Explainable Cross-Disease Reasoning for Cardiovascular Risk Assessment from Low-Dose Computed Tomography

arXiv:2511.06625v5 Announce Type: replace-cross Abstract: Low-dose chest computed tomography (LDCT) captures pulmonary and cardiac structures in a single scan, enabling joint assessment of lung and cardiovascular health. Existing approaches typically model these domains independently and do not explicitly represent their physiological interactions. We propose an Explainable Cross-Disease Reasoning Framework for cardiovascular risk assessment from LDCT. The framework follows a constrained clinical-information pathway: it extracts pulmonary findings, grounds cross-organ mechanisms in medical kno
Advances in AI, particularly in computer vision and medical knowledge representation, are now enabling sophisticated, explainable diagnostic tools for complex diseases.
This development can significantly improve early disease detection and personalized risk assessment for cardiovascular health, leveraging widely available medical imaging data efficiently.
Traditional siloed diagnostic approaches are being integrated into cross-disease reasoning frameworks, leading to more holistic patient risk profiles and potentially transforming preventative medicine.
- · Medical AI developers
- · Healthcare providers
- · Cardiology and pulmonology sectors
- · Patients at risk of cardiovascular disease
- · Traditional diagnostic imaging consultancies (if they fail to adapt)
- · Less advanced diagnostic testing methods
- · Disease models not incorporating cross-organ interactions
Early and more accurate identification of cardiovascular risks from existing medical scans becomes possible.
This leads to more personalized preventative interventions and treatment plans, reducing overall healthcare burdens related to cardiovascular disease.
The success of cross-disease reasoning frameworks could catalyze similar AI integration in other complex, multi-systemic illnesses, accelerating 'AI Agents' in medical diagnostics broadly.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG