Deep Variational Contrastive Learning for Joint Risk Stratification and Time-to-Event Estimation

2026-02-01

AI Summary

This work addresses the longstanding challenge in survival analysis of balancing predictive accuracy with model interpretability. To this end, the authors propose CONVERSE, a novel deep learning framework that introduces variational contrastive learning to the field for the first time. CONVERSE leverages a variational autoencoder to generate patient embeddings and jointly optimizes risk stratification and time-to-event prediction through a multi-level contrastive loss—encompassing both intra-cluster and inter-cluster relationships—and cluster-specific survival heads. Additionally, self-paced learning is incorporated to enhance training stability. Extensive experiments on four benchmark datasets demonstrate that CONVERSE matches or surpasses state-of-the-art deep survival models in predictive performance while yielding clinically interpretable and stable risk groups.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Survival analysis is essential for clinical decision-making, as it allows practitioners to estimate time-to-event outcomes, stratify patient risk profiles, and guide treatment planning. Deep learning has revolutionized this field with unprecedented predictive capabilities but faces a fundamental trade-off between performance and interpretability. While neural networks achieve high accuracy, their black-box nature limits clinical adoption. Conversely, deep clustering-based methods that stratify patients into interpretable risk groups typically sacrifice predictive power. We propose CONVERSE (CONtrastive Variational Ensemble for Risk Stratification and Estimation), a deep survival model that bridges this gap by unifying variational autoencoders with contrastive learning for interpretable risk stratification. CONVERSE combines variational embeddings with multiple intra- and inter-cluster contrastive losses. Self-paced learning progressively incorporates samples from easy to hard, improving training stability. The model supports cluster-specific survival heads, enabling accurate ensemble predictions. Comprehensive evaluation on four benchmark datasets demonstrates that CONVERSE achieves competitive or superior performance compared to existing deep survival methods, while maintaining meaningful patient stratification.

Problem

• survival analysis
• risk stratification
• interpretability
• deep learning
• time-to-event estimation

Innovation

• contrastive learning
• variational autoencoder
• risk stratification
• survival analysis
• self-paced learning