深度学习预测儿童近视的进展使用眼底图像和折射数据
Meng-Tian Kang1, Yansong Hu2, Ningli Wang1
1Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Institute of Ophthalmology, Beijing Key Laboratory of Intelligent Diagnosis Technology and Equipment for Optic Nerve-Related Eye Diseases, National Engineering Research Center for Ophthalmology, Engineering Research Center of Ophthalmic Equipment and Materials (Ministry of Education), Capital Medical University, Beijing, China.
JAMA network open
|January 26, 2026
概括
一个新的深度学习模型准确地预测近视的进展和高近视风险在学校的孩子,只使用 fundus 图像和折射数据. 这种方法使得早期干预成为可能,特别是在资源有限的环境中.
科学领域:
- 眼科和计算科学 眼科和计算科学
- 医疗保健中的人工智能
- 儿科视觉研究儿童视觉研究
背景情况:
- 儿童近视是一种日益严重的全球健康问题,具有不可逆转的视力障碍的重大风险.
- 早期预测近视的进展对于及时干预以预防高近视和其并发症至关重要.
研究的目的:
- 开发和验证深度学习 (DL) 模型,用于预测学龄儿童近视进展和高近视风险.
- 该模型仅使用 fundus 图像和基线折射数据进行定量预测.
主要方法:
- 一项基于学校的纵向队列研究 (安阳儿童眼睛研究) 涉及3048名6-9岁的儿童.
- 开发了一个DL模型,将卷积神经网络 (CNN) 和循环神经网络 (RNN) 结合起来.
- 用曲线下面面积 (AUC) 进行风险预测,用平均绝对误差 (MAE) 进行球体等效折射 (SER) 预测,在不同的队列中进行外部验证,评估模型性能.
主要成果:
- DL模型实现了高AUC得分:近视风险为0.941和高近视风险为0.985.
- 该模型预测了SER进展,整体MAE为0.322 D/年.
- 北京和拉萨队伍的外部验证显示了强大的跨种族表现 (MAE分别为0.355 D/年和0.261 D/年).
结论:
- 使用最小基线数据的DL模型提供了高度准确的近视和高近视风险预测.
- 这种由人工智能驱动的方法对大规模查和早期干预策略充满希望,特别是在服务不足的地区.
相关概念视频
02:27Predicting Molecular Geometry
45.7K
VSEPR Theory for Determination of Electron Pair Geometries
45.7K
01:28Erikson's Theory on Socioemotional Development during Childhood
1.0K
Erik Erikson, a stage theorist, adapted Freud's theory to emphasize social factors in personality development throughout life, a concept known as psychosocial development. Unlike Freud, who focused on early childhood, Erikson believed that personality evolves across eight life stages, each marked by a specific challenge or "crisis." Successful resolution of each stage fosters competence, while failure may lead to feelings of inadequacy.
The first four of Erikson's eight...
The first four of Erikson's eight...
1.0K
02:07Tumor Progression
7.4K
Tumor progression is a phenomenon where the pre-formed tumor acquires successive mutations to become clinically more aggressive and malignant. In the 1950s, Foulds first described the stepwise progression of cancer cells through successive stages.
Colon cancer is one of the best-documented examples of tumor progression. Early mutation in the APC gene in colon cells causes a small growth on the colon wall called a polyp. With time, this polyp grows into a benign, pre-cancerous tumor. Further...
Colon cancer is one of the best-documented examples of tumor progression. Early mutation in the APC gene in colon cells causes a small growth on the colon wall called a polyp. With time, this polyp grows into a benign, pre-cancerous tumor. Further...
7.4K
01:03Prediction Intervals
3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.4K
01:14Avoidance Learning and Learned Helplessness
2.6K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.6K
01:25Piaget's Theory of Cognitive Development from Childhood into Adulthood
1.5K
Jean Piaget's theory of cognitive development emphasizes the role of thinking in a child's learning process, suggesting that children are naturally curious about their environment. His approach to development is discontinuous, proposing that cognitive abilities progress through distinct stages, each with unique characteristics. Central to Piaget's theory is schemata—mental structures that allow individuals to understand and interpret the world.
Schemata: Building Blocks of Knowledge
Schemata: Building Blocks of Knowledge
1.5K