3 papers
cs.AI2026
StochIKM: Automated High-Fidelity Reconstruction of Individual Patient Data from Published Kaplan-Meier Curves
Liangze Ke, Daniel Zelterman, Wei Wei +1
Individual patient data are the gold standard for secondary analysis of time-to-event evidence, but they are rarely released, and reconstruction from a published Kaplan-Meier figur…
stat.ME2026
CARB: A Covariate-Assessed Robust Borrowing Strategy with Literature-Informed Prior Weights for External Data
Jinping Liang, Guannan Gong, Satrajit Roychoudhury +1
Borrowing external control data can improve the efficiency of clinical trials, particularly when patient accrual is difficult. A persistent challenge is how to prespecify the degre…
stat.AP2026
Learning from Literature: Integrating LLMs and Bayesian Hierarchical Modeling for Oncology Trial Design
Guannan Gong, Satrajit Roychoudhury, Allison Meisner +3
Designing modern oncology trials requires synthesizing evidence from prior studies to inform hypothesis generation and sample size determination. Trial designs based on incomplete…