使用门控Transformer网络基于纵向OCT数据预测视野恶化
这项回顾性纵向队列研究纳入4211只眼(2666例患者),使用门控Transformer网络(GTN)从纵向OCT数据中识别视野(VF)恶化,并与线性混合效应模型和朴素贝叶斯分类器比较。以「6种方法中多数」(M6)为参考标准时GTN的AUC为0.97(95%CI 0.88-1.00),以其他6种参考标准训练时AUC为0.78(MD斜率)至0.89(AGIS),7个GTN均优于对应的MEM和NBC。
要点
- M6算法将63只眼(1.50%)标记为视野恶化。
- 以M6为参考标准训练的GTN的AUC为0.97(95%CI 0.88-1.00)。
- GTN在基线青光眼更严重的眼中表现更差。
核心结论
- 用OCT数据训练的GTN模型或可用于识别视野恶化。
- 作者认为,经过进一步验证后,在临床实践中实施此类模型可能使我们能以更少负担的结构性检查来追踪青光眼的功能恶化。
研究设计与样本
- 回顾性纵向队列研究,纳入在Johns Hopkins Wilmer Eye Institute随访的4211只眼(2666例患者),每只眼至少有5次可靠视野结果且每次可靠视野检查前1年内至少有1次可靠OCT扫描。
- 使用3种基于趋势的方法(MD斜率、视野指数斜率、逐点线性回归)和3种基于事件的方法(引导进展分析、CIGTS评分系统、AGIS评分系统)定义视野恶化,并开发「6种方法中多数」(M6)算法:6种方法中4种及以上判定为恶化时将该眼分类为恶化。
- 使用这7种参考标准训练7个GTN,输入为至少5次OCT扫描序列,输出为视野恶化的概率,并与使用相同训练集和参考标准的线性混合效应模型(MEM)和朴素贝叶斯分类器(NBC)比较。
主要发现
- M6将63只眼(1.50%)标记为恶化。
- 以M6训练时GTN的AUC为0.97(95%CI 0.88-1.00)。
- 以其他6种参考标准训练和优化的GTN的AUC范围为0.78(MD斜率)至0.89(AGIS)。
- 7个GTN均优于相应的7个MEM和7个NBC。
- GTN在基线青光眼更严重的眼中表现更差。
临床怎么用
- 原文结论指出,用OCT数据训练的GTN模型或可用于识别视野恶化;作者认为经过进一步验证后,在临床实践中实施此类模型可能使我们能以更少负担的结构性检查来追踪青光眼的功能恶化。
局限性
- 原文在结论中写明「After further validation」,即需进一步验证。
- GTN在基线青光眼更严重的眼中表现更差。
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
PURPOSE: To identify visual field (VF) worsening from longitudinal OCT data using a gated transformer network (GTN) and to examine how GTN performance varies for different definitions of VF worsening and different stages of glaucoma severity at baseline. DESIGN: Retrospective longitudinal cohort study. PARTICIPANTS: A total of 4211 eyes (2666 patients) followed up at the Johns Hopkins Wilmer Eye Institute with at least 5 reliable VF results and 1 reliable OCT scan within 1 year of each reliable VF test. METHODS: For each eye, we used 3 trend-based methods (mean deviation [MD] slope, VF index slope, and pointwise linear regression) and 3 event-based methods (Guided Progression Analysis, Collaborative Initial Glaucoma Treatment Study scoring system, and Advanced Glaucoma Intervention Study [AGIS] scoring system) to define VF worsening. Additionally, we developed a "majority of 6" algorithm (M6) that classifies an eye as worsening if 4 or more of the 6 aforementioned methods classified the eye as worsening. Using these 7 reference standards for VF worsening, we trained 7 GTNs that accept a series of at least 5 as input OCT scans and provide as output a probability of VF worsening. Gated transformer network performance was compared with non-deep learning models with the same serial OCT input from previous studies-linear mixed-effects models (MEMs) and naive Bayes classifiers (NBCs)-using the same training sets and reference standards as for the GTN. MAIN OUTCOME MEASURES: Area under the receiver operating characteristic curve (AUC). RESULTS: The M6 labeled 63 eyes (1.50%) as worsening. The GTN achieved an AUC of 0.97 (95% confidence interval, 0.88-1.00) when trained with M6. Gated transformer networks trained and optimized with the other 6 reference standards showed an AUC ranging from 0.78 (MD slope) to 0.89 (AGIS). The 7 GTNs outperformed all 7 MEMs and all 7 NBCs accordingly. Gated transformer network performance was worse for eyes with more severe glaucoma at baseline. CONCLUSIONS: Gated transformer network models trained with OCT data may be used to identify VF worsening. After further validation, implementing such models in clinical practice may allow us to track functional worsening of glaucoma with less onerous structural testing. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.
引用
- Hou K, Bradley C, Herbert P, et al. Predicting Visual Field Worsening with Longitudinal OCT Data Using a Gated Transformer Network. Ophthalmology. 2023. PMID: 37003520. doi:10.1016/j.ophtha.2023.03.019
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。