Department of Ophthalmology and Visual Science, Tokyo Medical and Dental University, Tokyo, Japan.
Department of Ophthalmology, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, China.
JAMA Ophthalmol. 2023 Dec 1;141(12):1117-1124. doi: 10.1001/jamaophthalmol.2023.4786.
High myopia is a global concern due to its escalating prevalence and the potential risk of severe visual impairment caused by pathologic myopia. Using artificial intelligence to estimate future visual acuity (VA) could help clinicians to identify and monitor patients with a high risk of vision reduction in advance.
To develop machine learning models to predict VA at 3 and 5 years in patients with high myopia.
DESIGN, SETTING, AND PARTICIPANTS: This retrospective, single-center, cohort study was performed on patients whose best-corrected VA (BCVA) at 3 and 5 years was known. The ophthalmic examinations of these patients were performed between October 2011 and May 2021. Thirty-four variables, including general information, basic ophthalmic information, and categories of myopic maculopathy based on fundus and optical coherence tomography images, were collected from the medical records for analysis.
Regression models were developed to predict BCVA at 3 and 5 years, and a binary classification model was developed to predict the risk of developing visual impairment at 5 years. The performance of models was evaluated by discrimination metrics, calibration belts, and decision curve analysis. The importance of relative variables was assessed by explainable artificial intelligence techniques.
A total of 1616 eyes from 967 patients (mean [SD] age, 58.5 [14.0] years; 678 female [70.1%]) were included in this analysis. Findings showed that support vector machines presented the best prediction of BCVA at 3 years (R2 = 0.682; 95% CI, 0.625-0.733) and random forest at 5 years (R2 = 0.660; 95% CI, 0.604-0.710). To predict the risk of visual impairment at 5 years, logistic regression presented the best performance (area under the receiver operating characteristic curve = 0.870; 95% CI, 0.816-0.912). The baseline BCVA (logMAR odds ratio [OR], 0.298; 95% CI, 0.235-0.378; P < .001), prior myopic macular neovascularization (OR, 3.290; 95% CI, 2.209-4.899; P < .001), age (OR, 1.578; 95% CI, 1.227-2.028; P < .001), and category 4 myopic maculopathy (OR, 4.899; 95% CI, 1.431-16.769; P = .01) were the 4 most important predicting variables and associated with increased risk of visual impairment at 5 years.
Study results suggest that developing models for accurate prediction of the long-term VA for highly myopic eyes based on clinical and imaging information is feasible. Such models could be used for the clinical assessments of future visual acuity.
由于高度近视的患病率不断上升，以及病理性近视导致严重视力损害的潜在风险，高度近视成为了一个全球性的关注点。使用人工智能来预测未来的视力（VA）可以帮助临床医生提前识别和监测有视力下降风险的患者。
开发机器学习模型来预测高度近视患者的 3 年和 5 年 VA。
设计、地点和参与者：这是一项回顾性、单中心、队列研究，对已知 3 年和 5 年最佳矫正视力（BCVA）的患者进行研究。这些患者的眼科检查在 2011 年 10 月至 2021 年 5 月期间进行。从病历中收集了 34 个变量，包括一般信息、基本眼科信息以及基于眼底和光学相干断层扫描图像的近视性黄斑病变类别。
开发了回归模型来预测 3 年和 5 年的 BCVA，并开发了一个二进制分类模型来预测 5 年发生视力损害的风险。通过判别度量、校准带和决策曲线分析来评估模型的性能。通过可解释人工智能技术评估相对变量的重要性。
本研究共纳入了 967 名患者的 1616 只眼（平均[标准差]年龄为 58.5[14.0]岁；678 名女性[70.1%]）。研究结果表明，支持向量机在预测 3 年 BCVA 方面表现最佳（R2=0.682；95%置信区间，0.625-0.733），随机森林在预测 5 年 BCVA 方面表现最佳（R2=0.660；95%置信区间，0.604-0.710）。为了预测 5 年发生视力损害的风险，逻辑回归表现最佳（受试者工作特征曲线下面积=0.870；95%置信区间，0.816-0.912）。基线 BCVA（logMAR 比值比[OR]，0.298；95%置信区间，0.235-0.378；P<0.001）、既往近视性黄斑新生血管（OR，3.290；95%置信区间，2.209-4.899；P<0.001）、年龄（OR，1.578；95%置信区间，1.227-2.028；P<0.001）和 4 类近视性黄斑病变（OR，4.899；95%置信区间，1.431-16.769；P=0.01）是 4 个最重要的预测变量，与 5 年发生视力损害的风险增加相关。
研究结果表明，基于临床和影像学信息，开发高度近视眼长期 VA 准确预测模型是可行的。这些模型可用于未来视力的临床评估。
