开发一种深度学习模型,以选非洲祖先个体的初级开角玻璃眼
Shuo Li1, Rebecca Salowe2, Roy Lee2
1Department of Computer & Information Science, University of Pennsylvania, Philadelphia, PA, USA.
NPJ digital medicine
|February 6, 2026
概括
这项研究开发了一个人工智能模型,用于使用 fundus 图像进行初级开角眼 (POAG) 查. 该模型准确地识别了不同人群中的POAG,改善了对这种致盲眼病的早期检测.
科学领域:
- 眼科医生 眼科 眼科
- 人工智能的人工智能
- 医疗成像医学成像
背景情况:
- 主要开角青光眼 (POAG) 是导致失明的主要原因,特别影响非洲血统的个人.
- 目前用于POAG查的人工智能 (AI) 模型缺乏未经研究的人群的代表性.
- 在绿眼病检测中,急需公平的AI解决方案.
研究的目的:
- 开发和验证一个深度学习模型用于POAG选使用 fundus 摄影.
- 解决非洲血统个体在青光眼人工智能数据集中的不足.
- 创建一个强大的AI工具,适用于各种临床和低资源环境.
主要方法:
- 一个深度学习模型被训练在64,129个 fundus图像从初级开放角度的非洲裔美国人玻璃眼遗传学 (POAAGG) 队列.
- 该管道涉及使用二进制分类器进行图像选择,并通过视觉变压器进行POAG概率预测.
- 最终的预测是通过从选定的图像中平均概率来得出的.
主要成果:
- 该模型在POAAGG数据集上实现了0.925的曲线下的面积 (AUC).
- 在REFUGE-1数据集 (中国血统) 上的验证结果为AUC为0.920.
- 人工智能模型在对POAG的查中表现出高准确度.
结论:
- 开发的AI模型显示了有效的POAG查的巨大潜力.
- 该模型在不同祖先的表现突出了其概括性.
- 这种人工智能工具可以在各种环境中部署,包括初级保健和资源有限的地区,以提高青光眼的检测.
相关概念视频
Open Angle Glaucoma: Treatment
1.0K
In open-angle glaucoma, the iridocorneal angle remains open, but the trabecular meshwork becomes stiff, slowing down the outflow of aqueous humor. This causes a buildup of aqueous humor in the anterior chamber, leading to a sudden increase in intraocular pressure. The treatment for open-angle glaucoma focuses on reducing the elevated intraocular pressure by either decreasing the secretion of aqueous humor or increasing its outflow.
Drugs such as carbonic anhydrase inhibitors, α2- and...
Drugs such as carbonic anhydrase inhibitors, α2- and...
1.0K
Angle Closure Glaucoma: Treatment
1.3K
Angle-closure glaucoma, or closed-angle glaucoma, is an eye condition where the iris bulges out and blocks the iridocorneal angle, resulting in a buildup of aqueous humor and increased intraocular pressure. Immediate medical attention is necessary due to the sudden onset of symptoms. The treatment for angle-closure glaucoma includes short-term and long-term approaches. Short-term treatment involves using eye drops like pilocarpine to lower intraocular pressure by increasing aqueous humor...
1.3K
Glaucoma: Overview
1.4K
Glaucoma is an eye condition characterized by increased intraocular pressure that damages the retina and optic nerve, leading to irreversible blindness if left untreated. The human eye has various components, including the cornea, iris, pupil, lens, and optic nerve. Aqueous humor is secreted by the epithelium of the ciliary body in the posterior chamber and flows through the trabecular meshwork and canal of Schlemm, maintaining normal intraocular pressure. The trabecular meshwork and the canal...
1.4K
Contact Angle
21.8K
When a solid is dipped inside a liquid, the liquid surface becomes curved near the contact. For some solid–liquid interfaces, the liquid is pulled up along the solid, while for others, the liquid surface is convex or depressed near the solid surface. This phenomenon can be explained using the concept of cohesive and adhesive forces.
The adhesive force is the molecular force between molecules of different materials, that is, between the molecules of the solid and the liquid. The cohesive...
The adhesive force is the molecular force between molecules of different materials, that is, between the molecules of the solid and the liquid. The cohesive...
21.8K
Impact of Individuals on Individuals
403
Human behavior is intricately shaped by social influences that arise from interactions with others in diverse contexts. These influences not only mold beliefs and attitudes but also drive the regulation of behaviors through both direct communication and observational learning. The study of these processes falls within the domain of social psychology, which seeks to understand how individuals are affected by and affect those around them.Mechanisms of Social InfluenceDirect social influence...
403
Mechanistic Models: Compartment Models in Individual and Population Analysis
270
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
270


