Search

Purpose: Retinopathy of prematurity (ROP) is one of the leading causes of blindness in children. Although the role of oxygen in the pathophysiology of ROP is well established, a precise understanding of the dynamic relationship between oxygen exposure ROP incidence and severity is lacking. The purpose of this study was to evaluate the correlation between time-dependent oxygen variables and the onset of ROP., Design: Retrospective cohort study., Participants: Two hundred thirty infants who were born at a single academic center and met the inclusion criteria were included. Infants are mainly born between January 2011 and October 2022., Methods: Patient data were extracted from electronic health records (EHRs), with sufficient time-dependent oxygen data. Clinical outcomes for ROP were recorded as none/mild or moderate/severe (defined as type II or worse). Mixed-effects linear models were used to compare the 2 groups in terms of dynamic oxygen variables, such as daily average and the coefficient of variation (COV) fraction of inspired oxygen (FiO 2 ). Support vector machine (SVM) and long-short-term memory (LSTM)-based multimodal models were trained with fivefold cross-validation to predict which infants would develop moderate/severe ROP. Gestational age (GA), birth weight, and time-dependent oxygen variables were used to develop predictive models., Main Outcome Measures: Model cross-validation performance was evaluated by computing the mean area under the receiver operating characteristic (AUROC) curve, precision, recall, and F1 score., Results: We found that both daily average and COV of FiO 2 were associated with more severe ROP (adjusted P  < 0.001). With fivefold cross-validation, the multimodal LSTM models had higher performance than the best static models (SVM using GA and 3 average FiO 2 features) and SVM models trained on GA alone (mean AUROC = 0.89 ± 0.04 vs. 0.86 ± 0.05 vs. 0.83 ± 0.04)., Conclusions: The development of severe ROP might not only be influenced by oxygen exposure but also by its fluctuation, which provides direction for future study of pathophysiological factors associated with severe ROP development. Additionally, we demonstrated that multimodal neural networks can be a method to extract useful information from time-series data, which may be a valuable methodology for the investigation of other diseases using EHR data., Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article., (© 2023 Published by Elsevier Inc. on behalf of the American Academy of Ophthalmology.)

The rapid progress of large language models (LLMs) driving generative artificial intelligence applications heralds the potential of opportunities in health care. We conducted a review up to April 2023 on Google Scholar, Embase, MEDLINE, and Scopus using the following terms: "large language models," "generative artificial intelligence," "ophthalmology," "ChatGPT," and "eye," based on relevance to this review. From a clinical viewpoint specific to ophthalmologists, we explore from the different stakeholders' perspectives-including patients, physicians, and policymakers-the potential LLM applications in education, research, and clinical domains specific to ophthalmology. We also highlight the foreseeable challenges of LLM implementation into clinical practice, including the concerns of accuracy, interpretability, perpetuating bias, and data security. As LLMs continue to mature, it is essential for stakeholders to jointly establish standards for best practices to safeguard patient safety., Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article., (© 2023 by the American Academy of Ophthalmology.)

Purpose: To evaluate the performance of a deep learning (DL) algorithm for retinopathy of prematurity (ROP) screening in Nepal and Mongolia., Design: Retrospective analysis of prospectively collected clinical data., Participants: Clinical information and fundus images were obtained from infants in 2 ROP screening programs in Nepal and Mongolia., Methods: Fundus images were obtained using the Forus 3nethra neo (Forus Health) in Nepal and the RetCam Portable (Natus Medical, Inc.) in Mongolia. The overall severity of ROP was determined from the medical record using the International Classification of ROP (ICROP). The presence of plus disease was determined independently in each image using a reference standard diagnosis. The Imaging and Informatics for ROP (i-ROP) DL algorithm was trained on images from the RetCam to classify plus disease and to assign a vascular severity score (VSS) from 1 through 9., Main Outcome Measures: Area under the receiver operating characteristic curve and area under the precision-recall curve for the presence of plus disease or type 1 ROP and association between VSS and ICROP disease category., Results: The prevalence of type 1 ROP was found to be higher in Mongolia (14.0%) than in Nepal (2.2%; P  < 0.001) in these data sets. In Mongolia (RetCam images), the area under the receiver operating characteristic curve for examination-level plus disease detection was 0.968, and the area under the precision-recall curve was 0.823. In Nepal (Forus images), these values were 0.999 and 0.993, respectively. The ROP VSS was associated with ICROP classification in both datasets ( P < 0.001). At the population level, the median VSS was found to be higher in Mongolia (2.7; interquartile range [IQR], 1.3-5.4]) as compared with Nepal (1.9; IQR, 1.2-3.4; P < 0.001)., Conclusions: These data provide preliminary evidence of the effectiveness of the i-ROP DL algorithm for ROP screening in neonatal populations in Nepal and Mongolia using multiple camera systems and are useful for consideration in future clinical implementation of artificial intelligence-based ROP screening in low- and middle-income countries., (© 2022 by the American Academy of Ophthalmology.)

Purpose: Developing robust artificial intelligence (AI) models for medical image analysis requires large quantities of diverse, well-chosen data that can prove challenging to collect because of privacy concerns, disease rarity, or diagnostic label quality. Collecting image-based datasets for retinopathy of prematurity (ROP), a potentially blinding disease, suffers from these challenges. Progressively growing generative adversarial networks (PGANs) may help, because they can synthesize highly realistic images that may increase both the size and diversity of medical datasets., Design: Diagnostic validation study of convolutional neural networks (CNNs) for plus disease detection, a component of severe ROP, using synthetic data., Participants: Five thousand eight hundred forty-two retinal fundus images (RFIs) collected from 963 preterm infants., Methods: Retinal vessel maps (RVMs) were segmented from RFIs. PGANs were trained to synthesize RVMs with normal, pre-plus, or plus disease vasculature. Convolutional neural networks were trained, using real or synthetic RVMs, to detect plus disease from 2 real RVM test datasets., Main Outcome Measures: Features of real and synthetic RVMs were evaluated using uniform manifold approximation and projection (UMAP). Similarities were evaluated at the dataset and feature level using Fréchet inception distance and Euclidean distance, respectively. CNN performance was assessed via area under the receiver operating characteristic curve (AUC); AUCs were compared via bootstrapping and Delong's test for correlated receiver operating characteristic curves. Confusion matrices were compared using McNemar's chi-square test and Cohen's κ value., Results: The CNN trained on synthetic RVMs showed a significantly higher AUC (0.971; P = 0.006 and P  = 0.004) and classified plus disease more similarly to a set of 8 international experts (κ = 0.922) than the CNN trained on real RVMs (AUC = 0.934; κ = 0.701). Real and synthetic RVMs overlapped, by plus disease diagnosis, on the UMAP manifold, showing that synthetic images spanned the disease severity spectrum. Fréchet inception distance and Euclidean distances suggested that real and synthetic RVMs were more dissimilar to one another than real RVMs were to one another, further suggesting that synthetic RVMs were distinct from the training data with respect to privacy considerations., Conclusions: Synthetic datasets may be useful for training robust medical AI models. Furthermore, PGANs may be able to synthesize realistic data for use without protected health information concerns., (© 2022 by the American Academy of Ophthalmology.)

Purpose: To compare the efficacy and efficiency of training neural networks for medical image classification using comparison labels indicating relative disease severity versus diagnostic class labels from a retinopathy of prematurity (ROP) image dataset., Design: Evaluation of diagnostic test or technology., Participants: Deep learning neural networks trained on expert-labeled wide-angle retinal images obtained from patients undergoing diagnostic ROP examinations obtained as part of the Imaging and Informatics in ROP (i-ROP) cohort study., Methods: Neural networks were trained with either class or comparison labels indicating plus disease severity in ROP retinal fundus images from 2 datasets. After training and validation, all networks underwent evaluation using a separate test dataset in 1 of 2 binary classification tasks: normal versus abnormal or plus versus nonplus., Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) values were measured to assess network performance., Results: Given the same number of labels, neural networks learned more efficiently by comparison, generating significantly higher AUCs in both classification tasks across both datasets. Similarly, given the same number of images, comparison learning developed networks with significantly higher AUCs across both classification tasks in 1 of 2 datasets. The difference in efficiency and accuracy between models trained on either label type decreased as the size of the training set increased., Conclusions: Comparison labels individually are more informative and more abundant per sample than class labels. These findings indicate a potential means of overcoming the common obstacle of data variability and scarcity when training neural networks for medical image classification tasks., (© 2022 by the American Academy of Ophthalmology.)

Purpose: Generative adversarial networks (GANs) are deep learning (DL) models that can create and modify realistic-appearing synthetic images, or deepfakes, from real images. The purpose of our study was to evaluate the ability of experts to discern synthesized retinal fundus images from real fundus images and to review the current uses and limitations of GANs in ophthalmology., Design: Development and expert evaluation of a GAN and an informal review of the literature., Participants: A total of 4282 image pairs of fundus images and retinal vessel maps acquired from a multicenter ROP screening program., Methods: Pix2Pix HD, a high-resolution GAN, was first trained and validated on fundus and vessel map image pairs and subsequently used to generate 880 images from a held-out test set. Fifty synthetic images from this test set and 50 different real images were presented to 4 expert ROP ophthalmologists using a custom online system for evaluation of whether the images were real or synthetic. Literature was reviewed on PubMed and Google Scholars using combinations of the terms ophthalmology , GANs, generative adversarial networks, ophthalmology, images, deepfakes, and synthetic . Ancestor search was performed to broaden results., Main Outcome Measures: Expert ability to discern real versus synthetic images was evaluated using percent accuracy. Statistical significance was evaluated using a Fisher exact test, with P values ≤ 0.05 thresholded for significance., Results: The expert majority correctly identified 59% of images as being real or synthetic ( P  = 0.1). Experts 1 to 4 correctly identified 54%, 58%, 49%, and 61% of images ( P  = 0.505, 0.158, 1.000, and 0.043, respectively). These results suggest that the majority of experts could not discern between real and synthetic images. Additionally, we identified 20 implementations of GANs in the ophthalmology literature, with applications in a variety of imaging modalities and ophthalmic diseases., Conclusions: Generative adversarial networks can create synthetic fundus images that are indiscernible from real fundus images by expert ROP ophthalmologists. Synthetic images may improve dataset augmentation for DL, may be used in trainee education, and may have implications for patient privacy., (© 2021 Published by Elsevier Inc. on behalf of the American Academy of Ophthalmology.)

Purpose: Retinopathy of prematurity (ROP) is a leading cause of childhood blindness related to oxygen exposure in premature infants. Since oxygen monitoring protocols have reduced the incidence of treatment-requiring ROP (TR-ROP), it remains unclear whether oxygen exposure remains a relevant risk factor for incident TR-ROP and aggressive ROP (A-ROP), a severe, rapidly progressing form of ROP. The purpose of this proof-of-concept study was to use electronic health record (EHR) data to evaluate early oxygen exposure as a predictive variable for developing TR-ROP and A-ROP., Design: Retrospective cohort study., Participants: Two hundred forty-four infants screened for ROP at a single academic center., Methods: For each infant, oxygen saturations and fraction of inspired oxygen (FiO 2 ) were extracted manually from the EHR until 31 weeks postmenstrual age (PMA). Cumulative minimum, maximum, and mean oxygen saturation and FiO 2 were calculated on a weekly basis. Random forest models were trained with 5-fold cross-validation using gestational age (GA) and cumulative minimum FiO 2 at 30 weeks PMA to identify infants who developed TR-ROP. Secondary receiver operating characteristic (ROC) curve analysis of infants with or without A-ROP was performed without cross-validation because of small numbers., Main Outcome Measures: For each model, cross-validation performance for incident TR-ROP was assessed using area under the ROC curve (AUC) and area under the precision-recall curve (AUPRC) scores. For A-ROP, we calculated AUC and evaluated sensitivity and specificity at a high-sensitivity operating point., Results: Of the 244 infants included, 33 developed TR-ROP, of which 5 developed A-ROP. For incident TR-ROP, random forest models trained on GA plus cumulative minimum FiO 2 (AUC = 0.93 ± 0.06; AUPRC = 0.76 ± 0.08) were not significantly better than models trained on GA alone (AUC = 0.92 ± 0.06 [ P  = 0.59]; AUPRC = 0.74 ± 0.12 [ P  = 0.32]). Models using oxygen alone showed an AUC of 0.80 ± 0.09. ROC analysis for A-ROP found an AUC of 0.92 (95% confidence interval, 0.87-0.96)., Conclusions: Oxygen exposure can be extracted from the EHR and quantified as a risk factor for incident TR-ROP and A-ROP. Extracting quantifiable clinical features from the EHR may be useful for building risk models for multiple diseases and evaluating the complex relationships among oxygen exposure, ROP, and other sequelae of prematurity., (© 2021 by the American Academy of Ophthalmology.)