ABSTRACT
BACKGROUND: Optic neuritis (ON) is a complex clinical syndrome that has diverse etiologies and treatments based on its subtypes. Notably, ON associated with multiple sclerosis (MS ON) has a good prognosis for recovery irrespective of treatment, whereas ON associated with other conditions including neuromyelitis optica spectrum disorders or myelin oligodendrocyte glycoprotein antibody-associated disease is often associated with less favorable outcomes. Delay in treatment of these non-MS ON subtypes can lead to irreversible vision loss. It is important to distinguish MS ON from other ON subtypes early, to guide appropriate management. Yet, identifying ON and differentiating subtypes can be challenging as MRI and serological antibody test results are not always readily available in the acute setting. The purpose of this study is to develop a deep learning artificial intelligence (AI) algorithm to predict subtype based on fundus photographs, to aid the diagnostic evaluation of patients with suspected ON. METHODS: This was a retrospective study of patients with ON seen at our institution between 2007 and 2022. Fundus photographs (1,599) were retrospectively collected from a total of 321 patients classified into 2 groups: MS ON (262 patients; 1,114 photographs) and non-MS ON (59 patients; 485 photographs). The dataset was divided into training and holdout test sets with an 80%/20% ratio, using stratified sampling to ensure equal representation of MS ON and non-MS ON patients in both sets. Model hyperparameters were tuned using 5-fold cross-validation on the training dataset. The overall performance and generalizability of the model was subsequently evaluated on the holdout test set. RESULTS: The receiver operating characteristic (ROC) curve for the developed model, evaluated on the holdout test dataset, yielded an area under the ROC curve of 0.83 (95% confidence interval [CI], 0.72-0.92). The model attained an accuracy of 76.2% (95% CI, 68.4-83.1), a sensitivity of 74.2% (95% CI, 55.9-87.4) and a specificity of 76.9% (95% CI, 67.6-85.0) in classifying images as non-MS-related ON. CONCLUSION: This study provides preliminary evidence supporting a role for AI in differentiating non-MS ON subtypes from MS ON. Future work will aim to increase the size of the dataset and explore the role of combining clinical and paraclinical measures to refine deep learning models over time.
ABSTRACT
PURPOSE: To compare the sealability of femtosecond laser (FSL)-assisted corneal incisions (CIs) with that of triplanar manual (M)-CIs and to determine FSL wound parameters minimizing leakage. SETTING: Private practice. DESIGN: Phase IV, single-surgeon, retrospective cohort study. METHODS: One eye per patient was included. Two groups defined by the main wound (FSL-CI or M-CI) were compared for leakage, inferred by placement of a suture at the end of surgery. Leakage in FSL-CIs was analyzed as a function of customizable wound parameters: anterior plane depth (APD), posterior plane depth (PPD), anterior side-cut angle (ASCA), and posterior side-cut angle (PSCA). The risk of leakage of FSL-CIs with optimal and nonoptimal parameters was further compared with that of M-CIs. RESULTS: A total of 1100 eyes (757 [68.8%] FSL-CI; 343 [31.2%] M-CI) were included. Wound leakage occurred in 133 FSL-CI (17.6%) and 30 M-CI eyes (8.7%) (P < .001). FSL wound parameters associated with the lowest risk of leakage were 60% APD, 70% PPD, 120 degrees ASCA, and 70 degrees PSCA. FSL-CIs constructed with at least 3 optimal parameters (60% APD, 70% PPD, and 120 degrees ASCA) had a similar risk of leakage to M-CIs (odds ratio [OR], 1.1; 95% CI, 0.5-2.3). FSL-CIs with suboptimal parameters had twice the risk of leakage of M-CIs (OR, 2.0; 95% CI, 1.1-3.8). CONCLUSIONS: Overall, FSL-CIs leaked more than M-CIs. However, FSL-CIs with optimized wound profiles had an equivalent risk of leakage to M-CIs. Wound parameter customization is an asset of FSL technology that allows optimization of FSL-CI sealability.