Automatic Ametropia Examination via an Active‐EEG‐Assisted Wearable System
Huaixuan Zhou, Ruyi Zhang, Chixuan Fan, Xuming Liu, Haoyue Hu, Qingkai Ma, Yishi Han, Jianyang Gong · Journal of Sensors · 2025
Early detection and regular monitoring of ametropia are essential to prevent its progression. However, the traditional ametropia examination method is passive, which needs complicated manual operations and necessary communication between doctors and patients. In this study, we proposed an active ametropia examination method, which can obtain the state of ametropia by event‐related potentials (ERP), one kind of evoked electroencephalogram (EEG) signal. Specifically, we studied the correlation between ametropia degree and ERP signal features with establishing an ametropia ERP (A‐ERP) model for the first time. By collecting, processing, analyzing, and judging the ERP signal automatically, the A‐ERP system can realize ametropia examination by oneself. In order to stably induce the ERP signals, we designed a compound visual stimulus paradigm which integrated three types of stimulus images to provide nonsingle stimulus. Then we devised the eye movement artifact removal algorithm based on standard deviation as the threshold, proposed the A‐ERP component location algorithm based on peak and valley and feature extraction formulas. In test experiment, the examination accuracy of A‐ERP system for low, moderate, and high ametropia is 86.29%, 80.95% and 90.98%, respectively. And the overall average test time is about 50 s. Compared with traditional ametropia examination, the A‐ERP system is more active and objective, and the system is wearable for daily use and available to special groups such as communication obstacles or disabled people.