Survival In-Context: Prior-fitted In-context Learning Tabular Foundation Model for Survival Analysis
This addresses survival analysis challenges like limited data and censoring for medical applications, representing an incremental advance by adapting prior-fitted paradigms to time-to-event modeling.
The paper tackled survival analysis in medical applications by proposing Survival In-Context (SIC), a prior-fitted in-context learning model pretrained on synthetic data, which achieved competitive or superior performance compared to existing models, especially in medium-sized data regimes.
Survival analysis is crucial for many medical applications but remains challenging for modern machine learning due to limited data, censoring, and the heterogeneity of tabular covariates. While the prior-fitted paradigm, which relies on pretraining models on large collections of synthetic datasets, has recently facilitated tabular foundation models for classification and regression, its suitability for time-to-event modeling remains unclear. We propose a flexible survival data generation framework that defines a rich survival prior with explicit control over covariates and time-event distributions. Building on this prior, we introduce Survival In-Context (SIC), a prior-fitted in-context learning model for survival analysis that is pretrained exclusively on synthetic data. SIC produces individualized survival prediction in a single forward pass, requiring no task-specific training or hyperparameter tuning. Across a broad evaluation on real-world survival datasets, SIC achieves competitive or superior performance compared to classical and deep survival models, particularly in medium-sized data regimes, highlighting the promise of prior-fitted foundation models for survival analysis. The code will be made available upon publication.