EUVIMEDDescoperă EUVIMED
Open access

Optimizing Treatment Decision Estimation for Right‐Censored Survival Data Through Parameter Transfer Learning

Yingli Pan, Yinfei Guo, Chentao Yang, Yanhong Shao, Qinglong Yang

Statistics in Medicine · 2026-07 · 45 (15-17)

DOI: 10.1002/sim.70668 ↗

At a glance

Journal article in Statistics in Medicine, published online on 2026-07-07. Written by Yingli Pan and 4 co-authors. Institution: Hubei Key Laboratory of Applied Mathematics, Faculty of Mathematics and Statistics, Hubei University, Wuhan, China. Major MEDLINE topics: Transfer Machine Learning. 41 references. The full text is freely available in PubMed Central. Funded by: National Social Science Fund of China.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Accurately estimating treatment effects is crucial for designing optimal treatment plans in personalized medicine, especially in the presence of right‐censored survival data. We propose a parameter transfer learning method for estimating treatment effects on right‐censored survival data, which leverages multi‐source auxiliary data to enhance the prediction accuracy and robustness of the target model. This method constructs multiple source models by extracting shared parameters from other datasets and uses a smoothed concordance index function specifically designed for right‐censored survival data to estimate candidate model parameters. To enhance performance, a leave‐one‐out cross‐validation criterion is applied to optimize model averaging weights. Theoretically, we have demonstrated that under mild conditions, the proposed method asymptotically achieves the highest smoothed concordance index when the target model is misspecified, and ensures model weight consistency when the target model is correctly specified. Simulation studies confirm the advantages of our proposed method in reducing bias and enhancing prediction accuracy, particularly with right‐censored and heterogeneous data. Its application to the SUPPORT (Study to Understand Prognoses and Preferences for Outcomes and Risks of Treatments) extension dataset, support2, further demonstrates its strong potential in personalized clinical decision‐making.

Subjects

MeSH terms (MEDLINE)

Transfer Machine LearningHumansSurvival AnalysisComputer SimulationModels, StatisticalPrecision MedicineBiasPrediction Algorithms

Author keywords

greedy algorithmindividualized treatment ruleright‐censored survival datatransfer learning

Authors and institutions

  • Hubei Key Laboratory of Applied Mathematics, Faculty of Mathematics and Statistics, Hubei University, Wuhan, China.
  • School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, Hubei, China.

Funding

  • National Social Science Fund of China

Cite

APA

Pan, Y., Guo, Y., Yang, C., Shao, Y., & Yang, Q. (2026). Optimizing Treatment Decision Estimation for Right‐Censored Survival Data Through Parameter Transfer Learning. Statistics in Medicine, 45(15-17). https://doi.org/10.1002/sim.70668

Vancouver

Pan Y, Guo Y, Yang C, Shao Y, Yang Q. Optimizing Treatment Decision Estimation for Right‐Censored Survival Data Through Parameter Transfer Learning. Statistics in Medicine. 2026;45(15-17). doi:10.1002/sim.70668

BibTeX
@article{Pan2026,
  author = {Pan, Yingli and Guo, Yinfei and Yang, Chentao and Shao, Yanhong and Yang, Qinglong},
  title = {Optimizing Treatment Decision Estimation for Right‐Censored Survival Data Through Parameter Transfer Learning},
  journal = {Statistics in Medicine},
  year = {2026},
  volume = {45},
  number = {15-17},
  doi = {10.1002/sim.70668}
}
Start for free →