Mengying Lai

Mengying Lai

Auto-generated profile, based on publicly available information

Mengying Lai

School of Optometry, Hong Kong Polytechnic University, Hong Kong, China (Hong Kong)

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 January 2022 in American Journal of Ophthalmology
Verified
Journal Article
Closed access
MYMo Yang
Mo Yang
YWYiqun Wu
Yiqun Wu
HSHonglu Song
Honglu Song
MLMengying Lai
Mengying Lai
HLHongen Li
Hongen Li
SWShihui Wei
Shihui Wei

16 November 2020 in British Journal of Ophthalmology
Verified
Journal Article
Closed access
PDF file
MYMo Yang
Mo Yang
YWYiqun Wu
Yiqun Wu
MLMengying Lai
Mengying Lai
HSHonglu Song
Honglu Song
HLHongen Li
Hongen Li
WWWeiping Wu
Weiping Wu
Background Different glial-autoantibodies-related paediatric optic neuritis (ON) are associated with different clinical characteristics and prognosis that require different treatments. Because glial autoantibody detection is not available in some parts of the world and there is often a delay in obtaining results, clinical factors that can be used to predict the subtype of paediatric ON are needed. Methods This was a single-centre retrospective cohort study. Children who presented with their first ON attack and with complete clinical data were included in the analysis. Single and multiple parameters for predicting paediatric myelin oligodendrocyte glycoprotein immunoglobin-associated ON (MOG-ON) and aquaporin-4 immunoglobin-related ON (AQP4-ON) were calculated. Results 78 paediatric patients had their first ON attack from January 2016 to December 2019, of whom 69 were included in the final analysis, including 33 MOG-ON cases, 17 AQP4-ON cases and 19 Seronegative-ON cases. For predicting paediatric MOG-ON, the most sensitive predictors were ‘male or optic disc swelling (ODS) or bilateral’ (sensitivity 0.97 (95% CI 0.82 to 1.00)) and ‘follow-up visual acuity (VA) ≤0.1 logMAR or ODS’ (sensitivity 0.97 (95% CI 0.82 to 1.00)), and the most specific factor was ‘Age ≤11 y and simultaneous CNS involvement’ (specificity 0.97 (95% CI 0.84 to 1.00)). For predicting paediatric AQP4-ON, the most sensitive predictor was ‘Female or without ODS’ (sensitivity 1.00 (95% CI 0.77 to 1.00)), and the most specific factors were Neurological history (sensitivity 0.94 (95% CI 0.83 to 0.98)) and follow-up VA >1.0 logMAR (sensitivity 0.96 (95% CI 0.86 to 0.99)). Conclusion According to our data from a Chinese paediatric cohort, using multiple parameters increases the sensitivity and specificity of diagnosing paediatric MOG-ON and AQP4-ON. These can assist clinicians in diagnosing and treating paediatric ON when glial autoantibody status is not available.

24 January 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
YCYanxian Chen
Yanxian Chen
XDXiaohu Ding
Xiaohu Ding
RXRuilin Xiong
Ruilin Xiong
JZJian Zhang
Jian Zhang
FSFan Song
Fan Song
MHMingguang He
Mingguang He
To investigate the pattern and threshold of physiological growth, defining as axial length (AL) elongation that results in little refraction progression, among Chinese children and teenagers, a total of 916 children aged between 7 and 18 years from a 6-year longitudinal cohort study were included for analysis. Ocular biometry, cycloplegic refraction and demographic data were obtained annually. Physiological growth was calculated based on myopic progression and Gullstrand eye model, respectively. The annual change in AL was found to be significantly smaller in the persistent emmetropia (PE) group compared to the incident myopia (IM) and persistent myopia (PM) group at all ages (all P < 0.05). In children with non-progressive myopia, there was observed axial elongation ranging from 0.17 to 0.23 mm/year between the ages of 9 and 12. This growth rate persisted at approximately 0.10 mm/year beyond the age of 12. While the compensated AL growth calculated using Gullstrand model was only 0.02 to 0.15 mm/year at age of 9–12, and decreased to around 0 mm/year after age of 12. For children aged 7–9 years, the cutoff point for AL growth to distinguish between progressive myopia and non-progressive myopia was 0.19 mm/year. These findings indicate a notable disparity between the thresholds of physiological growth calculated using myopic progression and Gullstrand eye model. This observation suggests that when formulating effective myopia control strategies, consideration should be given to different calculation methods when applying physiological AL growth as a starting point or target.

20 September 2025 in JMIR Preprints
Verified
Preprint
Open access
FSFan Song
Fan Song
GLGuangyu Li
Guangyu Li
JZJian Zhang
Jian Zhang
ZTZhen Tian
Zhen Tian
MLMingge Li
Mingge Li
YCYanxian Chen
Yanxian Chen
BACKGROUND The escalating prevalence of screen-related eye fatigue has become a health burden in the digital era worldwide, 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 computer vision syndrome, or asthenopia. OBJECTIVE This study aimed 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 EyeFatigue Tracker, an integrated at-home system delivered via a desktop app, 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 measure to classify participants into deteriorated and nondeteriorated 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 fivefold cross-validation. RESULTS This study enrolled 38 participants aged 19-31 (mean 24.8, SD 3.11) years. Following visual tasks, participants’ CVS-Q scores were higher compared to baseline values (mean 9.21, SD 4.57, vs mean 6.76, SD 3.76; P<.001). Alongside the critical flicker fusion frequency (CFF), nine key features were selected as predictive indicators, with the top five reflecting fissure length variability (variance, coefficient of variation, and SD), average blink duration, and pupil size variability (coefficient of variation). Most ML models exhibited high discriminative ability, with the random forest achieving the best overall performance (mean accuracy 0.720, SD 0.035; mean area under the receiver operating characteristic curve 0.850, 95% CI 0.830-0.860). 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. 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.

28 April 2026 in JMIR Human Factors
Verified
Journal Article
Open access
FSFan Song
Fan Song
GLGuangyu Li
Guangyu Li
JZJian Zhang
Jian Zhang
ZTZhen Tian
Zhen Tian
MLMingge Li
Mingge Li
YCYanxian Chen
Yanxian Chen
Background: The escalating prevalence of screen-related eye fatigue has become a health burden in the digital era worldwide, 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 computer vision syndrome, or asthenopia. Objective: This study aimed 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 EyeFatigue Tracker, an integrated at-home system delivered via a desktop app, 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 measure to classify participants into deteriorated and nondeteriorated 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 fivefold cross-validation. Results: This study enrolled 38 participants aged 19-31 (mean 24.8, SD 3.11) years. Following visual tasks, participants’ CVS-Q scores were higher compared to baseline values (mean 9.21, SD 4.57, vs mean 6.76, SD 3.76; P<.001). Alongside the critical flicker fusion frequency (CFF), nine key features were selected as predictive indicators, with the top five reflecting fissure length variability (variance, coefficient of variation, and SD), average blink duration, and pupil size variability (coefficient of variation). Most ML models exhibited high discriminative ability, with the random forest achieving the best overall performance (mean accuracy 0.720, SD 0.035; mean area under the receiver operating characteristic curve 0.850, 95% CI 0.830-0.860). 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. 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.