文献速递青光眼

人工智能引导的青光眼神经保护试验终点选择

Artificial Intelligence-Guided Endpoint Selection for Neuroprotection Trials in Glaucoma.
PubMed 文献 · Am J Ophthalmol · 2026-01-02

本研究开发了一种基于图注意力网络的人工智能模型,利用基线视野数据预测青光眼患者最可能进展的视野位点,并在三个独立数据集上验证。结果显示,模型选出的五个高风险位点的进展斜率是全局MD的约两倍,且区分进展者与非进展者的AUC达0.883至0.937,支持更高效的神经保护试验和个性化监测。

要点

  • AI模型可从基线视野数据识别最易进展的五个位点(High-5)。
  • High-5位点的进展速率是全局MD的约两倍,且几乎全部进展者达到≥7 dB阈值。
  • High-5指标为青光眼神经保护试验提供了一种更敏感的功能终点框架。

核心结论

  • 基于AI的模型能从基线数据识别最脆弱的视野位点,High-5指标与监管功能终点概念一致,对进展更敏感。

研究设计与样本

  • 回顾性队列研究,纳入三个独立数据集共10,533名受试者的14,237只眼,包含82,449次SAP检查。
  • 图注意力网络在Bascom Palmer数据集上训练,并在Duke和University of Washington队列进行外部验证。

主要发现

  • 在进展眼中,High-5的平均斜率为-2.05至-2.32 dB/y,是Low-5(-0.45至-0.66 dB/y)的四到五倍(P < .001),约为MD(-0.93至-1.14 dB/y)的两倍(P < .001)。
  • High-5区分进展者与非进展者的AUC为0.883至0.937,优于Low-5(0.668-0.731;P < .001)和MD(0.871-0.911;P = .003)。
  • 几乎所有进展者在随访期间均达到High-5的≥7 dB阈值。

关键数值与推荐

  • 研究提出以基线预测的五个最高风险位点(High-5)作为功能终点选择框架,阈值定义为至少五个预设测试点中≥7 dB丢失。

临床怎么用

  • AI模型可辅助青光眼神经保护试验筛选高风险位点,提高终点敏感性,并可能支持个性化监测策略。

局限性

  • 原文未报告

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: Standard Automated Perimetry (SAP) is the primary method for monitoring glaucoma progression and an established functional endpoint in clinical trials. A ≥7 dB loss in at least five prespecified test locations has been proposed as a potential endpoint for glaucoma trials, but identifying such vulnerable points in advance remains a major challenge. We developed an artificial intelligence model that uses baseline SAP data to predict the locations most likely to progress, enabling a targeted approach to endpoint selection in neuroprotection trials. DESIGN: Retrospective cohort study to predict progression. SUBJECTS: A total of 82,449 SAP tests from 14,237 eyes of 10,533 subjects with open-angle glaucoma across three independent datasets: the Bascom Palmer Ophthalmic Registry, the Duke Glaucoma Registry, and the University of Washington Humphrey Visual Field. METHODS: A graph attention network was trained on Bascom Palmer Ophthalmic Registry data, split at the patient level into development and internal validation datasets, to predict progression risk at each SAP location using baseline total deviation values and anatomically informed graph connectivity. For each eye, the five highest-risk points (High-5) were identified and compared with global mean deviation (MD) and the five lowest-risk points (Low-5). The model was applied without retraining to the Duke Glaucoma Registry and University of Washington Humphrey Visual Field cohorts for external validation. MAIN OUTCOME MEASURES: Model ranking performance, neighborhood hit rate, rates of change at High-5, Low-5, and MD, discrimination by area under the receiver operating characteristic curve, and time to repeatable ≥7 dB decline. RESULTS: In progressing eyes, mean slopes at High-5 were -2.05 to -2.32 dB/y, four to five times steeper than Low-5 (-0.45 to -0.66; P < .001) and approximately twice that of MD (-0.93 to -1.14; P < .001). Area under the receiver operating characteristic curve for discriminating progressors from nonprogressors ranged from 0.883 to 0.937 for High-5, outperforming Low-5 (0.668-0.731; P < .001) and MD (0.871-0.911; P = .003). Nearly all progressors reached the High-5 ≥7 dB threshold during follow-up. CONCLUSIONS: The artificial intelligence-based model identified the most vulnerable visual field locations from baseline data. The High-5 metric provides a proof-of-concept framework consistent with regulatory concepts of functional endpoints and shows improved sensitivity to progression, supporting more efficient neuroprotection trials and personalized glaucoma monitoring.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. R da Costa D, Scherer R, Swaminathan SS, et al. Artificial Intelligence-Guided Endpoint Selection for Neuroprotection Trials in Glaucoma. Am J Ophthalmol. 2026. PMID: 41485729. doi:10.1016/j.ajo.2025.12.038

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。