Facial Foundational Model Advances Early Warning of Coronary Artery Disease from Live Videos with DigitalShadow

TL;DR

DigitalShadow is a contactless, privacy-preserving facial analysis system that leverages a large pre-trained foundation model to predict coronary artery disease risk from live videos, enabling early detection and personalized health advice.

Contribution

This work introduces DigitalShadow, a novel facial-based CAD risk assessment system utilizing a large pre-trained foundation model and fine-tuning on a specialized dataset for early warning.

Findings

Pre-trained on 21 million facial images for robust feature extraction.

Fine-tuned on 7,004 facial images from 1,751 subjects for CAD risk prediction.

Supports local deployment with privacy-focused design.

Abstract

Global population aging presents increasing challenges to healthcare systems, with coronary artery disease (CAD) responsible for approximately 17.8 million deaths annually, making it a leading cause of global mortality. As CAD is largely preventable, early detection and proactive management are essential. In this work, we introduce DigitalShadow, an advanced early warning system for CAD, powered by a fine-tuned facial foundation model. The system is pre-trained on 21 million facial images and subsequently fine-tuned into LiveCAD, a specialized CAD risk assessment model trained on 7,004 facial images from 1,751 subjects across four hospitals in China. DigitalShadow functions passively and contactlessly, extracting facial features from live video streams without requiring active user engagement. Integrated with a personalized database, it generates natural language risk reports and individualized health recommendations. With privacy as a core design principle, DigitalShadow supports local deployment to ensure secure handling of user data.