Chain-of-Influence: Tracing Interdependencies Across Time and Features in Clinical Predictive Modelings

2025-10-10

AI Summary

Clinical temporal modeling faces two key challenges: the dynamic evolution of latent dependencies among features, and the obscurity of variable influence propagation pathways over time. To address these, we propose Chain-of-Influence—a novel framework that explicitly and traceably models temporal influence pathways among clinical variables. It employs temporal attention to identify critical time points, cross-feature attention to characterize directed influence propagation, and graph-structured representation to capture dynamic interactions. The framework generates patient-specific, fine-grained attribution trajectories, substantially enhancing both predictive accuracy and model interpretability. Evaluated on MIMIC-IV and a chronic kidney disease cohort, it outperforms state-of-the-art methods in prediction performance. Case studies demonstrate its ability to uncover clinically meaningful, dynamically evolving dependency patterns, offering a new analytical tool for mechanistic investigation of disease progression.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Planning, Routing, and Scheduling: Temporal Planning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• 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

Modeling clinical time-series data is hampered by the challenge of capturing latent, time-varying dependencies among features. State-of-the-art approaches often rely on black-box mechanisms or simple aggregation, failing to explicitly model how the influence of one clinical variable propagates through others over time. We propose $ extbf{Chain-of-Influence (CoI)}$, an interpretable deep learning framework that constructs an explicit, time-unfolded graph of feature interactions. CoI leverages a multi-level attention architecture: first, a temporal attention layer identifies critical time points in a patient's record; second, a cross-feature attention layer models the directed influence from features at these time points to subsequent features. This design enables the tracing of influence pathways, providing a granular audit trail that shows how any feature at any time contributes to the final prediction, both directly and through its influence on other variables. We evaluate CoI on mortality and disease progression tasks using the MIMIC-IV dataset and a private chronic kidney disease cohort. Our framework significantly outperforms existing methods in predictive accuracy. More importantly, through case studies, we show that CoI can uncover clinically meaningful, patient-specific patterns of disease progression that are opaque to other models, offering unprecedented transparency into the temporal and cross-feature dependencies that inform clinical decision-making.

Problem

• Capturing latent time-varying dependencies among clinical features
• Modeling influence propagation between clinical variables over time
• Providing interpretable audit trails for clinical prediction pathways

Innovation

• Constructs explicit time-unfolded graph of feature interactions
• Uses multi-level attention to identify critical time points
• Models directed influence between features across time