机器学习检测青光眼视野纵向进展
本研究利用机器学习构建青光眼视野进展检测指数,并在2085眼开发集、133眼重测数据集及270眼独立验证集上与全局、区域、点wise指数比较。在固定95%特异性下,机器学习检测到25%眼进展的时间为3.5年,早于全局MD的5.2年、区域wise的4.5年和点wise的3.9年;加入2次确认访视后机器学习仍最早(5.1年)。
要点
- 机器学习指数在固定95%特异性下检测青光眼视野进展早于全局、区域和点wise指数。
- 纵向数据集中机器学习检测25%眼进展时间为3.5年,全局MD为5.2年。
- 加入2次确认访视后机器学习仍最早,且对缓慢进展眼检测更有优势。
核心结论
- 机器学习分析在其他方法之前一致地检测到进展眼,无论是否包含确认访视。
- 机器学习尤其比其他方法检测到更多缓慢进展的眼睛。
研究设计与样本
- 开发与比较预后指数的研究。
- 使用2085眼(1214名受试者)视野通过机器学习识别青光眼进展模式。
- 133眼(71例青光眼患者)在10周内采集10次视野,构成无变化重测数据集。
- 使用270眼(136例青光眼患者)独立数据集及生存分析进行比较。
主要发现
- 纵向数据集中检测25%眼进展时间:全局MD为5.2年(95%CI 4.1-6.5),区域wise为4.5年(4.0-5.5),点wise为3.9年(3.5-4.6),机器学习为3.5年(3.1-4.0)。
- 加入2次额外访视确认后,25%眼显示随后确认进展的时间:全局为6.6年(5.6-7.4),区域wise为5.7年(4.8-6.7),点wise为5.6年(4.7-6.5),机器学习为5.1年(4.5-6.0)。
关键数值与推荐
- 所有方法参数在重测数据集上设定以满足固定95%特异性。
- 主要比较指标为检测25%眼进展的时间及加入2次确认访视后确认进展的时间。
临床怎么用
- 机器学习视野进展指数可在固定95%特异性下较全局、区域及点wise指数更早检测青光眼进展。
- 机器学习对缓慢进展眼的检测优于其他方法。
局限性
- 原文未述局限性
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: Global indices of standard automated perimerty are insensitive to localized losses, while point-wise indices are sensitive but highly variable. Region-wise indices sit in between. This study introduces a machine learning-based index for glaucoma progression detection that outperforms global, region-wise, and point-wise indices. DESIGN: Development and comparison of a prognostic index. METHOD: Visual fields from 2085 eyes of 1214 subjects were used to identify glaucoma progression patterns using machine learning. Visual fields from 133 eyes of 71 glaucoma patients were collected 10 times over 10 weeks to provide a no-change, test-retest dataset. The parameters of all methods were identified using visual field sequences in the test-retest dataset to meet fixed 95% specificity. An independent dataset of 270 eyes of 136 glaucoma patients and survival analysis were used to compare methods. RESULTS: The time to detect progression in 25% of the eyes in the longitudinal dataset using global mean deviation (MD) was 5.2 (95% confidence interval, 4.1-6.5) years; 4.5 (4.0-5.5) years using region-wise, 3.9 (3.5-4.6) years using point-wise, and 3.5 (3.1-4.0) years using machine learning analysis. The time until 25% of eyes showed subsequently confirmed progression after 2 additional visits were included were 6.6 (5.6-7.4) years, 5.7 (4.8-6.7) years, 5.6 (4.7-6.5) years, and 5.1 (4.5-6.0) years for global, region-wise, point-wise, and machine learning analyses, respectively. CONCLUSIONS: Machine learning analysis detects progressing eyes earlier than other methods consistently, with or without confirmation visits. In particular, machine learning detects more slowly progressing eyes than other methods.
引用
- Yousefi S, Kiwaki T, Zheng Y, et al. Detection of Longitudinal Visual Field Progression in Glaucoma Using Machine Learning. Am J Ophthalmol. 2018. PMID: 29920226. doi:10.1016/j.ajo.2018.06.007
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。