Department of Ophthalmology, University of Tennessee Health Science Center, Memphis, Tennessee; Department of Genetics, Genomics, and Informatics, University of Tennessee Health Science Center, Memphis, Tennessee.
Department of Ophthalmology, Icahn School of Medicine at Mount Sinai, New York, New York.
Ophthalmology. 2022 Dec;129(12):1402-1411. doi: 10.1016/j.ophtha.2022.07.001. Epub 2022 Jul 8.
To identify patterns of visual field (VF) loss based on unsupervised machine learning and to identify patterns that are associated with rapid progression.
Cross-sectional and longitudinal study.
A total of 2231 abnormal VFs from 205 eyes of 176 Ocular Hypertension Treatment Study (OHTS) participants followed over approximately 16 years.
Visual fields were assessed by an unsupervised deep archetypal analysis algorithm and an OHTS-certified VF reader to identify prevalent patterns of VF loss. Machine-identified patterns of glaucoma damage were compared against those patterns previously identified (expert-identified) in the OHTS in 2003. Based on the longitudinal VFs of each eye, VF loss patterns that were strongly associated with rapid glaucoma progression were identified.
Machine-expert correspondence and type of patterns of VF loss associated with rapid progression.
The average VF mean deviation (MD) at conversion to glaucoma was -2.7 decibels (dB) (standard deviation [SD] = 2.4 dB), whereas the average MD of the eyes at the last visit was -5.2 dB (SD = 5.5 dB). Fifty out of 205 eyes had MD rate of -1 dB/year or worse and were considered rapid progressors. Eighteen machine-identified patterns of VF loss were compared with expert-identified patterns, in which 13 patterns of VF loss were similar. The most prevalent expert-identified patterns included partial arcuate, paracentral, and nasal step defects, and the most prevalent machine-identified patterns included temporal wedge, partial arcuate, nasal step, and paracentral VF defects. One of the machine-identified patterns of VF loss predicted future rapid VF progression after adjustment for age, sex, and initial MD.
An automated machine learning system can identify patterns of VF loss and could provide objective and reproducible nomenclature for characterizing early signs of visual defects and rapid progression in patients with glaucoma.
通过无监督机器学习来识别视野（VF）丧失模式，并确定与快速进展相关的模式。
横断面和纵向研究。
共纳入了 176 名 Ocular Hypertension Treatment Study（OHTS）参与者的 205 只眼的 2231 例异常 VF，这些参与者的随访时间约为 16 年。
使用无监督深度原型分析算法和 OHTS 认证的 VF 阅读器评估视野，以识别 VF 丧失的常见模式。将机器识别的青光眼损害模式与 2003 年 OHTS 中先前确定的（专家识别）模式进行比较。根据每只眼的纵向 VF，确定与快速青光眼进展密切相关的 VF 丧失模式。
机器与专家识别的 VF 丧失模式的对应关系以及与快速进展相关的 VF 丧失模式的类型。
转化为青光眼时的平均视野平均偏差（MD）为-2.7 分贝（dB）（标准差[SD]为 2.4 dB），而最后一次就诊时的平均 MD 为-5.2 dB（SD 为 5.5 dB）。205 只眼中有 50 只眼的 MD 率为-1 dB/年或更差，被认为是快速进展者。将 18 种机器识别的 VF 丧失模式与专家识别的模式进行了比较，其中 13 种模式相似。最常见的专家识别模式包括部分弓形、旁中心和鼻侧阶梯缺损，最常见的机器识别模式包括颞楔形、部分弓形、鼻侧阶梯和旁中心 VF 缺损。在调整年龄、性别和初始 MD 后，机器识别的 VF 丧失模式之一可预测未来 VF 的快速进展。
自动化机器学习系统可以识别 VF 丧失模式，并为描述青光眼患者早期视觉缺陷和快速进展的客观、可重复的命名法提供依据。
