Dataset Information

Predicting Post-Therapeutic Visual Acuity and OCT Images in Patients With Central Serous Chorioretinopathy by Artificial Intelligence.

ABSTRACT: To predict visual acuity (VA) and post-therapeutic optical coherence tomography (OCT) images 1, 3, and 6 months after laser treatment in patients with central serous chorioretinopathy (CSC) by artificial intelligence (AI). Real-world clinical and imaging data were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The data obtained from ZOC (416 eyes of 401 patients) were used as the training set; the data obtained from XEC (64 eyes of 60 patients) were used as the test set. Six different machine learning algorithms and a blending algorithm were used to predict VA, and a pix2pixHD method was adopted to predict post-therapeutic OCT images in patients after laser treatment. The data for VA predictions included clinical features obtained from electronic medical records (20 features) and measured features obtained from fundus fluorescein angiography, indocyanine green angiography, and OCT (145 features). The data for OCT predictions included 480 pairs of pre- and post-therapeutic OCT images. The VA and OCT images predicted by AI were compared with the ground truth. In the VA predictions of XEC dataset, the mean absolute errors (MAEs) were 0.074-0.098 logMAR (within four to five letters), and the root mean square errors were 0.096-0.127 logMAR (within five to seven letters) for the 1-, 3-, and 6-month predictions, respectively; in the post-therapeutic OCT predictions, only about 5.15% (5 of 97) of synthetic OCT images could be accurately identified as synthetic images. The MAEs of central macular thickness of synthetic OCT images were 30.15 ± 13.28 μm and 22.46 ± 9.71 μm for the 1- and 3-month predictions, respectively. This is the first study to apply AI to predict VA and post-therapeutic OCT of patients with CSC. This work establishes a reliable method of predicting prognosis 6 months in advance; the application of AI has the potential to help reduce patient anxiety and serve as a reference for ophthalmologists when choosing optimal laser treatments.

SUBMITTER: Xu F

PROVIDER: S-EPMC8650495 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PURPOSE:To assess parameters on optical coherence tomography (OCT), and their correlation with best-corrected visual acuity (BCVA) in patients with non-resolving central serous chorioretinopathy (CSC). METHODS:For 25 non-resolving CSC patients treated with photodynamic therapy (PDT), the thickness of retinal layers was assessed on the foveal spectral-domain (SD) OCT scan. Evaluated OCT parameters included the central retinal thickness (CRT), defined as the internal limiting membrane (ILM) to ellipsoid zone (EZ) distance, and the second band thickness (SBT), defined as the EZ to hyperreflective subretinal accumulation distance. Integrity of the external limiting membrane (ELM) and the EZ bands was also determined. These parameters, along with BCVA and CRT measured automatically by SD-OCT device software were obtained before PDT, after PDT, and at final visit. After Bonferroni correction, a p-value <0.007 was considered statistically significant. RESULTS:Twenty-five patients could be included at last visit before PDT and first visit after PDT. At final visit, 24 patients could be included, since 1 patients was lost to follow-up. Mean CRT was 112 ?m at last visit before PDT, 118 ?m at first visit after PDT (p = 0.030), and 127 ?m at final visit (p<0.001compared to baseline). Mean SBT was 74 ?m, 26 ?m (p<0.001 compared to baseline), and 21 ?m (p<0.001 compared to baseline), respectively. Mean BCVA in Early Treatment of Diabetic Retinopathy Study letters was 79 at baseline, 85 at first visit after PDT (p = 0.005 compared to baseline), and 87 at final visit (p = 0.001 compared to baseline). BCVA had an estimated correlation of ? = 0.103 (p = 0.114) with CRT, ? = -0.051 (p = 0.014) with SBT, ? = 0.615 (p = 0.600) with the integrity of the ELM, and ? = 4.917 with the integrity of the EZ (p = 0.001). CONCLUSIONS:In non-resolving CSC patients treated with half-dose PDT, the CRT increased at final visit in comparison to the last visit before PDT. The continuity of the EZ on SD-OCT was positively correlated with BCVA. We propose that the distance between ILM and EZ should be used as a reliable CRT measurement in non-resolving CSC patients treated with half-dose PDT.

Dataset Information

Predicting Post-Therapeutic Visual Acuity and OCT Images in Patients With Central Serous Chorioretinopathy by Artificial Intelligence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets