Kim Juntae, Ryu Ik Hee, Kim Jin Kuk, Lee In Sik, Kim Hong Kyu, Han Eoksoo, Yoo Tae Keun
DATARIZE, Seoul, Korea.
B&VIIT Eye Center, B2 GT Tower, 1317-23 Seocho-Dong, Seocho-Gu, Seoul, South Korea.
Graefes Arch Clin Exp Ophthalmol. 2022 Nov;260(11):3701-3710. doi: 10.1007/s00417-022-05738-y. Epub 2022 Jun 24.
Myopic regression after surgery is the most common long-term complication of refractive surgery, but it is difficult to identify myopic regression without long-term observation. This study aimed to develop machine learning models to identify high-risk patients for refractive regression based on preoperative data and fundus photography.
This retrospective study assigned subjects to the training (n = 1606 eyes) and validation (n = 403 eyes) datasets with chronological data splitting. Machine learning models with ResNet50 (for image analysis) and XGBoost (for integration of all variables and fundus photography) were developed based on subjects who underwent corneal refractive surgery. The primary outcome was the predictive performance for the presence of myopic regression at 4 years of follow-up examination postoperatively.
By integrating all factors and fundus photography, the final combined machine learning model showed good performance to predict myopic regression of more than 0.5 D (area under the receiver operating characteristic curve [ROC-AUC], 0.753; 95% confidence interval [CI], 0.710-0.793). The performance of the final model was better than the single ResNet50 model only using fundus photography (ROC-AUC, 0.673; 95% CI, 0.627-0.716). The top-five most important input features were fundus photography, preoperative anterior chamber depth, planned ablation thickness, age, and preoperative central corneal thickness.
Our machine learning algorithm provides an efficient strategy to identify high-risk patients with myopic regression without additional labor, cost, and time. Surgeons might benefit from preoperative risk assessment of myopic regression, patient counseling before surgery, and surgical option decisions.
手术后近视回退是屈光手术最常见的长期并发症，但若无长期观察则难以识别近视回退。本研究旨在基于术前数据和眼底照片开发机器学习模型，以识别屈光回退的高危患者。
本回顾性研究采用按时间顺序的数据拆分方法，将受试者分配到训练数据集（n = 1606只眼）和验证数据集（n = 403只眼）。基于接受角膜屈光手术的受试者，开发了具有ResNet50（用于图像分析）和XGBoost（用于整合所有变量和眼底照片）的机器学习模型。主要结局是术后4年随访检查时近视回退是否存在的预测性能。
通过整合所有因素和眼底照片，最终的联合机器学习模型在预测近视回退超过0.5 D方面表现良好（受试者操作特征曲线下面积[ROC-AUC]，0.753；95%置信区间[CI]，0.710 - 0.793）。最终模型的性能优于仅使用眼底照片的单一ResNet50模型（ROC-AUC，0.673；95% CI，0.627 - 0.716）。最重要的五个输入特征是眼底照片、术前前房深度、计划消融厚度、年龄和术前中央角膜厚度。
我们的机器学习算法提供了一种有效的策略，无需额外的人力、成本和时间即可识别近视回退的高危患者。外科医生可能会从近视回退的术前风险评估、手术前的患者咨询以及手术方案决策中受益。
