Babenko Boris, Traynis Ilana, Chen Christina, Singh Preeti, Uddin Akib, Cuadros Jorge, Daskivich Lauren P, Maa April Y, Kim Ramasamy, Kang Eugene Yu-Chuan, Matias Yossi, Corrado Greg S, Peng Lily, Webster Dale R, Semturs Christopher, Krause Jonathan, Varadarajan Avinash V, Hammel Naama, Liu Yun
Google Health, Palo Alto, CA, USA.
Advanced Clinical, Deerfield, IL, USA.
Lancet Digit Health. 2023 May;5(5):e257-e264. doi: 10.1016/S2589-7500(23)00022-5. Epub 2023 Mar 23.
Photographs of the external eye were recently shown to reveal signs of diabetic retinal disease and elevated glycated haemoglobin. This study aimed to test the hypothesis that external eye photographs contain information about additional systemic medical conditions.
We developed a deep learning system (DLS) that takes external eye photographs as input and predicts systemic parameters, such as those related to the liver (albumin, aspartate aminotransferase [AST]); kidney (estimated glomerular filtration rate [eGFR], urine albumin-to-creatinine ratio [ACR]); bone or mineral (calcium); thyroid (thyroid stimulating hormone); and blood (haemoglobin, white blood cells [WBC], platelets). This DLS was trained using 123 130 images from 38 398 patients with diabetes undergoing diabetic eye screening in 11 sites across Los Angeles county, CA, USA. Evaluation focused on nine prespecified systemic parameters and leveraged three validation sets (A, B, C) spanning 25 510 patients with and without diabetes undergoing eye screening in three independent sites in Los Angeles county, CA, and the greater Atlanta area, GA, USA. We compared performance against baseline models incorporating available clinicodemographic variables (eg, age, sex, race and ethnicity, years with diabetes).
Relative to the baseline, the DLS achieved statistically significant superior performance at detecting AST >36·0 U/L, calcium <8·6 mg/dL, eGFR <60·0 mL/min/1·73 m, haemoglobin <11·0 g/dL, platelets <150·0 × 10/μL, ACR ≥300 mg/g, and WBC <4·0 × 10/μL on validation set A (a population resembling the development datasets), with the area under the receiver operating characteristic curve (AUC) of the DLS exceeding that of the baseline by 5·3-19·9% (absolute differences in AUC). On validation sets B and C, with substantial patient population differences compared with the development datasets, the DLS outperformed the baseline for ACR ≥300·0 mg/g and haemoglobin <11·0 g/dL by 7·3-13·2%.
We found further evidence that external eye photographs contain biomarkers spanning multiple organ systems. Such biomarkers could enable accessible and non-invasive screening of disease. Further work is needed to understand the translational implications.
Google.
近期研究表明，眼部外观照片能够揭示糖尿病视网膜病变迹象及糖化血红蛋白升高情况。本研究旨在验证眼部外观照片是否包含有关其他全身性疾病的信息这一假设。
我们开发了一种深度学习系统（DLS），该系统以眼部外观照片作为输入，预测全身性参数，如与肝脏相关的参数（白蛋白、天冬氨酸转氨酶[AST]）；肾脏相关的参数（估计肾小球滤过率[eGFR]、尿白蛋白与肌酐比值[ACR]）；骨骼或矿物质相关的参数（钙）；甲状腺相关的参数（促甲状腺激素）；以及血液相关的参数（血红蛋白、白细胞[WBC]、血小板）。该DLS使用来自美国加利福尼亚州洛杉矶县11个地点接受糖尿病眼部筛查的38398例糖尿病患者的123130张图像进行训练。评估聚焦于9个预先设定的全身性参数，并利用了三个验证集（A、B、C），这些验证集涵盖了在美国加利福尼亚州洛杉矶县和佐治亚州大亚特兰大地区三个独立地点接受眼部筛查的25510例有或无糖尿病的患者。我们将该模型的性能与纳入可用临床人口统计学变量（如年龄、性别、种族和民族、糖尿病病程）的基线模型进行了比较。
与基线相比，在验证集A（一个与开发数据集相似的人群）上，DLS在检测AST>36.0 U/L、钙<8.6 mg/dL、eGFR<60.0 mL/min/1.73 m²、血红蛋白<11.0 g/dL、血小板<150.0×10⁹/μL、ACR≥300 mg/g和WBC<4.0×10⁹/μL方面取得了具有统计学意义的卓越性能，DLS的受试者工作特征曲线下面积（AUC）比基线高出5.3 - 19.9%（AUC的绝对差异）。在验证集B和C上，与开发数据集相比患者群体存在显著差异，DLS在检测ACR≥300.0 mg/g和血红蛋白<11.0 g/dL方面比基线高出7.3 - 13.2%。
我们发现了进一步的证据，表明眼部外观照片包含跨越多个器官系统的生物标志物。这些生物标志物能够实现对疾病的便捷且非侵入性筛查。需要进一步开展工作以了解其转化意义。
谷歌。
