Deep Learning-Based Eye Rubbing Detection Using Wrist-Based Wearable Devices to Enable Rigorous Study of Risk Factors for Ectasia Progression.

PURPOSE: To develop and validate an artificial intelligence (AI)-enabled eye rubbing detection tool using sensor data collected from wrist-based wearable devices.

METHODS

An automated system was designed to detect eye rubbing using wrist-based wearable devices. The system involves 3 components: sensor data acquisition, data preprocessing, and deep learning-based classification model. Six different deep learning architectures were developed, including 1D and 2D CNN-LSTM models and an ensemble, to identify the most effective approach. Two datasets were established in the time and frequency domains: a timeseries dataset contains 8640 recordings and a scalogram dataset 15 comprising 112,320 images from 20 subjects.

RESULTS

The proposed system demonstrated strong performance, achieving an F1-score of 95.27 ± 0.87% and AUC of 98.26 ± 0.92% across 5 cross-validation folds when using the 1D CNN-LSTM model to distinguish eye rubbing and noneye rubbing activities. When evaluated on the testing set, the system maintained high performance, with an F1-score of 92.54% and AUC of 96.70%. Model inference required 15.32 milliseconds per segment, supporting real-time operation and practical deployments.

CONCLUSIONS

The proposed system provides high reliability in detecting eye rubbing behaviors, indicating its potential as a tool to support ophthalmologists and researchers in the rigorous study of the contributions of eye rubbing to the development and progression of keratoconus and other corneal ectasias.