Department of Ophthalmology, Shengjing Hospital of China Medical University, Shenyang, China.
Front Endocrinol (Lausanne). 2023 Jun 13;14:1197783. doi: 10.3389/fendo.2023.1197783. eCollection 2023.
To systematically evaluate the diagnostic value of an artificial intelligence (AI) algorithm model for various types of diabetic retinopathy (DR) in prospective studies over the previous five years, and to explore the factors affecting its diagnostic effectiveness.
A search was conducted in Cochrane Library, Embase, Web of Science, PubMed, and IEEE databases to collect prospective studies on AI models for the diagnosis of DR from January 2017 to December 2022. We used QUADAS-2 to evaluate the risk of bias in the included studies. Meta-analysis was performed using MetaDiSc and STATA 14.0 software to calculate the combined sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio of various types of DR. Diagnostic odds ratios, summary receiver operating characteristic (SROC) plots, coupled forest plots, and subgroup analysis were performed according to the DR categories, patient source, region of study, and quality of literature, image, and algorithm.
Finally, 21 studies were included. Meta-analysis showed that the pooled sensitivity, specificity, pooled positive likelihood ratio, pooled negative likelihood ratio, area under the curve, Cochrane Q index, and pooled diagnostic odds ratio of AI model for the diagnosis of DR were 0.880 (0.875-0.884), 0.912 (0.99-0.913), 13.021 (10.738-15.789), 0.083 (0.061-0.112), 0.9798, 0.9388, and 206.80 (124.82-342.63), respectively. The DR categories, patient source, region of study, sample size, quality of literature, image, and algorithm may affect the diagnostic efficiency of AI for DR.
AI model has a clear diagnostic value for DR, but it is influenced by many factors that deserve further study.
https://www.crd.york.ac.uk/prospero/, identifier CRD42023389687.
系统评估过去五年内前瞻性研究中用于各种类型糖尿病视网膜病变（DR）的人工智能（AI）算法模型的诊断价值，并探讨影响其诊断效果的因素。
在 Cochrane Library、Embase、Web of Science、PubMed 和 IEEE 数据库中进行检索，收集 2017 年 1 月至 2022 年 12 月期间用于 DR 诊断的 AI 模型的前瞻性研究。使用 QUADAS-2 评估纳入研究的偏倚风险。使用 MetaDiSc 和 STATA 14.0 软件进行 Meta 分析，计算各种类型 DR 的合并敏感性、特异性、阳性似然比和阴性似然比。根据 DR 类别、患者来源、研究区域以及文献、图像和算法质量，进行诊断比值比、汇总受试者工作特征（SROC）曲线、联合森林图和亚组分析。
最终纳入 21 项研究。Meta 分析显示，AI 模型用于诊断 DR 的合并敏感性、特异性、合并阳性似然比、合并阴性似然比、曲线下面积、Cochrane Q 指数和合并诊断比值比分别为 0.880（0.875-0.884）、0.912（0.99-0.913）、13.021（10.738-15.789）、0.083（0.061-0.112）、0.9798、0.9388 和 206.80（124.82-342.63）。DR 类别、患者来源、研究区域、样本量、文献质量、图像和算法可能影响 AI 对 DR 的诊断效能。
AI 模型对 DR 具有明确的诊断价值，但受许多因素影响，值得进一步研究。
https://www.crd.york.ac.uk/prospero/，标识符 CRD42023389687。
