How Breast Cancer Survival Predictions Change over Time: A Large SEER Study of Model Calibration and Updating
Informatics · 29.10.2026 · 13 (11) · 181
DOI: 10.3390/informatics13110181 ↗Kurz gefasst
Fachartikel in der Zeitschrift Informatics, online erschienen am 29.10.2026. Verfasst von Ayan Kokhan und 2 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan.
Abstract (Originalsprache)
Background/Objectives: Survival models can retain their ability to rank patients while their absolute-risk predictions become less accurate over time. We compared temporal calibration drift and updating across statistical and machine-learning models under competing risks.
Methods
This retrospective SEER study included 881,201 women with breast cancer. Cause-specific ridge Cox, elastic-net Cox, random survival forest, and DeepSurv models were trained on diagnoses from 2004–2007 and evaluated across five two-year eras from 2008–2017. We compared fixed prediction, isotonic recalibration using the preceding two-year window, and refitting using the preceding four-year window for 5-year mortality.
Results
Fixed-model breast cancer-specific mortality overprediction increased from 0.52–1.22 percentage points (pp) in 2008–2009 to 1.55–2.41 pp in 2016–2017. Discrimination remained stable or improved slightly; the latest-era inverse-probability-of-censoring-weighted area under the curve was 0.870–0.884. Latest-era residual mean calibration bias was at most 0.36 pp after isotonic recalibration and 0.57–0.97 pp after refitting. The coupled-bootstrap interval for the random survival forest bias difference included zero; refitting yielded lower Brier scores for random survival forest and DeepSurv. Calibration patterns differed by age and predicted risk. Three families first exceeded the illustrative 2-pp reference value in 2016–2017; random survival forest remained below it.
Conclusions
Recalibration reduced average bias, but its advantage depended on the model and metric. Prospective evaluation must account for delayed outcome availability before these updating protocols can inform clinical practice.
Förderung
- Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan
Zitieren
APA
Kokhan, A., Zhaksylyk, T., & Kuldeyev, N. (2026). How Breast Cancer Survival Predictions Change over Time: A Large SEER Study of Model Calibration and Updating. Informatics, 13(11), 181. https://doi.org/10.3390/informatics13110181
Vancouver
Kokhan A, Zhaksylyk T, Kuldeyev N. How Breast Cancer Survival Predictions Change over Time: A Large SEER Study of Model Calibration and Updating. Informatics. 2026;13(11):181. doi:10.3390/informatics13110181
BibTeX
@article{Kokhan2026,
author = {Kokhan, Ayan and Zhaksylyk, Tomiris and Kuldeyev, Nursultan},
title = {How Breast Cancer Survival Predictions Change over Time: A Large SEER Study of Model Calibration and Updating},
journal = {Informatics},
year = {2026},
volume = {13},
number = {11},
pages = {181},
doi = {10.3390/informatics13110181}
}
EUVIMED