深度学习算法与人工分级在印度检测糖尿病视网膜病变的性能比较
这项在印度两家眼科中心开展的前瞻性观察研究纳入3049例糖尿病患者,比较自动糖尿病视网膜病变(DR)分级系统与人工分级(由1名培训分级员和1名视网膜专科医生分别完成,分歧时由3名视网膜专科医生小组裁定作为参考标准)的性能。自动系统在Aravind眼科医院数据集上敏感度88.9%、特异度92.2%、AUC 0.963,在Sankara Nethralaya数据集上敏感度92.1%、特异度95.2%、AUC 0.980,性能等于或超过人工分级,作者认为该自动DR系统可在印度患者人群中推广并支持扩大筛查项目。
要点
- 自动DR系统在Aravind数据集敏感度88.9%、特异度92.2%,在Sankara Nethralaya数据集敏感度92.1%、特异度95.2%。
- 人工分级个体非裁定者敏感度73.4%至89.8%、特异度83.5%至98.7%,自动系统性能等于或超过人工分级。
- 作者认为该自动系统可在印度患者中推广,并证明用自动DR分级扩大筛查项目的可行性。
核心结论
- 作者认为该自动DR系统在前瞻性设置下可推广至印度患者人群,并证明使用自动DR分级系统扩大筛查项目的可行性。
研究设计与样本
- 前瞻性观察研究,在印度两家眼科中心(Aravind眼科医院和Sankara Nethralaya)纳入3049例糖尿病患者,数据收集与患者入组时间为Aravind 2016年4月至2016年7月、Sankara Nethralaya 2016年5月至2017年4月,模型于2016年3月训练并固定。
- 自动DR分级系统与人工分级比较,人工分级由每个中心的1名培训分级员和1名视网膜专科医生完成,分歧病例由3名视网膜专科医生小组裁定作为参考标准。
主要发现
- 3049例患者中1091例(35.8%)为女性,Aravind与Sankara Nethralaya患者的平均(SD)年龄分别为56.6(9.0)岁和56.0(10.0)岁。
- 对于中度或更差DR,个体非裁定者人工分级的敏感度范围为73.4%至89.8%,特异度范围为83.5%至98.7%。
- 自动DR系统在Aravind眼科医院数据集上敏感度88.9%(95% CI,85.8-91.5)、特异度92.2%(95% CI,90.3-93.8)、AUC 0.963。
- 自动DR系统在Sankara Nethralaya数据集上敏感度92.1%(95% CI,90.1-93.8)、特异度95.2%(95% CI,94.2-96.1)、AUC 0.980。
关键数值与推荐
- 主要结局指标为中度或更差DR或需转诊的糖尿病黄斑水肿的敏感度和特异度。
- 自动DR系统性能等于或超过人工分级。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
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
IMPORTANCE: More than 60 million people in India have diabetes and are at risk for diabetic retinopathy (DR), a vision-threatening disease. Automated interpretation of retinal fundus photographs can help support and scale a robust screening program to detect DR. OBJECTIVE: To prospectively validate the performance of an automated DR system across 2 sites in India. DESIGN, SETTING, AND PARTICIPANTS: This prospective observational study was conducted at 2 eye care centers in India (Aravind Eye Hospital and Sankara Nethralaya) and included 3049 patients with diabetes. Data collection and patient enrollment took place between April 2016 and July 2016 at Aravind and May 2016 and April 2017 at Sankara Nethralaya. The model was trained and fixed in March 2016. INTERVENTIONS: Automated DR grading system compared with manual grading by 1 trained grader and 1 retina specialist from each site. Adjudication by a panel of 3 retinal specialists served as the reference standard in the cases of disagreement. MAIN OUTCOMES AND MEASURES: Sensitivity and specificity for moderate or worse DR or referable diabetic macula edema. RESULTS: Of 3049 patients, 1091 (35.8%) were women and the mean (SD) age for patients at Aravind and Sankara Nethralaya was 56.6 (9.0) years and 56.0 (10.0) years, respectively. For moderate or worse DR, the sensitivity and specificity for manual grading by individual nonadjudicator graders ranged from 73.4% to 89.8% and from 83.5% to 98.7%, respectively. The automated DR system's performance was equal to or exceeded manual grading, with an 88.9% sensitivity (95% CI, 85.8-91.5), 92.2% specificity (95% CI, 90.3-93.8), and an area under the curve of 0.963 on the data set from Aravind Eye Hospital and 92.1% sensitivity (95% CI, 90.1-93.8), 95.2% specificity (95% CI, 94.2-96.1), and an area under the curve of 0.980 on the data set from Sankara Nethralaya. CONCLUSIONS AND RELEVANCE: This study shows that the automated DR system generalizes to this population of Indian patients in a prospective setting and demonstrates the feasibility of using an automated DR grading system to expand screening programs.
引用
- Gulshan V, Rajan RP, Widner K, et al. Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India. JAMA Ophthalmol. 2019. PMID: 31194246. doi:10.1001/jamaophthalmol.2019.2004
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。