Explainable Cross-Disease Reasoning for Cardiovascular Risk Assessment from LDCT

2025-11-10

AI Summary

Existing low-dose computed tomography (LDCT) analysis typically treats pulmonary and cardiac assessment as disjoint tasks, neglecting their physiological interdependence and shared imaging biomarkers. Method: We propose the first interpretable cross-disease reasoning framework for integrated cardiopulmonary risk assessment from a single LDCT scan. It comprises a lung-aware module that extracts pulmonary abnormality representations, a knowledge-guided reasoning module—integrating medical knowledge graphs and clinical logic—and a cardiac representation module that generates pathophysiologically consistent cardiovascular risk predictions. Our agent-based reasoning explicitly models the “pulmonary abnormality → cardiovascular risk” pathological pathway, bridging imaging features with underlying physiological mechanisms. Contribution/Results: Evaluated on the NLST cohort, our method significantly outperforms unidisease models and purely data-driven approaches in both cardiovascular disease screening and all-cause mortality prediction. Crucially, it produces clinically verifiable, mechanistic reasoning paths, establishing a novel paradigm for expanding the clinical utility of routine LDCT.

Technology Category

• Knowledge Representation and Reasoning: Reasoning with Beliefs
• Reasoning under Uncertainty: Graphical Models
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Low-dose chest computed tomography (LDCT) inherently captures both pulmonary and cardiac structures, offering a unique opportunity for joint assessment of lung and cardiovascular health. However, most existing approaches treat these domains as independent tasks, overlooking their physiological interplay and shared imaging biomarkers. We propose an Explainable Cross-Disease Reasoning Framework that enables interpretable cardiopulmonary risk assessment from a single LDCT scan. The framework introduces an agentic reasoning process that emulates clinical diagnostic thinking-first perceiving pulmonary findings, then reasoning through established medical knowledge, and finally deriving a cardiovascular judgment with explanatory rationale. It integrates three synergistic components: a pulmonary perception module that summarizes lung abnormalities, a knowledge-guided reasoning module that infers their cardiovascular implications, and a cardiac representation module that encodes structural biomarkers. Their outputs are fused to produce a holistic cardiovascular risk prediction that is both accurate and physiologically grounded. Experiments on the NLST cohort demonstrate that the proposed framework achieves state-of-the-art performance for CVD screening and mortality prediction, outperforming single-disease and purely image-based baselines. Beyond quantitative gains, the framework provides human-verifiable reasoning that aligns with cardiological understanding, revealing coherent links between pulmonary abnormalities and cardiac stress mechanisms. Overall, this work establishes a unified and explainable paradigm for cardiovascular analysis from LDCT, bridging the gap between image-based prediction and mechanism-based medical interpretation.

Problem

• Enables interpretable cardiovascular risk assessment from LDCT scans
• Bridges pulmonary abnormalities and cardiac risks through medical reasoning
• Overcomes limitations of single-disease approaches in cardiopulmonary assessment

Innovation

• Agentic reasoning process emulating clinical diagnostic thinking
• Integration of pulmonary perception and knowledge-guided reasoning modules
• Fusion of lung abnormalities with cardiac biomarkers for CVD prediction