Tag
Introduces AdaSurvMamba, an adaptive framework for multimodal survival analysis that uses a dual-scale importance-aware reconstruction module and semantic aggregation scanning to improve integration of whole slide images and genomic profiles, achieving consistent gains across five TCGA cohorts.
This paper introduces iLENS, an interpretable LLM-guided mixture-of-experts framework for survival prediction and patient subtyping in Alzheimer's disease using neuroimaging data. The approach provides transparent, biologically grounded rationales for its routing decisions, bridging high-performance survival analysis with interpretable clinical decision support.
This paper introduces FoGS, a filtered mixture-of-generators pipeline that selects synthetic samples from multiple generative models to improve survival analysis training, outperforming real-data training on many datasets while preserving privacy.
This paper systematically evaluates three survival models (Cox, DeepSurv, RSF) under federated learning on heterogeneous breast cancer data, finding that FL outperforms local training and RSF offers the best balance of performance across clients.
This paper introduces a decision-focused learning approach for survival analysis that aligns predictive models with downstream allocation decisions, using NDCG optimization. Applied to US heart transplant data, it improves ranking performance by 50-100%, potentially yielding thousands of additional life-years annually.
This paper proposes TopoMamSurv, a Graph Mamba framework for whole-slide image survival analysis that uses topology-aware ordering to address Mamba's sensitivity to input order, and incorporates bidirectional Mamba and GCN for spatial context modeling.
This paper presents acopula, a JAX-native framework for nested Archimedean copula inference that handles arbitrary censoring, nesting trees, and exact parameter gradients using Taylor-mode automatic differentiation, achieving significant speedups over existing methods.
This paper presents FederatedRSF, a Python package for federated random survival forests that handles partially overlapping medical data across institutions without sharing raw data, and demonstrates comparable performance to centralized training on breast cancer data.
The paper proposes non-parametric estimators KM-ARL and KM-ADD for evaluating changepoint detectors under finite and irregular sequence lengths, drawing an analogy between QCD and survival analysis.
SurvivalPFN is a prior-data fitted network that amortizes Bayesian inference for survival analysis via in-context learning, achieving strong predictive performance across 61 datasets without task-specific training or hyperparameter tuning.