Related Experiment Video
Updated: May 17, 2025
10:03
Conformable Wearable Electrodes: From Fabrication to Electrophysiological Assessment
Published on: July 22, 2022
4.3K
Mobile Sleep Stage Analysis Using Multichannel Wearable Devices Integrated with Stretchable Transparent Electrodes.
Hyun-Kyung Um1,2, Eunseo Noh3,4, Chaehwa Yoo5
1Department of Mechanical and Biomedical Engineering, Ewha Womans University, Seoul 03760, Republic of Korea.
ACS Sensors
|May 15, 2025
Summary
A new wearable device uses stretchable electrodes to monitor sleep signals accurately. This technology enables artificial intelligence-driven sleep staging for improved at-home sleep disorder diagnosis.
Area of Science:
- Biomedical Engineering
- Sleep Medicine
- Wearable Technology
Background:
- Sleep disorders are prevalent in aging populations, impacting overall health.
- Polysomnography (PSG) is the gold standard for diagnosis but is inconvenient.
- There is a need for accessible, accurate at-home sleep monitoring solutions.
Purpose of the Study:
- To develop a wearable device (WD) with stretchable transparent electrodes (STEs) for multisignal sleep monitoring.
- To implement artificial intelligence (AI) for sleep staging using data from the WD.
- To evaluate the WD's performance against PSG standards.
Main Methods:
- Developed a WD with conductive and flexible STEs for recording biological signals.
- Collected multisignal data including electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), photoplethysmography, and motion.
- Trained an AI model on the multisignal data for automated sleep staging.
Main Results:
- The WD recorded biological signals with high precision and low noise, comparable to PSG.
- Achieved 73.2% accuracy and a macro F1 score of 0.72 in AI-driven sleep staging.
- Sleep staging accuracy showed marginal improvement using only EEG, EOG, and EMG signals.
Conclusions:
- The developed WD offers a compact, multisignal solution for convenient at-home sleep monitoring.
- This technology has potential as an evaluation tool for personalized sleep therapies.
- Future designs could be simplified by focusing on core electrophysiological signals.
