OBJECTIVE: To develop an AI model to identify myopia, strabismus, and ptosis using mobile photographs.
METHODS: This cross-sectional study was conducted at the Department of Ophthalmology of Shanghai Ninth People\'s Hospital from October 1, 2022, to September 30, 2023, and included children who were diagnosed with myopia, strabismus, or ptosis.
METHODS: A deep learning-based model was developed to identify myopia, strabismus, and ptosis. The performance of the model was assessed using sensitivity, specificity, accuracy, the area under the curve (AUC), positive predictive values (PPV), negative predictive values (NPV), positive likelihood ratios (P-LR), negative likelihood ratios (N-LR), and the F1-score. GradCAM++ was utilized to visually and analytically assess the impact of each region on the model. A sex subgroup analysis and an age subgroup analysis were performed to validate the model\'s generalizability.
RESULTS: A total of 1419 images obtained from 476 patients (225 female [47.27%]; 299 [62.82%] aged between 6 and 12 years) were used to build the model. Among them, 946 monocular images were used to identify myopia and ptosis, and 473 binocular images were used to identify strabismus. The model demonstrated good sensitivity in detecting myopia (0.84 [95% CI, 0.82-0.87]), strabismus (0.73 [95% CI, 0.70-0.77]), and ptosis (0.85 [95% CI, 0.82-0.87]). The model showed comparable performance in identifying eye disorders in both female and male children during sex subgroup analysis. There were differences in identifying eye disorders among different age subgroups.
CONCLUSIONS: In this cross-sectional study, the AI model demonstrated strong performance in accurately identifying myopia, strabismus, and ptosis using only smartphone images. These results suggest that such a model could facilitate the early detection of pediatric eye diseases in a convenient manner at home.
目标:开发一种识别近视的AI模型,斜视,和使用手机照片的眼睑。
方法:这项横断面研究于2022年10月1日至2023年9月30日在上海市第九人民医院眼科进行,包括被诊断为近视的儿童,斜视,或上睑下垂。
方法:开发了一种基于深度学习的模型来识别近视,斜视,和上眼睑。使用灵敏度评估模型的性能,特异性,准确度,曲线下面积(AUC),阳性预测值(PPV),负预测值(NPV),正似然比(P-LR),负似然比(N-LR),和F1得分。GradCAM++用于视觉和分析评估每个区域对模型的影响。进行性别亚组分析和年龄亚组分析以验证模型的普适性。
结果:从476名患者(225名女性[47.27%];299名[62.82%],年龄在6至12岁之间)获得的1419张图像被用于构建模型。其中,946张单目图像用于识别近视和上睑下垂,473张双目图像用于识别斜视。该模型在检测近视方面表现出良好的敏感性(0.84[95%CI,0.82-0.87]),斜视(0.73[95%CI,0.70-0.77]),和下垂(0.85[95%CI,0.82-0.87])。在性别亚组分析期间,该模型在识别女性和男性儿童的眼部疾病方面表现出可比的性能。不同年龄亚组在识别眼部疾病方面存在差异。
结论:在这项横断面研究中,AI模型在准确识别近视方面表现出强大的性能,斜视,和只使用智能手机图像的眼睑。这些结果表明,这种模型可以方便地在家中以方便的方式早期发现儿科眼部疾病。