Kamei Takuro, Miyake Masahiro, Sado Keina, Morino Kazuya, Mori Yuki, Tabara Yasuharu, Matsuda Fumihiko, Tamura Hiroshi, Tsujikawa Akitaka
Department of Ophthalmology and Visual Sciences, Kyoto University Graduate School of Medicine, 54 Kawahara-cho Syogoin Sakyo-ku, Kyoto, 606-8507, Japan.
Department of Ophthalmology, Osaka City General Hospital, Osaka, Japan.
Jpn J Ophthalmol. 2025 Apr 30. doi: 10.1007/s10384-025-01205-3.
To investigate the retinal age gap, defined as the difference between deep learning-predicted retinal age and chronological age, as a potential biomarker of systemic health in the Japanese population.
Prospective cohort study.
Data from the Nagahama Study, a large-scale Japanese cohort study, were used. Participants were divided into fine-tuning (n=2,261) and analysis (n=6,070) cohorts based on their visit status across the two periods. The fine-tuning cohort only included individuals without a history of systemic or cardiovascular diseases. A deep learning model, originally released in the Japan Ocular Imaging Registry, was fine-tuned using a fine-tuning cohort to predict retinal age from images. This refined model was then applied to the analysis cohort to calculate retinal age gaps. We conducted cross-sectional and longitudinal analyses to examine the association of these gaps with systemic and cardiovascular diseases.
The retinal age-prediction model achieved a mean absolute error of 3.00-3.42 years. Cross-sectional analysis revealed significant associations between the retinal age gap and a history of diabetes (β = 1.08, p < 0.001) and hyperlipidemia (β = -0.67, p < 0.001). Longitudinal analysis showed no significant association between the baseline retinal age gap and disease onset. However, onset of hypertension (β = 0.35, p = 0.049) and hyperlipidemia (β = 0.34, p = 0.035) showed marginal associations with an increase in retinal age gap over time.
The retinal age gap is a promising biomarker for systemic health, particularly in relation to diabetes, hypertension, and hyperlipidemia.
研究视网膜年龄差距（定义为深度学习预测的视网膜年龄与实际年龄之间的差异）作为日本人群全身健康潜在生物标志物的情况。
前瞻性队列研究。
使用来自日本大规模队列研究长滨研究的数据。根据参与者在两个时期的就诊状态，将其分为微调队列（n = 2261）和分析队列（n = 6070）。微调队列仅包括无全身或心血管疾病史的个体。最初在日本眼部成像登记处发布的深度学习模型，使用微调队列进行微调，以从图像预测视网膜年龄。然后将这个优化后的模型应用于分析队列以计算视网膜年龄差距。我们进行了横断面和纵向分析，以检查这些差距与全身和心血管疾病的关联。
视网膜年龄预测模型的平均绝对误差为3.00 - 3.42岁。横断面分析显示视网膜年龄差距与糖尿病史（β = 1.08，p < 0.001）和高脂血症（β = -0.67，p < 0.001）之间存在显著关联。纵向分析显示基线视网膜年龄差距与疾病发病之间无显著关联。然而，高血压发病（β = 0.35，p = 0.049）和高脂血症发病（β = 0.34，p = 0.035）与视网膜年龄差距随时间增加存在边缘关联。
视网膜年龄差距是全身健康的一个有前景的生物标志物，特别是与糖尿病、高血压和高脂血症相关。
