Prediction of postoperative visual acuity in patients with age-related cataracts using macular optical coherence tomography-based deep learning method

Jingwen Wang; Jinhong Wang; Dan Chen; Xingdi Wu; Zhe Xu; Xuewen Yu; Siting Sheng; Xueqi Lin; Xiang Chen; Jian Wu; Haochao Ying; Wen Xu

doi:10.3389/fmed.2023.1165135

Prediction of postoperative visual acuity in patients with age-related cataracts using macular optical coherence tomography-based deep learning method

Front Med (Lausanne). 2023 May 12:10:1165135. doi: 10.3389/fmed.2023.1165135. eCollection 2023.

Authors

Jingwen Wang¹, Jinhong Wang², Dan Chen¹, Xingdi Wu¹, Zhe Xu¹, Xuewen Yu^{1

3}, Siting Sheng¹, Xueqi Lin¹, Xiang Chen¹, Jian Wu⁴, Haochao Ying⁵, Wen Xu¹

Affiliations

¹ Eye Center of the Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
² College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China.
³ Department of Ophthalmology, The First People's Hospital of Xiaoshan District, Xiaoshan Affiliated Hospital of Wenzhou Medical University, Hangzhou, Zhejiang, China.
⁴ Second Affiliated Hospital School of Medicine, School of Public Health, and Institute of Wenzhou, Zhejiang University, Hangzhou, Zhejiang, China.
⁵ School of Public Health, Zhejiang University, Hangzhou, Zhejiang, China.

Abstract

Background: To predict postoperative visual acuity (VA) in patients with age-related cataracts using macular optical coherence tomography-based deep learning method.

Methods: A total of 2,051 eyes from 2,051 patients with age-related cataracts were included. Preoperative optical coherence tomography (OCT) images and best-corrected visual acuity (BCVA) were collected. Five novel models (I, II, III, IV, and V) were proposed to predict postoperative BCVA. The dataset was randomly divided into a training (n = 1,231), validation (n = 410), and test set (n = 410). The performance of the models in predicting exact postoperative BCVA was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The performance of the models in predicting whether postoperative BCVA was improved by at least two lines in the visual chart (0.2LogMAR) was evaluated using precision, sensitivity, accuracy, F1 and area under curve (AUC).

Results: Model V containing preoperative OCT images with horizontal and vertical B-scans, macular morphological feature indices, and preoperative BCVA had a better performance in predicting postoperative VA, with the lowest MAE (0.1250 and 0.1194LogMAR) and RMSE (0.2284 and 0.2362LogMAR), and the highest precision (90.7% and 91.7%), sensitivity (93.4% and 93.8%), accuracy (88% and 89%), F1 (92% and 92.7%) and AUCs (0.856 and 0.854) in the validation and test datasets, respectively.

Conclusion: The model had a good performance in predicting postoperative VA, when the input information contained preoperative OCT scans, macular morphological feature indices, and preoperative BCVA. The preoperative BCVA and macular OCT indices were of great significance in predicting postoperative VA in patients with age-related cataracts.

Keywords: cataract surgery; deep learning; macula; optical coherence tomography; visual acuity.