Chaurasia Abadh K, Greatbatch Connor J, Hewitt Alex W
Menzies Institute for Medical Research, School of Medicine, University of Tasmania, Tasmania.
Centre for Eye Research Australia, University of Melbourne, Melbourne, Australia.
J Glaucoma. 2022 May 1;31(5):285-299. doi: 10.1097/IJG.0000000000002015. Epub 2022 Mar 18.
Artificial intelligence (AI) has been shown as a diagnostic tool for glaucoma detection through imaging modalities. However, these tools are yet to be deployed into clinical practice. This meta-analysis determined overall AI performance for glaucoma diagnosis and identified potential factors affecting their implementation.
We searched databases (Embase, Medline, Web of Science, and Scopus) for studies that developed or investigated the use of AI for glaucoma detection using fundus and optical coherence tomography (OCT) images. A bivariate random-effects model was used to determine the summary estimates for diagnostic outcomes. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis of Diagnostic Test Accuracy (PRISMA-DTA) extension was followed, and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was used for bias and applicability assessment.
Seventy-nine articles met inclusion criteria, with a subset of 66 containing adequate data for quantitative analysis. The pooled area under receiver operating characteristic curve across all studies for glaucoma detection was 96.3%, with a sensitivity of 92.0% (95% confidence interval: 89.0-94.0) and specificity of 94.0% (95% confidence interval: 92.0-95.0). The pooled area under receiver operating characteristic curve on fundus and OCT images was 96.2% and 96.0%, respectively. Mixed data set and external data validation had unsatisfactory diagnostic outcomes.
Although AI has the potential to revolutionize glaucoma care, this meta-analysis highlights that before such algorithms can be implemented into clinical care, a number of issues need to be addressed. With substantial heterogeneity across studies, many factors were found to affect the diagnostic performance. We recommend implementing a standard diagnostic protocol for grading, implementing external data validation, and analysis across different ethnicity groups.
人工智能（AI）已被证明是一种通过成像方式检测青光眼的诊断工具。然而，这些工具尚未应用于临床实践。本荟萃分析确定了AI在青光眼诊断中的总体性能，并确定了影响其应用的潜在因素。
我们在数据库（Embase、Medline、Web of Science和Scopus）中搜索了开发或研究使用AI通过眼底和光学相干断层扫描（OCT）图像检测青光眼的研究。采用双变量随机效应模型确定诊断结果的汇总估计值。遵循诊断试验准确性系统评价和荟萃分析的首选报告项目（PRISMA-DTA）扩展版，并使用诊断准确性研究质量评估-2（QUADAS-2）工具进行偏倚和适用性评估。
79篇文章符合纳入标准，其中66篇子集包含足够的数据进行定量分析。所有研究中用于青光眼检测的受试者操作特征曲线下的合并面积为96.3%，敏感性为92.0%（95%置信区间：89.0-94.0），特异性为94.0%（95%置信区间：92.0-95.0）。眼底和OCT图像上受试者操作特征曲线下的合并面积分别为96.2%和96.0%。混合数据集和外部数据验证的诊断结果不理想。
尽管AI有可能彻底改变青光眼的治疗方式，但本荟萃分析强调，在将此类算法应用于临床治疗之前，需要解决一些问题。由于各研究之间存在很大的异质性，发现许多因素会影响诊断性能。我们建议实施标准的诊断方案进行分级，实施外部数据验证，并对不同种族群体进行分析。
