Literature DB >> 35748936

Machine learning predicting myopic regression after corneal refractive surgery using preoperative data and fundus photography.

Juntae Kim1, Ik Hee Ryu2,3, Jin Kuk Kim2,3, In Sik Lee2, Hong Kyu Kim4, Eoksoo Han5, Tae Keun Yoo6,7,8.   

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.
© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Entities:  

Keywords:  Fundus photography; Machine learning; Myopic regression; Refractive surgery

Mesh:

Year:  2022        PMID: 35748936     DOI: 10.1007/s00417-022-05738-y

Source DB:  PubMed          Journal:  Graefes Arch Clin Exp Ophthalmol        ISSN: 0721-832X            Impact factor:   3.535


  18 in total

1.  Predictors of Myopic Regression for Laser-assisted Subepithelial Keratomileusis and Laser-assisted in Situ Keratomileusis Flap Creation with Mechanical Microkeratome and Femtosecond Laser in Low and Moderate Myopia.

Authors:  Jihong Zhou; Yan Gao; Shaowei Li; Wei Gu; Lijuan Wu; Xiuhua Guo
Journal:  Ophthalmic Epidemiol       Date:  2019-12-26       Impact factor: 1.648

Review 2.  Refractive surgery.

Authors:  Tae-Im Kim; Jorge L Alió Del Barrio; Mark Wilkins; Beatrice Cochener; Marcus Ang
Journal:  Lancet       Date:  2019-05-18       Impact factor: 79.321

3.  Deep Learning for Predicting Refractive Error From Retinal Fundus Images.

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

4.  Myopic regression after photorefractive keratectomy.

Authors:  J H Kim; W J Sah; C K Park; T W Hahn; M S Kim
Journal:  Ophthalmic Surg Lasers       Date:  1996-05

Review 5.  Refractive regression after laser in situ keratomileusis.

Authors:  Mabel K Yan; John Sm Chang; Tommy Cy Chan
Journal:  Clin Exp Ophthalmol       Date:  2018-05-17       Impact factor: 4.207

6.  Visual outcomes after three different surgical procedures for correction of refractive error in patients with thin corneas.

Authors:  Hye Seong Hwang; Hyun Jeong Lee; Seong Jun Lee; Jae-Hyung Kim
Journal:  Int J Ophthalmol       Date:  2020-06-18       Impact factor: 1.779

7.  The economic cost of myopia in adults aged over 40 years in Singapore.

Authors:  Ying-Feng Zheng; Chen-Wei Pan; Junxing Chay; Tien Y Wong; Eric Finkelstein; Seang-Mei Saw
Journal:  Invest Ophthalmol Vis Sci       Date:  2013-11-13       Impact factor: 4.799

8.  An interval-censored model for predicting myopic regression after laser in situ keratomileusis.

Authors:  Yun-I Chen; Kuo-Liong Chien; I-Jong Wang; Amy Ming-Fang Yen; Li-Sheng Chen; Pi-Jung Lin; Tony Hsiu-Hsi Chen
Journal:  Invest Ophthalmol Vis Sci       Date:  2007-08       Impact factor: 4.799

9.  Reduction of corneal epithelial thickness during medical treatment for myopic regression following FS-LASIK.

Authors:  Ik-Hee Ryu; Wook Kyum Kim; Myoung Sik Nam; Jin Kook Kim; Sun Woong Kim
Journal:  BMC Ophthalmol       Date:  2020-07-18       Impact factor: 2.209

10.  Is the axial length a risk factor for post-LASIK myopic regression?

Authors:  Amr A Gab-Alla
Journal:  Graefes Arch Clin Exp Ophthalmol       Date:  2020-10-31       Impact factor: 3.117

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.