LubDubDecoder: Bringing Micro-Mechanical Cardiac Monitoring to Hearables

2025-09-12

AI Summary

This study addresses the limited accessibility of wearable cardiac mechanical vibration monitoring, which traditionally relies on specialized hardware. We propose a zero-overhead, microphone-free cardiac monitoring method leveraging ubiquitous headphones. For the first time, commercial headphone speakers are repurposed in reverse as high-sensitivity vibrometers; acoustic sensing is combined with time–frequency analysis and a lightweight machine learning model to reconstruct seismocardiogram (SCG) and gyrocardiogram (GCG) waveforms from phonocardiographic signals and to precisely extract valve opening/closing timings. Validation across 18 subjects demonstrates intrasubject and intersubject waveform correlations of 0.88–0.95, cross-device correlation of 0.91 without device-specific calibration, and robust performance under challenging conditions—including tight headphone wear and concurrent music playback. Our approach eliminates dependence on custom hardware, enabling low-cost, broadly compatible, and high-fidelity assessment of cardiac mechanical function.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Brain-Sensing and Analysis
• Computer Vision: Motion & Tracking

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Web measurements

Abstract

We present LubDubDecoder, a system that enables fine-grained monitoring of micro-cardiac vibrations associated with the opening and closing of heart valves across a range of hearables. Our system transforms the built-in speaker, the only transducer common to all hearables, into an acoustic sensor that captures the coarse "lub-dub" heart sounds, leverages their shared temporal and spectral structure to reconstruct the subtle seismocardiography (SCG) and gyrocardiography (GCG) waveforms, and extract the timing of key micro-cardiac events. In an IRB-approved feasibility study with 18 users, our system achieves correlations of 0.88-0.95 compared to chest-mounted reference measurements in within-user and cross-user evaluations, and generalizes to unseen hearables using a zero-effort adaptation scheme with a correlation of 0.91. Our system is robust across remounting sessions and music playback.

Problem

• Enables fine-grained cardiac vibration monitoring using hearables
• Transforms built-in speakers into acoustic sensors for heart sounds
• Reconstructs SCG and GCG waveforms to extract micro-cardiac events

Innovation

• Transforms speaker into acoustic sensor
• Reconstructs SCG and GCG waveforms
• Zero-effort adaptation for unseen hearables