Related Experiment Video
Updated: Aug 11, 2026
Subjective Refraction Test Using a Smartphone for Vision Screening
Published on: October 18, 2024
Validation of a Multimodal Wearable Device for Assessing Environmental and Behavioral Risk Factors of Myopia in
Wenjun Xu1, Junliang Chen2, Zihang Zhang3,4
1Beijing Tongren Eye Centre, Beijing Tongren Hospital, Beijing Institute of Ophthalmology, Beijing Key Laboratory of Intelligent Diagnosis Technology and Equipment for Optic Nerve-Related Eye Diseases, Capital Medical University, Beijing, China.
Purpose:
To validate a wrist-worn multimodal wearable system for synchronised monitoring of multispectral light exposure, activity phenotypes and five-stage sleep architecture in children and adolescents in a structured 24-h pilot validation protocol.
Methods:
A wrist-mounted multimodal wearable system was developed, integrating a 9-channel multispectral light sensor (350-1000 nm), a 9-axis inertial measurement unit (IMU) and a photoplethysmography (PPG) sensor for synchronised acquisition of environmental light, body movement and cardiovascular signals. Twelve healthy children and adolescents (mean age: 10.04 ± 3.26 years; range: 6-15 years) underwent a 24-h pilot validation protocol. Long short-term memory (LSTM) networks were developed for activity recognition and a Stacking ensemble framework combined with cost-sensitive learning was implemented for five-stage sleep classification, i.e., wake (W), non-rapid eye movement stage 1 (N1), non-rapid eye movement stage 2 (N2), non-rapid eye movement stage 3 (N3) and rapid eye movement (REM).
Results:
Under the three lighting conditions tested, the device captured distinct spectral irradiance profiles: outdoor natural light (1.8 W m-2 nm-1; broad-spectrum 350-1000 nm), indoor natural light (0.30 W m-2 nm-1) and artificial illumination (0.07 W m-2 nm-1; peak at 545-600 nm). The LSTM-based model achieved 86.33% overall accuracy for five-activity classification, with 92.4% for writing and 91.5% for walking. The Stacking ensemble sleep classifier attained 83.41% overall accuracy; cost-sensitive learning improved N3 and REM detection by 15.8% and 8.9%, respectively. Incorporation of PPG signals enhanced activity recognition accuracy by 3.62%.
Conclusions:
This multimodal platform enabled objective, high-resolution quantification of paediatric light exposure, behaviour and sleep architecture in a structured pilot validation setting, supporting individualised assessment of modifiable myopia-related factors.
