Instability as Signal: Diagnosing Latent Heterogeneity in Multimodal Survival Models
Ray, R.; Shekhawat, S. S.
Show abstract
Survival prediction frequently exhibit unstable and irreproducible performance, limiting their clinical applicability. Rather than proposing a new predictive architecture, this work presents a diagnostic investigation into the sources of this instability. Using a transformer-based deep fusion model combining RNA sequencing and histopathology data from the TCGA-BRCA cohort as a diagnostic probe, we demonstrate that global survival prediction is highly unstable across data splits. We then analyze the learned multimodal embeddings in an unsupervised manner, revealing stable latent patient subgroups with significantly divergent survival outcomes. These subgroups are not explained by canonical receptor status or immune infiltration, but instead align with tumor-intrinsic proliferative activity. Conditioning survival modeling on the largest discovered subgroup recovers strong and stable prognostic performance, substantially outperforming unimodal baselines. These findings indicate that survival predictability is conditional on latent heterogeneity and suggest that heterogeneity-aware modeling strategies are essential for robust multimodal prognostication. This work establishes a methodological framework for interpreting instability in multimodal survival learning.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- MultiSurv: Long-term cancer survival prediction using multimodal deep learning 94%
- Robust Evaluation of Deep Learning-based Representation Methods for Survival and Gene Essentiality Prediction on Bulk RNA-seq Data 93%
- Spatial Transcriptomics Inferred from Pathology Whole-Slide Images Links Tumor Heterogeneity to Survival in Breast and Lung Cancer 93%
Similar papers in this journal
- DeePaN: A deep patient graph convolutional network integrating clinico-genomic evidence to stratify lung cancers benefiting from immunotherapy 92%
- STPath: A Generative Foundation Model for Integrating Spatial Transcriptomics and Whole Slide Images 92%
- FedWeight: Mitigating Covariate Shift of Federated Learning on Electronic Health Records Data through Patients Re-weighting 92%
Similar papers in this journal
- Joint Clinical And Molecular Subtyping Of COPD With Variational Autoencoders 93%
- Features fusion or not: harnessing multiple pathological foundation models using Meta-Encoder for downstream tasks fine-tuning 93%
- Integration of clinical, pathological, radiological, and transcriptomic data improves the prediction of first-line immunotherapy outcome in metastatic non-small cell lung cancer 92%
Similar papers in this journal
Similar papers in this journal
- Bi-level Graph Learning Unveils Prognosis-Relevant Tumor Microenvironment Patterns in Breast Multiplexed Digital Pathology 94%
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 91%
- Obtaining Spatially Resolved Tumor Purity Maps Using Deep Multiple Instance Learning In A Pan-cancer Study 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.