Department of Ophthalmology, Guangdong Academy of Medical Sciences, Guangdong Provincial People's Hospital, Guangzhou, China.
Centre for Eye Research Australia, Ophthalmology, University of Melbourne, Melbourne, Australia.
BMC Med. 2022 Nov 30;20(1):466. doi: 10.1186/s12916-022-02620-w.
The aim of this study is to investigate the association of retinal age gap with the risk of incident stroke and its predictive value for incident stroke.
A total of 80,169 fundus images from 46,969 participants in the UK Biobank cohort met the image quality standard. A deep learning model was constructed based on 19,200 fundus images of 11,052 disease-free participants at baseline for age prediction. Retinal age gap (retinal age predicted based on the fundus image minus chronological age) was generated for the remaining 35,917 participants. Stroke events were determined by data linkage to hospital records on admissions and diagnoses, and national death registers, whichever occurred earliest. Cox proportional hazards regression models were used to estimate the effect of retinal age gap on risk of stroke. Logistic regression models were used to estimate the predictive value of retinal age and well-established risk factors in 10-year stroke risk.
A total of 35,304 participants without history of stroke at baseline were included. During a median follow-up of 5.83 years, 282 (0.80%) participants had stroke events. In the fully adjusted model, each one-year increase in the retinal age gap was associated with a 4% increase in the risk of stroke (hazard ratio [HR] = 1.04, 95% confidence interval [CI]: 1.00-1.08, P = 0.029). Compared to participants with retinal age gap in the first quintile, participants with retinal age gap in the fifth quintile had significantly higher risks of stroke events (HR = 2.37, 95% CI: 1.37-4.10, P = 0.002). The predictive capability of retinal age alone was comparable to the well-established risk factor-based model (AUC=0.676 vs AUC=0.661, p=0.511).
We found that retinal age gap was significantly associated with incident stroke, implying the potential of retinal age gap as a predictive biomarker of stroke risk.
本研究旨在探讨视网膜年龄差距与卒中事件风险的相关性及其对卒中事件的预测价值。
从 UK Biobank 队列中符合图像质量标准的 46969 名参与者的 80169 张眼底图像中，选择 19200 张无疾病的 11052 名参与者的眼底图像，基于深度学习模型预测年龄。为其余 35917 名参与者生成视网膜年龄差距（基于眼底图像预测的年龄减去实际年龄）。通过与医院记录的入院和诊断以及国家死亡登记相关联，确定卒中事件。使用 Cox 比例风险回归模型估计视网膜年龄差距对卒中风险的影响。使用逻辑回归模型估计视网膜年龄和经过验证的 10 年卒中风险的危险因素的预测价值。
共纳入 35304 名基线无卒中史的参与者。在中位数为 5.83 年的随访期间，282（0.80%）名参与者发生卒中事件。在完全调整模型中，视网膜年龄差距每增加 1 年，卒中风险增加 4%（风险比 [HR] = 1.04，95%置信区间 [CI]：1.00-1.08，P = 0.029）。与视网膜年龄差距处于第一五分位的参与者相比，视网膜年龄差距处于第五五分位的参与者发生卒中事件的风险显著更高（HR = 2.37，95% CI：1.37-4.10，P = 0.002）。视网膜年龄单独的预测能力与经过验证的基于危险因素的模型相当（AUC=0.676 与 AUC=0.661，p=0.511）。
我们发现视网膜年龄差距与卒中事件显著相关，提示视网膜年龄差距可能是卒中风险的预测生物标志物。
