Enabling Cardiac Monitoring using In-ear Ballistocardiogram on COTS Wireless Earbuds

TL;DR

This work demonstrates that commercial TWS earbuds' IMU sensors can capture in-ear BCG, enabling non-invasive cardiac monitoring without hardware changes. The authors build TWSCardio, a software-only pipeline that denoises multi-axis IMU data and reconstructs high-fidelity SCG using a transformer-based cardiogram network, streaming data via BLE to a smartphone. They validate with 100 participants and multiple case studies, showing accurate HR/IBI estimation, robust motion artifact tolerance, and capabilities in pathological detection, authentication, BP estimation, and ECG reconstruction. The approach promises real-time, low-power cardiac monitoring suitable for large-scale deployment in consumer earbuds, potentially transforming earable healthcare and human–computer interaction.

Abstract

The human ear offers a unique opportunity for cardiac monitoring due to its physiological and practical advantages. However, existing earable solutions require additional hardware and complex processing, posing challenges for commercial True Wireless Stereo (TWS) earbuds which are limited by their form factor and resources. In this paper, we propose TWSCardio, a novel system that repurposes the IMU sensors in TWS earbuds for cardiac monitoring. Our key finding is that these sensors can capture in-ear ballistocardiogram (BCG) signals. TWSCardio reuses the unstable Bluetooth channel to stream the IMU data to a smartphone for BCG processing. It incorporates a signal enhancement framework to address issues related to missing data and low sampling rate, while mitigating motion artifacts by fusing multi-axis information. Furthermore, it employs a region-focused signal reconstruction method to translate the multi-axis in-ear BCG signals into fine-grained seismocardiogram (SCG) signals. We have implemented TWSCardio as an efficient real-time app. Our experiments on 100 subjects verify that TWSCardio can accurately reconstruct cardiac signals while showing resilience to motion artifacts, missing data, and low sampling rates. Our case studies further demonstrate that TWSCardio can support diverse cardiac monitoring applications.

Figures (22)

• Figure 1: The causes and model of BCG formation.
• Figure 2: BCG propagation near the ears.
• Figure 3: Raw IMU waveform collected by Apple AirPods Pro (Duration: 8 seconds; Sampling Rate: 25 Hz; Units: accelerometer $m/s^2$ and gyroscope $dps$). Red dotted line represents the noise floor when the AirPods Pro is placed on a flat surface.
• Figure 4: Frequency domain Bandpass SNR benchmark across different IMU axes and subjects. Each marker represents a specific subject. "$\medwhitestar$" and "$\ast$" denote male and female subjects using Apple AirPods, respectively, while "$\medsquare$" and "$\meddiamond$" indicate male and female subjects using eSense, respectively. All figures share the same x-axis representing the subject's BMI.
• Figure 5: IMU stream BLE channel packet loss rate.