Artificial intelligence promotes early detection and management of myopia

Artificial intelligence promotes early detection and management of myopia

The increasing prevalence of myopia is a global health problem, with high myopia increasing the risk of vision damage. This requires the use of artificial intelligence (AI) for early diagnosis, prevention and treatment of myopia. Well, aPediatric examinationReview highlights potential applications of AI in early identification, risk assessment and prevention of myopia. It further shows the challenges and the current development status of AI technology in the field of myopia.

Myopia or nearsightedness affects two billion people worldwide. Uncorrected myopia can affect vision, disrupt education, career prospects and quality of life. By 2050, it is estimated that almost half of the world's population will become myopic. High myopia is often associated with complications that can lead to visual impairment, affecting patients' quality of life and increasing the global medical and economic burden. Therefore, early diagnosis of myopia is important for preventing visual impairment in patients with myopia.

Artificial intelligence (AI) has opened new frontiers in the medical field and can be a solution for this global healthcare company. The subgroups of AI, such as Advanced technologies, such as machine learning (ML) and deep learning (DL), can help analyze data to diagnose diseases and predict risk factors, biomarkers, and outcomes.

In a new literature review, Dr. Li Li, Dr. Jifeng Yu and Dr. Nan Liu, all from the Department of Ophthalmology, Capital Medical University, China, summarized the applications and challenges of AI in myopia, including detection, risk factor assessment and prediction models. This study was published in the Journal ofPediatric examinationon March 18, 2025.

Interestingly, AI models can be trained with ML/DL to detect myopia from fundus photos and optical coherence tomography images. By feeding a model a large set of fundus images from myopic patients, AI can be taught to detect tiny changes in color and pattern in the retina that are associated with myopia. This allows the model to diagnose future patients from their fundus photos.

Additionally, self-monitoring devices such as SVOne, a handheld device that uses a wavefront sensor to measure eye defects, can detect refractive defects in the eyes using AI algorithms. The device can access an online database of images that the AI ​​can use as references to diagnose myopia. Additionally, AI can be trained to detect behavioral changes associated with myopia onset. Such detection is particularly useful for early detection of myopia in children, which is often otherwise ignored. For example, the Vivior Monitor uses ML algorithms to detect changes in visual behavior, such as:

In addition, ML methods such as vector machine, logistic regression and Xgboost can be used to identify risk factors for myopia."An XGBOOST-based model can obtain large amounts of longitudinal data, allowing it to learn the outcomes and associated risk factors of myopia in numerous patients. This, in turn, allows the model to assess the risk factors of new patients based on their genetics, family history, environment and physiological parameters."Explains Dr. Li Li.

Predicting myopia progression and outcome can help physicians tailor their clinical approach. On a large scale, it can shape clinical practice and policy making that help control myopia. By feeding an AI model large amounts of biometric data, refractive data, treatment responses, and eye images from numerous myopia patients, AI can be taught to predict myopia outcomes in new patients.

Despite the great potential of AI in myopia, several challenges must be overcome. First, it is important to ensure that the data set used to train an AI model is accurate and of high quality. Bias, false negatives/positives, and poor data quality can negatively impact the model's diagnostic and predictive accuracy. Second, most AI models are trained using data from large hospitals, which may not be representative of patients going to smaller clinics. This creates a discrepancy between real and training populations. Third, an AI model is not a trained doctor and may not provide a clinical basis for its diagnosis, which may result in the diagnosis being rejected by medical professionals. Finally, with such large amounts of patient data, it is important to see AI models ensure the privacy of patients' medical records.

“While our study highlights the notable onesAdvances in the clinical application of AI in myopia require further studies to overcome the technological challenges. FromBy building high-quality data sets, improving the model's ability to process multimodal image data, and improving the interaction ability of human computers, the AI ​​models can be further improved for widespread clinical use.“Concludes Dr. Jifeng Yu.

Sources: