mCardiacDx: Radar-Driven Contactless Monitoring and Diagnosis of Arrhythmia

2025-08-04

AI Summary

Remote arrhythmia monitoring faces dual challenges: discomfort from contact-based devices and poor spatial localization accuracy coupled with temporal waveform instability in non-contact approaches—particularly among clinical patient populations. This paper introduces the first radar-based, contactless monitoring and diagnostic system specifically designed for arrhythmia patients. We propose a pathology-aware target localization algorithm to suppress motion artifacts induced by pathological movements, and develop a temporally aligned encoder–decoder deep learning architecture to robustly reconstruct high-fidelity photoplethysmographic (PPG)-like pulse waveforms from raw radar reflections. Evaluated on a large-scale, real-world dataset comprising healthy subjects and diverse arrhythmia patients, our system achieves state-of-the-art performance across heartbeat detection, rhythm classification, and waveform reconstruction tasks—demonstrating significant improvements in accuracy (average F1-score gain of 8.2%), robustness to motion and physiological variability, and clinical applicability.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Hardware-aware ML
• Computer Vision: Motion & Tracking

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Arrhythmia is a common cardiac condition that can precipitate severe complications without timely intervention. While continuous monitoring is essential for timely diagnosis, conventional approaches such as electrocardiogram and wearable devices are constrained by their reliance on specialized medical expertise and patient discomfort from their contact nature. Existing contactless monitoring, primarily designed for healthy subjects, face significant challenges when analyzing reflected signals from arrhythmia patients due to disrupted spatial stability and temporal consistency. In this paper, we introduce mCardiacDx, a radar-driven contactless system that accurately analyzes reflected signals and reconstructs heart pulse waveforms for arrhythmia monitoring and diagnosis. The key contributions of our work include a novel precise target localization (PTL) technique that locates reflected signals despite spatial disruptions, and an encoder-decoder model that transforms these signals into HPWs, addressing temporal inconsistencies. Our evaluation on a large dataset of healthy subjects and arrhythmia patients shows that both mCardiacDx and PTL outperform state-of-the-art approach in arrhythmia monitoring and diagnosis, also demonstrating improved performance in healthy subjects.

Problem

• Contactless monitoring of arrhythmia without patient discomfort
• Overcoming disrupted spatial stability in reflected radar signals
• Reconstructing accurate heart pulse waveforms for arrhythmia diagnosis

Innovation

• Radar-driven contactless arrhythmia monitoring system
• Novel precise target localization technique
• Encoder-decoder model for heart pulse reconstruction