当前位置: X-MOL 学术Ophthalmology › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Monitoring Glaucomatous Functional Loss Using an Artificial Intelligence-Enabled Dashboard.
Ophthalmology ( IF 13.1 ) Pub Date : 2020-03-10 , DOI: 10.1016/j.ophtha.2020.03.008
Siamak Yousefi 1 , Tobias Elze 2 , Louis R Pasquale 3 , Osamah Saeedi 4 , Mengyu Wang 2 , Lucy Q Shen 5 , Sarah R Wellik 6 , Carlos G De Moraes 7 , Jonathan S Myers 8 , Michael V Boland 9
Affiliation  

Purpose

To develop an artificial intelligence (AI) dashboard for monitoring glaucomatous functional loss.

Design

Retrospective, cross-sectional, longitudinal cohort study.

Participants

Of 31 591 visual fields (VFs) on 8077 subjects, 13 231 VFs from the most recent visit of each patient were included to develop the AI dashboard. Longitudinal VFs from 287 eyes with glaucoma were used to validate the models.

Method

We entered VF data from the most recent visit of glaucomatous and nonglaucomatous patients into a “pipeline” that included principal component analysis (PCA), manifold learning, and unsupervised clustering to identify eyes with similar global, hemifield, and local patterns of VF loss. We visualized the results on a map, which we refer to as an “AI-enabled glaucoma dashboard.” We used density-based clustering and the VF decomposition method called “archetypal analysis” to annotate the dashboard. Finally, we used 2 separate benchmark datasets—one representing “likely nonprogression” and the other representing “likely progression”—to validate the dashboard and assess its ability to portray functional change over time in glaucoma.

Main Outcome Measures

The severity and extent of functional loss and characteristic patterns of VF loss in patients with glaucoma.

Results

After building the dashboard, we identified 32 nonoverlapping clusters. Each cluster on the dashboard corresponded to a particular global functional severity, an extent of VF loss into different hemifields, and characteristic local patterns of VF loss. By using 2 independent benchmark datasets and a definition of stability as trajectories not passing through over 2 clusters in a left or downward direction, the specificity for detecting “likely nonprogression” was 94% and the sensitivity for detecting “likely progression” was 77%.

Conclusions

The AI-enabled glaucoma dashboard, developed using a large VF dataset containing a broad spectrum of visual deficit types, has the potential to provide clinicians with a user-friendly tool for determination of the severity of glaucomatous vision deficit, the spatial extent of the damage, and a means for monitoring the disease progression.



中文翻译:

使用支持人工智能的仪表板监测青光眼功能丧失。

目的

开发用于监测青光眼功能丧失的人工智能 (AI) 仪表板。

设计

回顾性、横断面、纵向队列研究。

参与者

在 8077 名受试者的 31591 个视野 (VF) 中,包括每位患者最近一次访问的 13231 个 VF,以开发 AI 仪表板。来自 287 只患有青光眼的眼睛的纵向 VF 用于验证模型。

方法

我们将青光眼和非青光眼患者最近一次访问的 VF 数据输入到“管道”中,其中包括主成分分析 (PCA)、流形学习和无监督聚类,以识别具有相似全局、半场和局部 VF 损失模式的眼睛。我们在地图上可视化了结果,我们称之为“支持人工智能的青光眼仪表盘”。我们使用基于密度的聚类和称为“原型分析”的 VF 分解方法来注释仪表板。最后,我们使用了 2 个独立的基准数据集——一个代表“可能无进展”,另一个代表“可能进展”——来验证仪表板并评估其描绘青光眼功能随时间变化的能力。

主要观察指标

青光眼患者功能丧失的严重程度和程度以及 VF 丧失的特征模式。

结果

构建仪表板后,我们确定了 32 个不重叠的集群。仪表板上的每个集群对应于特定的全局功能严重性、不同半场的 VF 损失程度以及 VF 损失的特征局部模式。通过使用 2 个独立的基准数据集和将稳定性定义为不通过向左或向下方向超过 2 个集群的轨迹,检测“可能不进展”的特异性为 94%,检测“可能进展”的灵敏度为 77%。

结论

启用 AI 的青光眼仪表板使用包含广泛视觉缺陷类型的大型 VF 数据集开发,有可能为临床医生提供一个用户友好的工具,用于确定青光眼视力缺陷的严重程度、损害的空间范围,以及监测疾病进展的手段。

更新日期:2020-03-10
down
wechat
bug