AI framework enhances cardiovascular risk assessment from CT scans

Researchers have developed a novel Explainable Cross-Disease Reasoning Framework designed to assess cardiovascular risk using low-dose computed tomography (LDCT) scans. This framework integrates pulmonary and cardiac health assessments by extracting pulmonary findings, incorporating medical knowledge for cross-organ mechanisms, and generating cardiovascular predictions with natural-language rationales. Tested on the National Lung Screening Trial cohort, the system achieved an AUC of 0.919 for CVD screening and 0.838 for CVD mortality prediction, surpassing existing baselines and demonstrating an auditable approach to risk assessment. AI

IMPACT This framework offers a more auditable and integrated approach to cardiovascular risk assessment from medical imaging, potentially improving diagnostic accuracy and patient outcomes.

RANK_REASON This is a research paper detailing a new AI framework for medical risk assessment. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Explainable Cross-Disease Reasoning Framework
• National Lung Screening Trial
• Yifei Zhang

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →