The Sound of Death: Deep Learning Reveals Vascular Damage from Carotid Ultrasound

2026-02-19

AI Summary

Current cardiovascular risk assessment tools struggle to detect early vascular damage. This study proposes a non-invasive, deep learning–based approach that leverages routine carotid ultrasound videos to identify structural and hemodynamic features associated with vascular injury, using only hypertension as a weak label. By integrating explainable artificial intelligence (XAI) with weakly supervised learning, the method uncovers rich prognostic information embedded in standard ultrasound imaging, revealing novel anatomical and functional biomarkers. Notably, it enables interpretable risk stratification without reliance on laboratory measurements. The derived vascular injury score significantly predicts myocardial infarction, cardiac death, and all-cause mortality, demonstrating performance comparable to or better than established models such as SCORE2.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, yet early risk detection is often limited by available diagnostics. Carotid ultrasound, a non-invasive and widely accessible modality, encodes rich structural and hemodynamic information that is largely untapped. Here, we present a machine learning (ML) framework that extracts clinically meaningful representations of vascular damage (VD) from carotid ultrasound videos, using hypertension as a weak proxy label. The model learns robust features that are biologically plausible, interpretable, and strongly associated with established cardiovascular risk factors, comorbidities, and laboratory measures. High VD stratifies individuals for myocardial infarction, cardiac death, and all-cause mortality, matching or outperforming conventional risk models such as SCORE2. Explainable AI analyses reveal that the model relies on vessel morphology and perivascular tissue characteristics, uncovering novel functional and anatomical signatures of vascular damage. This work demonstrates that routine carotid ultrasound contains far more prognostic information than previously recognized. Our approach provides a scalable, non-invasive, and cost-effective tool for population-wide cardiovascular risk assessment, enabling earlier and more personalized prevention strategies without reliance on laboratory tests or complex clinical inputs.

Problem

• vascular damage
• carotid ultrasound
• cardiovascular risk assessment
• early detection
• non-invasive diagnostics

Innovation

• deep learning
• carotid ultrasound
• vascular damage
• explainable AI
• cardiovascular risk prediction