassifies High-Risk Mortality and Mitigates Overtreatment. Proceedings of Anticancer Research, 10(2), 89-99. https://doi.org/10.26689/par.v10i2.14542

Vancouver

Yi F. Redefining Prognostic Risk in Colorectal Cancer: Calibrated Deep Learning Reclassifies High-Risk Mortality and Mitigates Overtreatment. Proceedings of Anticancer Research. 2026;10(2):89-99. doi:10.26689/par.v10i2.14542

BibTeX
@article{Yi2026,
  author = {Yi, Fengmei},
  title = {Redefining Prognostic Risk in Colorectal Cancer: Calibrated Deep Learning Reclassifies High-Risk Mortality and Mitigates Overtreatment},
  journal = {Proceedings of Anticancer Research},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {89--99},
  doi = {10.26689/par.v10i2.14542}
}
Kostenlos starten →