Atrial Fibrillation Detection System via Acoustic Sensing for Mobile Phones

TL;DR

This work presents MobileAF, a novel smartphone-based AF detection system using speakers and microphones, and proposes a multi-channel pulse wave probing method, which enhances the signal quality by introducing a three-stage pulse wave purification pipeline.

Abstract

Atrial fibrillation (AF) is characterized by irregular electrical impulses originating in the atria, which can lead to severe complications and even death. Due to the intermittent nature of the AF, early and timely monitoring of AF is critical for patients to prevent further exacerbation of the condition. Although ambulatory ECG Holter monitors provide accurate monitoring, the high cost of these devices hinders their wider adoption. Current mobile-based AF detection systems offer a portable solution, however, these systems have various applicability issues such as being easily affected by environmental factors and requiring significant user effort. To overcome the above limitations, we present MobileAF, a novel smartphone-based AF detection system using speakers and microphones. In order to capture minute cardiac activities, we propose a multi-channel pulse wave probing method. In addition, we enhance the signal quality by introducing a three-stage pulse wave purification pipeline. What's more, a ResNet-based network model is built to implement accurate and reliable AF detection. We collect data from 23 participants utilizing our data collection application on the smartphone. Extensive experimental results demonstrate the superior performance of our system, with 97.9% accuracy, 96.8% precision, 97.2% recall, 98.3% specificity, and 97.0% F1 score.

Figures (19)

• Figure 1: MobileAF application scenario.
• Figure 2: Feasibility study setup and result. (a): Scenario of feasibility study. The PPG sensor is placed at the fingertip, and the smartphone is placed at the wrist above the radial artery. (b): Comparison of PPG and acoustic phase changes. The phase waveform shows a high similarity with the PPG waveform.
• Figure 3: MobileAF system overview.
• Figure 4: Comparison of extracted pulse waves between subjects with AF and NSR, illustrating various patterns. Results labeled (a), (c), (e), and (f) pertain to NSR subjects, while (b), (d), (f), and (g) correspond to AF subjects. Subfigures (a) and (b) depict ideal cases, (c) and (d) represent reversed cases, (e) and (f) show distorted cases, (g) and (h) illustrate baseline-drift cases.
• Figure 5: Examples of (a) high-quality pulse waves and (b) low-quality pulse waves.