基层医疗中自动检测糖尿病视网膜病变设备的诊断准确性
在基层医疗筛查场景中,纳入1616例2型糖尿病患者,评估深度学习增强设备(IDx-DR-EU-2.1)自动检测糖尿病视网膜病变(DR)的诊断准确性,以鹿特丹研究阅片中心按国际临床分类的判读为参考标准。设备对威胁视力DR(vtDR)的敏感度/特异度为100%(95%CI 77.1-100)/97.8%(95%CI 96.8-98.5),对高于轻度DR(mtmDR)为79.4%(95%CI 66.5-87.9)/93.8%(95%CI 92.1-94.9)。结论认为该设备在基层医疗中对vtDR和mtmDR均具有较高诊断准确性。
要点
- 设备对vtDR敏感度100%、特异度97.8%,但vtDR病例数较少。
- 设备对mtmDR敏感度79.4%、特异度93.8%,适用于基层筛查。
- 与独立阅片中心参考标准对照,支持其在基层医疗安全使用。
核心结论
- 深度学习增强设备在基层医疗中对vtDR和mtmDR检测均具有较高诊断准确性,可安全用于基层医疗。
研究设计与样本
- 在基层医疗筛查项目中,对就诊的2型糖尿病患者进行视网膜成像,共纳入1616例。
- 由深度学习增强设备(IDx-DR-EU-2.1)判读,并与鹿特丹研究阅片中心按国际临床DR分类的判读参考标准比较。
主要发现
- 设备对vtDR的敏感度/特异度为100%(95%CI 77.1-100)/97.8%(95%CI 96.8-98.5)。
- 设备对mtmDR的敏感度/特异度为79.4%(95%CI 66.5-87.9)/93.8%(95%CI 92.1-94.9)。
关键数值与推荐
- vtDR:敏感度100%(95%CI 77.1-100),特异度97.8%(95%CI 96.8-98.5)。
- mtmDR:敏感度79.4%(95%CI 66.5-87.9),特异度93.8%(95%CI 92.1-94.9)。
临床怎么用
- 可在基层医疗筛查流程中使用该设备自动判读视网膜图像,辅助识别需转诊的vtDR与mtmDR。
局限性
- vtDR病例数较少,其敏感度估计的置信区间较宽。
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
OBJECTIVE: To determine the diagnostic accuracy in a real-world primary care setting of a deep learning-enhanced device for automated detection of diabetic retinopathy (DR). RESEARCH DESIGN AND METHODS: Retinal images of people with type 2 diabetes visiting a primary care screening program were graded by a hybrid deep learning-enhanced device (IDx-DR-EU-2.1; IDx, Amsterdam, the Netherlands), and its classification of retinopathy (vision-threatening [vt]DR, more than mild [mtm]DR, and mild or more [mom]DR) was compared with a reference standard. This reference standard consisted of grading according to the International Clinical Classification of DR by the Rotterdam Study reading center. We determined the diagnostic accuracy of the hybrid deep learning-enhanced device (IDx-DR-EU-2.1) against the reference standard. RESULTS: A total of 1,616 people with type 2 diabetes were imaged. The hybrid deep learning-enhanced device's sensitivity/specificity against the reference standard was, respectively, for vtDR 100% (95% CI 77.1-100)/97.8% (95% CI 96.8-98.5) and for mtmDR 79.4% (95% CI 66.5-87.9)/93.8% (95% CI 92.1-94.9). CONCLUSIONS: The hybrid deep learning-enhanced device had high diagnostic accuracy for the detection of both vtDR (although the number of vtDR cases was low) and mtmDR in a primary care setting against an independent reading center. This allows its' safe use in a primary care setting.
引用
- Verbraak FD, Abramoff MD, Bausch GCF, et al. Diagnostic Accuracy of a Device for the Automated Detection of Diabetic Retinopathy in a Primary Care Setting. Diabetes Care. 2019. PMID: 30765436. doi:10.2337/dc18-0148
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。