超广角彩色眼底图像与人工智能诊断糖尿病视网膜病变:系统综述与荟萃分析
该系统综述与荟萃分析检索截至2025年2月9日的文献,共纳入17项使用超广角眼底图像(UWFI)联合人工智能(AI)评估糖尿病视网膜病变(DR)的研究,其中4项进入荟萃分析,且全部使用Optos软件。AI驱动UWFI筛查DR的汇总敏感度为85.0%、特异度为72.5%、受试者工作特征曲线下面积为0.870(0.838-0.897),敏感度可接受但特异度有限,作者提示因研究数量有限需谨慎解读。
要点
- AI联合UWFI筛查DR汇总敏感度85.0%、特异度72.5%,敏感度可接受而特异度有限。
- 汇总AUC为0.870(0.838-0.897),基于4项进入荟萃分析的研究。
- 纳入研究均使用Optos软件,作者呼吁在多种UWF平台开展更大样本的外部验证。
核心结论
- 基于UWFI的AI驱动DR筛查可能达到可接受的敏感度,但特异度有限。
- 鉴于现有研究数量有限,上述发现应谨慎解读。
- 需在更大、更多样化的数据集上跨UWF平台进行严格外部验证,以改善泛化性并明确其临床作用。
研究设计与样本
- 系统综述与荟萃分析,遵循PRISMA指南,检索PubMed、Scopus、Cochrane Library和Web of Science至2025年2月9日。
- 共识别527条记录,17项研究纳入系统综述,4项纳入荟萃分析。
- 纳入研究全部使用Optos软件,研究质量采用Joanna Briggs Institute诊断准确性关键评价清单评估。
- 纳入研究中2项评估DR与多种视网膜疾病的区分,6项按指南量表进行DR分期分类,6项评估DR筛查,另各有1项分别聚焦可转诊视网膜病变检测、DR进展预测和临床DR特征检测。
- 采用森林图和汇总受试者工作特征曲线估计敏感度与特异度。
主要发现
- AI驱动UWFI筛查DR的汇总敏感度为85.0%,汇总特异度为72.5%。
- 汇总AUC为0.870(0.838-0.897)。
- UWFI-based AI筛查显示敏感度可接受但特异度有限。
关键数值与推荐
- AI驱动UWFI筛查DR的汇总敏感度85.0%、特异度72.5%、AUC 0.870(0.838-0.897),基于荟萃分析的4项研究。
临床怎么用
- UWFI联合AI可作为DR筛查的辅助手段,其敏感度可接受但特异度有限,阳性结果需结合临床复核。
- 现有证据仅来自使用Optos软件的研究,跨平台应用前应谨慎。
- 作者建议在更大、多样化数据集和跨UWF平台外部验证后再明确其临床定位。
局限性
- 可纳入荟萃分析的研究数量有限(4项),作者提示结果需谨慎解读。
- 纳入研究全部使用Optos软件,平台单一,泛化性受限。
- 作者指出需更大、更多样化数据集及跨UWF平台的严格外部验证。
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: Ultrawide-field (UWF) fundus cameras capture a larger retinal area without pupil dilation. The authors summarized evidence and diagnostic performance of artificial intelligence (AI)-driven diabetic retinopathy (DR) assessments using UWF images (UWFIs). METHODS: The authors searched PubMed, Scopus, the Cochrane Library, and Web of Science to February 9, 2025, for studies evaluating DR using UWFIs and AI analyses. They followed the PRISMA guidelines and assessed study quality using the Joanna Briggs Institute Critical Appraisal Checklist for diagnostic accuracy. Forest plots and summary receiver operating characteristic curves estimated sensitivity and specificity of AI-driven DR screening using UWFI. RESULTS: Of 527 records identified, 17 studies were included in the systematic review and four in the meta-analysis. All studies used Optos software. Among the included studies, two evaluated DR discrimination from multiple retinal disorders, six addressed DR stage classification based on guideline scales, six evaluated DR screening, and one each focused on referable retinal pathology detection, DR progression prediction, and detection of clinical DR features. The summary sensitivity, specificity, and area under receiver operating characteristic curve for AI-driven DR screening using UWFI were 85.0%, 72.5%, and 0.870 (0.838-0.897), respectively. UWFI-based AI screening showed acceptable sensitivity but limited specificity. CONCLUSION: AI-driven DR screening using UWFIs may achieve acceptable sensitivity but with limited specificity; however, these findings should be interpreted with caution, given the limited number of available studies. Further studies using larger, diverse data sets with rigorous external validation across UWF platforms are needed to improve generalizability and clarify the clinical role of UWFI-based AI.
引用
- Hirosawa K, Inomata T, Nagino K, et al. ULTRAWIDE-FIELD COLOR FUNDUS IMAGES AND ARTIFICIAL INTELLIGENCE FOR DIAGNOSIS OF DIABETIC RETINOPATHY: A Systematic Review and Meta-Analysis. Retina. 2026. PMID: 42497322. doi:10.1097/IAE.0000000000004939
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。