Development of an Artificially Intelligent Tool for Analysis and Prediction of Myopia Progression Among School-Going Children
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 发起方
- 入组人数
- 12,000
- 试验地点
- 1
- 主要终点
- Change in Spherical Equivalent Refraction (SER) – to quantify progression of myopia.
研究概览
简要总结
This study aims to develop and validate an Artificial Intelligence (AI) based predictive model for assessing myopia progression among school-going children aged 6 to 18 years in urban and rural areas of the Bhopal Division, India. The research will be conducted in two phases. Phase one involves a cross-sectional survey of approximately 12000 children to collect ocular, demographic, and behavioral data such as axial length, refractive status, screen time, and outdoor activity. Phase two will follow a stratified 10 percent cohort of these children longitudinally every six months over two years to track changes in spherical equivalent refraction and axial length. Using this data, machine learning models including linear regression, support vector machines, XGBoost, and convolutional neural networks will be trained to predict the risk of myopia progression. The validated AI model will be integrated into a mobile application for field-level screening and early identification of at-risk children. The study also includes awareness initiatives on preventive eye care and aims to establish a large-scale Indian dataset to support policy planning and public health strategies for pediatric vision health.
研究设计
- 研究类型
- Observational
入排标准
- 年龄范围
- 6.00 Year(s) 至 18.00 Year(s)（—）
- 性别
- All
入选标准
- •School-going children aged 6 to 18 years Enrolled in selected schools across urban and rural areas of Bhopal Division (Madhya Pradesh) Parental or legal guardian consent and age-appropriate child assent provided Willing to participate in ocular assessments and periodic follow-ups over 24 months.
排除标准
- •History of ocular trauma, congenital anomalies, or prior eye surgeries Children with systemic illnesses affecting vision (e.g., diabetes, neurological disorders) Inability to cooperate with eye exams or data collection Already enrolled in another interventional ophthalmic study.
结局指标
主要结局
Change in Spherical Equivalent Refraction (SER) – to quantify progression of myopia.
时间窗: Outcome: Change in Spherical Equivalent Refraction (SER) and Axial Length – used to measure and quantify myopia progression in school-going children. | Time Points: At baseline (enrolment), at 6 months, and at 12 months.
Change in Axial Length – to assess ocular growth associated with myopia progression.
时间窗: Outcome: Change in Spherical Equivalent Refraction (SER) and Axial Length – used to measure and quantify myopia progression in school-going children. | Time Points: At baseline (enrolment), at 6 months, and at 12 months.
Time Points for Assessment:
时间窗: Outcome: Change in Spherical Equivalent Refraction (SER) and Axial Length – used to measure and quantify myopia progression in school-going children. | Time Points: At baseline (enrolment), at 6 months, and at 12 months.
Baseline (at enrolment)
时间窗: Outcome: Change in Spherical Equivalent Refraction (SER) and Axial Length – used to measure and quantify myopia progression in school-going children. | Time Points: At baseline (enrolment), at 6 months, and at 12 months.
6 months from baseline
时间窗: Outcome: Change in Spherical Equivalent Refraction (SER) and Axial Length – used to measure and quantify myopia progression in school-going children. | Time Points: At baseline (enrolment), at 6 months, and at 12 months.
12 months from baselin
时间窗: Outcome: Change in Spherical Equivalent Refraction (SER) and Axial Length – used to measure and quantify myopia progression in school-going children. | Time Points: At baseline (enrolment), at 6 months, and at 12 months.
次要结局
- Identification and Ranking of Dominant Risk Factors (e.g., screen time, parental myopia, near work duration)
- Validation Accuracy of Mobile Application Predictions vs. clinical diagnoses (Positive Predictive Value, Kappa score)
- Awareness and Behavior Change Metrics – Number of children reached, engagement in prevention programs
- AI Model Performance Metrics – Accuracy, Sensitivity, Specificity, AUROC, F1 Score
研究者
Dr Priti Singh
All India Institute of Medical Sciences, Bhopal