Juntae Kim1, Ik Hee Ryu2,3, Jin Kuk Kim2,3, In Sik Lee2, Hong Kyu Kim4, Eoksoo Han5, Tae Keun Yoo6,7,8. 1. DATARIZE, Seoul, Korea. 2. B&VIIT Eye Center, B2 GT Tower, 1317-23 Seocho-Dong, Seocho-Gu, Seoul, South Korea. 3. VISUWORKS, Seoul, South Korea. 4. Department of Ophthalmology, Dankook University Hospital, Dankook University College of Medicine, Cheonan, South Korea. 5. Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea. 6. B&VIIT Eye Center, B2 GT Tower, 1317-23 Seocho-Dong, Seocho-Gu, Seoul, South Korea. eyetaekeunyoo@gmail.com. 7. VISUWORKS, Seoul, South Korea. eyetaekeunyoo@gmail.com. 8. Department of Ophthalmology, Aerospace Medical Center, Republic of Korea Air Force, Cheongju, South Korea. eyetaekeunyoo@gmail.com.
Abstract
PURPOSE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.
PURPOSE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.
Authors: Avinash V Varadarajan; Ryan Poplin; Katy Blumer; Christof Angermueller; Joe Ledsam; Reena Chopra; Pearse A Keane; Greg S Corrado; Lily Peng; Dale R Webster Journal: Invest Ophthalmol Vis Sci Date: 2018-06-01 Impact factor: 4.799