在社区糖尿病眼部筛查项目中使用手持式视网膜成像进行综合人工智能分级的准确性。
Accuracy of Integrated Artificial Intelligence Grading Using Handheld Retinal Imaging in a Community Diabetic Eye Screening Program.
作者信息
Salongcay Recivall P, Aquino Lizzie Anne C, Alog Glenn P, Locaylocay Kaye B, Saunar Aileen V, Peto Tunde, Silva Paolo S
机构信息
Centre for Public Health, Queen's University Belfast, Belfast, United Kingdom.
Philippine Eye Research Institute, University of the Philippines, Manila, Philippines.
出版信息
Ophthalmol Sci. 2023 Dec 15;4(3):100457. doi: 10.1016/j.xops.2023.100457. eCollection 2024 May-Jun.
PURPOSE
To evaluate mydriatic handheld retinal imaging performance assessed by point-of-care (POC) artificial intelligence (AI) as compared with retinal image graders at a centralized reading center (RC) in identifying diabetic retinopathy (DR) and diabetic macular edema (DME).
DESIGN
Prospective, comparative study.
SUBJECTS
Five thousand five hundred eighty-five eyes from 2793 adult patients with diabetes.
METHODS
Point-of-care AI assessment of disc and macular handheld retinal images was compared with RC evaluation of validated 5-field handheld retinal images (disc, macula, superior, inferior, and temporal) in identifying referable DR (refDR; defined as moderate nonproliferative DR [NPDR], or worse, or any level of DME) and vision-threatening DR (vtDR; defined as severe NPDR or worse, or any level of center-involving DME [ciDME]). Reading center evaluation of the 5-field images followed the international DR/DME classification. Sensitivity (SN) and specificity (SP) for ungradable images, refDR, and vtDR were calculated.
MAIN OUTCOME MEASURES
Agreement for DR and DME; SN and SP for refDR, vtDR, and ungradable images.
RESULTS
Diabetic retinopathy severity by RC evaluation: no DR, 67.3%; mild NPDR, 9.7%; moderate NPDR, 8.6%; severe NPDR, 4.8%; proliferative DR, 3.8%; and ungradable, 5.8%. Diabetic macular edema severity by RC evaluation was as follows: no DME (80.4%), non-ciDME (7.7%), ciDME (4.4%), and ungradable (7.5%). Referable DR was present in 25.3% and vtDR was present in 17.5% of eyes. Images were ungradable for DR or DME in 7.5% by RC evaluation and 15.4% by AI. There was substantial agreement between AI and RC for refDR (κ = 0.66) and moderate agreement for vtDR (κ = 0.54). The SN/SP of AI grading compared with RC evaluation was 0.86/0.86 for refDR and 0.92/0.80 for vtDR.
CONCLUSIONS
This study demonstrates that POC AI following a defined handheld retinal imaging protocol at the time of imaging has SN and SP for refDR that meets the current United States Food and Drug Administration thresholds of 85% and 82.5%, but not for vtDR. Integrating AI at the POC could substantially reduce centralized RC burden and speed information delivery to the patient, allowing more prompt eye care referral.
FINANCIAL DISCLOSURES
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
目的
评估即时护理（POC）人工智能（AI）评估的散瞳手持式视网膜成像性能，并与集中阅片中心（RC）的视网膜图像分级人员在识别糖尿病视网膜病变（DR）和糖尿病性黄斑水肿（DME）方面进行比较。
设计
前瞻性比较研究。
研究对象
来自2793例成年糖尿病患者的5585只眼。
方法
将即时护理AI对视盘和黄斑手持式视网膜图像的评估与RC对经验证的5视野手持式视网膜图像（视盘、黄斑、上方、下方和颞侧）的评估进行比较，以识别可转诊的DR（refDR；定义为中度非增殖性DR [NPDR]或更严重，或任何程度的DME）和威胁视力的DR（vtDR；定义为重度NPDR或更严重，或任何程度的累及中心凹的DME [ciDME]）。RC对5视野图像的评估遵循国际DR/DME分类标准。计算不可分级图像、refDR和vtDR的敏感性（SN）和特异性（SP）。
主要观察指标
DR和DME的一致性；refDR、vtDR和不可分级图像的SN和SP。
结果
RC评估的糖尿病视网膜病变严重程度：无DR，67.3%；轻度NPDR，9.7%；中度NPDR，8.6%；重度NPDR，4.8%；增殖性DR，3.8%；不可分级，5.8%。RC评估的糖尿病性黄斑水肿严重程度如下：无DME（80.4%），非ciDME（7.7%），ciDME（4.4%），不可分级（7.5%）。25.3%的眼存在可转诊DR，17.5%的眼存在威胁视力的DR。RC评估中7.5%的图像因DR或DME不可分级，AI评估中为15.4%。AI与RC在refDR方面有高度一致性（κ = 0.66），在vtDR方面有中度一致性（κ = 0.54）。与RC评估相比，AI分级的refDR的SN/SP为0.86/0.86，vtDR为0.92/0.80。
结论
本研究表明，成像时遵循既定手持式视网膜成像方案的即时护理AI在refDR方面的SN和SP符合美国食品药品监督管理局目前85%和82.5%的阈值，但在vtDR方面不符合。在即时护理中整合AI可大幅减轻集中阅片中心的负担，并加快向患者传递信息，从而更及时地进行眼科护理转诊。
财务披露
本文末尾的脚注和披露中可能会有专有或商业披露信息。
Zotero 插件