JMIR Publications

ABSTRACT

Background:

The escalating prevalence of screen-related eye fatigue has become a global health burden in the digital era, yet routine monitoring relies largely on subjective reports. This underscores the urgent need for clinically applicable, objective diagnostic solutions. Ocular metrics provide an objective method to assess asthenopia.

Objective:

This study aims to develop and evaluate an integrated at-home system for predicting short-term deteriorated asthenopia using objective ocular metrics. This system classifies the short-term risk level for practical monitoring and automatically generates a session report that summarizes metrics to complement symptom-based evaluation.

Methods:

We developed the EyeFatigue Tracker, an integrated at-home system delivered via a desktop application, comprising a head-mounted device to record binocular infrared eye videos, a deep learning (DL) model to extract ocular metrics, and a machine learning (ML) classifier to estimate asthenopia risk. The DL model, trained on an in-house dataset, segments the palpebral fissure, pupil, and iris from recorded videos to derive ocular metrics. To build the prediction model, participants were recruited to complete a 1-hour computer gameplay session. Changes in the Computer Vision Syndrome Questionnaire (CVS-Q) scores served as the primary outcome measures to classify participants into deteriorated and non-deteriorated asthenopia groups. Metrics showing significant between-group differences were used as inputs for four ML models, including support vector machine (SVM), decision tree, extreme gradient boosting (XGBoost), and random forest, to identify deteriorated asthenopia. Model performance was evaluated with 5-fold cross-validation.

Results:

This study enrolled 38 participants aged 19 to 31 years (mean [SD], 24.8 [3.11] years). Following visual tasks, participants’ CVS-Q scores were higher compared to baseline values (mean [SD], 9.21 [4.57] vs. 6.76 [3.76], P < 0.0001). Alongside critical flicker fusion frequency (CFF), nine key features were selected as predictive indicators, with the top five being the variance of fissure length (frames 600-1200), average blink duration, coefficient of variation of fissure length (frames 600-1200), standard deviation of fissure length (frames 600-1200), and coefficient of variation of pupil size (frames 600-1200). All ML models exhibited high discriminative ability, with the decision tree model achieving the best overall performance (accuracy:0.938; AUC: 0.840 [95% CI: 0.758-0.932]).

Conclusions:

The findings highlight the potential of objective indicators in identifying individuals at risk for asthenopia following computer gameplay. The ML models using ocular biomarkers identified in this study achieved plausible discriminative ability in detecting deteriorated asthenopia. The EyeFatigue Tracker functions as an integrated, at-home system that produces a risk-level prediction and a concise session report, supporting early detection and informing preventive care in real-world settings.