EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CliTsSurv: Asymmetry-Aware Survival Prediction from Irregular Longitudinal Clinical Data

Can Xu, Yaqin Huang, Haike Lei, Jie Yang

Symmetry · 10.11.2026 · 18 (11) · 1879

DOI: 10.3390/sym18111879 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 10.11.2026. Verfasst von Can Xu und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Survival prediction from longitudinal clinical records is challenged by heterogeneous feature availability, irregular observation intervals, and imbalanced event distributions with heavy censoring. These interacting feature, temporal, and event asymmetries are only partly addressed by approaches that reduce histories to fixed covariates, place observations on regular grids, or optimize a single survival objective. We propose CliTsSurv, an integrated framework that learns separate representations of longitudinal and static inputs, encodes actual elapsed time at multiple scales, and combines latent-space augmentation with a multi-task objective comprising negative log-likelihood, ranking loss, and Brier loss. We evaluated CliTsSurv on a retrospective breast cancer cohort of 7509 patients with 92,820 longitudinal records and up to 171 months of follow-up. Across 20 repeated experiments using random patient-level splits and independent model initializations, CliTsSurv-Transformer achieved an IPCW C-index of 0.970, a Harrell C-index of 0.965, and an integrated Brier score of 0.032, outperforming the strongest baseline under the common evaluation protocol. Ablation and sensitivity analyses examined the contributions and limitations of the representation learning, temporal encoding, and augmentation components and identified elapsed-time encoding as the largest contributor. These findings support coordinated modeling of feature, temporal, and event asymmetries for survival prediction from irregular clinical records.

Zitieren

APA

Xu, C., Huang, Y., Lei, H., & Yang, J. (2026). CliTsSurv: Asymmetry-Aware Survival Prediction from Irregular Longitudinal Clinical Data. Symmetry, 18(11), 1879. https://doi.org/10.3390/sym18111879

Vancouver

Xu C, Huang Y, Lei H, Yang J. CliTsSurv: Asymmetry-Aware Survival Prediction from Irregular Longitudinal Clinical Data. Symmetry. 2026;18(11):1879. doi:10.3390/sym18111879

BibTeX
@article{Xu2026,
  author = {Xu, Can and Huang, Yaqin and Lei, Haike and Yang, Jie},
  title = {CliTsSurv: Asymmetry-Aware Survival Prediction from Irregular Longitudinal Clinical Data},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1879},
  doi = {10.3390/sym18111879}
}
Kostenlos starten →