Prediction of postoperative visual acuity after vitrectomy for macular hole using deep learning–based artificial intelligence

Abstract

To create a model for prediction of postoperative visual acuity (VA) after vitrectomy for macular hole (MH) treatment using preoperative optical coherence tomography (OCT) images, using deep learning (DL)–based artificial intelligence. This was a retrospective single-center study. We evaluated 259 eyes that underwent vitrectomy for MHs. We divided the eyes into four groups, based on their 6-month postoperative Snellen VA values: (A)\u2009≥\u200920/20; (B) 20/25–20/32; (C) 20/32–20/63; and (D)\u2009≤\u200920/100. Training data were randomly selected, comprising 20 eyes in each group. Test data were also randomly selected, comprising 52 total eyes in the same proportions as those of each group in the total database. Preoperative OCT images with corresponding postoperative VA values were used to train the original DL network. The final prediction of postoperative VA was subjected to regression analysis based on inferences made with DL network output. We created a model for predicting postoperative VA from preoperative VA, MH size, and age using multivariate linear regression. Precision values were determined, and correlation coefficients between predicted and actual postoperative VA values were calculated in two models. The DL and multivariate models had precision values of 46% and 40%, respectively. The predicted postoperative VA values on the basis of DL and on preoperative VA and MH size were correlated with actual postoperative VA at 6 months postoperatively (P\u2009<\u2009.0001 and P\u2009<\u2009.0001, r\u2009=\u2009.62 and r\u2009=\u2009.55, respectively). Postoperative VA after MH treatment could be predicted via DL using preoperative OCT images with greater accuracy than multivariate linear regression using preoperative VA, MH size, and age.