Trajectory-informed graph-based clustering for longitudinal cancer subtyping

2026-03-10

AI Summary

Traditional cancer subtyping methods rely on static biopsies, which struggle to capture tumor heterogeneity and dynamic evolution. This work proposes a novel framework that integrates multimodal clinical data with longitudinal patient trajectories, embedding disease progression paths directly into graph-based clustering for the first time. By constructing a patient similarity graph from temporal imaging features, clinical covariates, and critical state transitions, the approach enables subtype discovery that simultaneously models temporal dynamics and retains structural interpretability. Evaluated on a real-world dataset of liver metastases, the method successfully identifies clinically relevant subtypes exhibiting significantly distinct prognostic trajectories, demonstrating its effectiveness and practical utility.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Cancer subtyping plays a crucial role in informing prognosis and guiding personalized treatment strategies. However, conventional subtyping approaches often rely on static, biopsy-derived scores that hardly capture the biological heterogeneity and temporal evolution of the disease. In this study, we propose a novel trajectory-informed clustering method for cancer subtyping that integrates multi-modal clinical data and longitudinal patient trajectories. Our method constructs a patient similarity graph using time-varying imaging-derived features, clinical covariates, and transitions among key clinical states such as therapy, surveillance, relapse, and death. This graph structure enables the identification of patient subgroups that are not only phenotypically and genotypically distinct but also aligned with patterns of disease progression. We position our approach within the landscape of existing subtyping methods and highlight its advantages in terms of temporal modeling and graph-based interpretability. Through simulation studies and application to a real world dataset of liver metastases, we demonstrate the ability of our framework to uncover clinically relevant subtypes with distinct prognostic trajectories. Our results underscore the potential of trajectory-informed clustering to enhance personalized oncology by bridging cross-sectional biomarkers with dynamic disease evolution.

Problem

• cancer subtyping
• longitudinal data
• disease evolution
• temporal heterogeneity
• clinical trajectories

Innovation

• trajectory-informed clustering
• longitudinal cancer subtyping
• patient similarity graph
• multi-modal clinical data
• disease progression modeling