Retinal structural changes after cessation of pentosan polysulfate sodium.

PURPOSE: To quantify baseline and longitudinal structural changes post-cessation in pentosan polysulfate sodium (PPS) retinopathy patients. METHODS: This is a retrospective cohort study. Retinal thickness and volume of choroidal and hyperreflective retinal pigment epithelium (RPE) excrescences were manually segmented from optical coherence tomography (OCT) volume scans. Baseline measurements were compared against age-matched controls. Longitudinal measurements were performed on patients with follow-up data. RESULTS: Twenty-four eyes of 13 patients were included. At baseline, the mean total retinal thickness was lower in the PPS retinopathy cohort than in age and sex-matched controls (269.1 µm vs. 290.2 µm, p = 0.006).The median (range) of follow-up was 18.6 (4.1 to 34.7) months, with the mean last follow-up of 35.2 months after cessation. During the follow-up period, the thickness of the retina decreased significantly by 11.3 µm (CI: 16.8, 5.8) (p<0.001), with an annual mean decrease of 6.70 µm. However, the mean hyperreflective RPE excrescence volume did not change significantly (p = 0.140) over the follow-up period. CONCLUSIONS: Following PPS discontinuation, although RPE excrescence volumes do not change significantly in volume, there continues to be a progressive long-term thinning of the retina which continues at a rate greater than that associated with normal aging. Consequently, long-term follow-up is suggested to monitor patients with PPS maculopathy.

Evaluation of Retinal Arterial Occlusion and its Visual and Systemic Prognosis after Hyperbaric Oxygen Therapy.

PURPOSE: To evaluate the systemic and ocular outcomes of patients with branch retinal artery occlusion (BRAO) and central retinal artery occlusion (CRAO) after hyperbaric oxygen therapy (HBOT). METHODS: This is a single-institution study of 75 subjects diagnosed with BRAO (28, 37.3%) and CRAO (47, 62.7%) who visited the emergency department or stroke clinic. Twenty-seven (36%) subjects received HBOT on initial presentation (BRAO-14.3%, CRAO-48.9%). The primary outcome was the best corrective visual acuity (BCVA) change in non-HBOT and HBOT subjects. Secondary outcomes included subsequent development of an acute cerebrovascular accident (CVA)/stroke or neovascular glaucoma (NVG). RESULTS: Overall BCVA did not change from the initial presentation to the final timepoint (logMAR 1.5) in either the conservative management or HBOT cohorts for either BRAO subjects (non-HBOT-logMAR 0.4 vs. 0.6, p=0.658; HBOT-logMAR 0.1 vs. 0.4, p=0.207) or CRAO subjects (non-HBOT-logMAR 2.1 vs. 2.2, p=0.755; HBOT-logMAR 2.1 vs. 2.0, p=0.631). Seven (9.3%) subjects developed CVA (BRAO: non-HBOT-4.2% and HBOT-25.0%, p=0.207; CRAO: non-HBOT-16.7% and HBOT-4.3%, p=0.348) and five subjects (6.7%) developed NVG (BRAO: non-HBOT-4.2% and HBOT-0%, p=1.00; CRAO: non-HBOT-16.7% and HBOT-0%, p=0.109). CONCLUSIONS: Our findings suggest that HBOT does not significantly improve BCVA or mitigate the subsequent development of stroke and NVG in patients with RAOs.

Barriers to Implementation of Teleretinal Diabetic Retinopathy Screening Programs Across the University of California.

Aim: To describe barriers to implementation of diabetic retinopathy (DR) teleretinal screening programs and artificial intelligence (AI) integration at the University of California (UC). Methods: Institutional representatives from UC Los Angeles, San Diego, San Francisco, Irvine, and Davis were surveyed for the year of their program's initiation, active status at the time of survey (December 2021), number of primary care clinics involved, screening image quality, types of eye providers, image interpretation turnaround time, and billing codes used. Representatives were asked to rate perceptions toward barriers to teleretinal DR screening and AI implementation using a 5-point Likert scale. Results: Four UC campuses had active DR teleretinal screening programs at the time of survey and screened between 246 and 2,123 patients at 1-6 clinics per campus. Sites reported variation between poor-quality photos (<5% to 15%) and average image interpretation time (1-5 days). Patient education, resource availability, and infrastructural support were identified as barriers to DR teleretinal screening. Cost and integration into existing technology infrastructures were identified as barriers to AI integration in DR screening. Conclusions: Despite the potential to increase access to care, there remain several barriers to widespread implementation of DR teleretinal screening. More research is needed to develop best practices to overcome these barriers.

Artificial Intelligence for Retinopathy of Prematurity: Validation of a Vascular Severity Scale against International Expert Diagnosis.

PURPOSE: To validate a vascular severity score as an appropriate output for artificial intelligence (AI) Software as a Medical Device (SaMD) for retinopathy of prematurity (ROP) through comparison with ordinal disease severity labels for stage and plus disease assigned by the International Classification of Retinopathy of Prematurity, Third Edition (ICROP3), committee. DESIGN: Validation study of an AI-based ROP vascular severity score. PARTICIPANTS: A total of 34 ROP experts from the ICROP3 committee. METHODS: Two separate datasets of 30 fundus photographs each for stage (0-5) and plus disease (plus, preplus, neither) were labeled by members of the ICROP3 committee using an open-source platform. Averaging these results produced a continuous label for plus (1-9) and stage (1-3) for each image. Experts were also asked to compare each image to each other in terms of relative severity for plus disease. Each image was also labeled with a vascular severity score from the Imaging and Informatics in ROP deep learning system, which was compared with each grader's diagnostic labels for correlation, as well as the ophthalmoscopic diagnosis of stage. MAIN OUTCOME MEASURES: Weighted kappa and Pearson correlation coefficients (CCs) were calculated between each pair of grader classification labels for stage and plus disease. The Elo algorithm was also used to convert pairwise comparisons for each expert into an ordered set of images from least to most severe. RESULTS: The mean weighted kappa and CC for all interobserver pairs for plus disease image comparison were 0.67 and 0.88, respectively. The vascular severity score was found to be highly correlated with both the average plus disease classification (CC = 0.90, P < 0.001) and the ophthalmoscopic diagnosis of stage (P < 0.001 by analysis of variance) among all experts. CONCLUSIONS: The ROP vascular severity score correlates well with the International Classification of Retinopathy of Prematurity committee member's labels for plus disease and stage, which had significant intergrader variability. Generation of a consensus for a validated scoring system for ROP SaMD can facilitate global innovation and regulatory authorization of these technologies.

A comparative analysis of system features used in the TREC-COVID information retrieval challenge.

The COVID-19 pandemic has resulted in a rapidly growing quantity of scientific publications from journal articles, preprints, and other sources. The TREC-COVID Challenge was created to evaluate information retrieval (IR) methods and systems for this quickly expanding corpus. Using the COVID-19 Open Research Dataset (CORD-19), several dozen research teams participated in over 5 rounds of the TREC-COVID Challenge. While previous work has compared IR techniques used on other test collections, there are no studies that have analyzed the methods used by participants in the TREC-COVID Challenge. We manually reviewed team run reports from Rounds 2 and 5, extracted features from the documented methodologies, and used a univariate and multivariate regression-based analysis to identify features associated with higher retrieval performance. We observed that fine-tuning datasets with relevance judgments, MS-MARCO, and CORD-19 document vectors was associated with improved performance in Round 2 but not in Round 5. Though the relatively decreased heterogeneity of runs in Round 5 may explain the lack of significance in that round, fine-tuning has been found to improve search performance in previous challenge evaluations by improving a system's ability to map relevant queries and phrases to documents. Furthermore, term expansion was associated with improvement in system performance, and the use of the narrative field in the TREC-COVID topics was associated with decreased system performance in both rounds. These findings emphasize the need for clear queries in search. While our study has some limitations in its generalizability and scope of techniques analyzed, we identified some IR techniques that may be useful in building search systems for COVID-19 using the TREC-COVID test collections.

Looking beyond blurred margins.

A 60-year-old man presented to an outside ophthalmology clinic with 1 month of progressive vision loss in the right eye (OD). Right optic disc edema was noted. Brain and orbit magnetic resonance imaging revealed right optic nerve and left occipital lobe enhancement. He was seen initially by neurology and neurosurgery and subsequently referred to neuro-ophthalmology for consideration of optic nerve biopsy. He was seen 3 months after his initial symptom onset where vision was light perception OD and a relative afferent pupillary defect with optic nerve edema. OS was unremarkable. A lumbar puncture with flow cytometry was negative for multiple sclerosis and lymphoma. At his oculoplastic evaluation for optic nerve biopsy, his vision was noted to be no light perception OD. Optic nerve biopsy demonstrated non-caseating granulomatous inflammation consistent with neurosarcoidosis. The patient was started on high-dose oral steroids with improvement of disc edema, as well as significant improvement in optic nerve and intracranial parenchymal enhancement, although his vision never improved.

Development of a Semi-automated Computer-based Tool for the Quantification of Vascular Tortuosity in the Murine Retina.

Purpose: The murine oxygen-induced retinopathy (OIR) model is one of the most widely used animal models of ischemic retinopathy, mimicking hallmark pathophysiology of initial vaso-obliteration (VO) resulting in ischemia that drives neovascularization (NV). In addition to NV and VO, human ischemic retinopathies, including retinopathy of prematurity (ROP), are characterized by increased vascular tortuosity. Vascular tortuosity is an indicator of disease severity, need to treat, and treatment response in ROP. Current literature investigating novel therapeutics in the OIR model often report their effects on NV and VO, and measurements of vascular tortuosity are less commonly performed. No standardized quantification of vascular tortuosity exists to date despite this metric's relevance to human disease. This proof-of-concept study aimed to apply a previously published semi-automated computer-based image analysis approach (iROP-Assist) to develop a new tool to quantify vascular tortuosity in mouse models. Design: Experimental study. Subjects: C57BL/6J mice subjected to the OIR model. Methods: In a pilot study, vasculature was manually segmented on flat-mount images of OIR and normoxic (NOX) mice retinas and segmentations were analyzed with iROP-Assist to quantify vascular tortuosity metrics. In a large cohort of age-matched (postnatal day 12 [P12], P17, P25) NOX and OIR mice retinas, NV, VO, and vascular tortuosity were quantified and compared. In a third experiment, vascular tortuosity in OIR mice retinas was quantified on P17 following intravitreal injection with anti-VEGF (aflibercept) or Immunoglobulin G isotype control on P12. Main Outcome Measures: Vascular tortuosity. Results: Cumulative tortuosity index was the best metric produced by iROP-Assist for discriminating between OIR mice and NOX controls. Increased vascular tortuosity correlated with disease activity in OIR. Treatment of OIR mice with aflibercept rescued vascular tortuosity. Conclusions: Vascular tortuosity is a quantifiable feature of the OIR model that correlates with disease severity and may be quickly and accurately quantified using the iROP-Assist algorithm. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Variations in Electronic Health Record-Based Definitions of Diabetic Retinopathy Cohorts: A Literature Review and Quantitative Analysis.

Purpose: Use of the electronic health record (EHR) has motivated the need for data standardization. A gap in knowledge exists regarding variations in existing terminologies for defining diabetic retinopathy (DR) cohorts. This study aimed to review the literature and analyze variations regarding codified definitions of DR. Design: Literature review and quantitative analysis. Subjects: Published manuscripts. Methods: Four graders reviewed PubMed and Google Scholar for peer-reviewed studies. Studies were included if they used codified definitions of DR (e.g., billing codes). Data elements such as author names, publication year, purpose, data set type, and DR definitions were manually extracted. Each study was reviewed by ≥ 2 authors to validate inclusion eligibility. Quantitative analyses of the codified definitions were then performed to characterize the variation between DR cohort definitions. Main Outcome Measures: Number of studies included and numeric counts of billing codes used to define codified cohorts. Results: In total, 43 studies met the inclusion criteria. Half of the included studies used datasets based on structured EHR data (i.e., data registries, institutional EHR review), and half used claims data. All but 1 of the studies used billing codes such as the International Classification of Diseases 9th or 10th edition (ICD-9 or ICD-10), either alone or in addition to another terminology for defining disease. Of the 27 included studies that used ICD-9 and the 20 studies that used ICD-10 codes, the most common codes used pertained to the full spectrum of DR severity. Diabetic retinopathy complications (e.g., vitreous hemorrhage) were also used to define some DR cohorts. Conclusions: Substantial variations exist among codified definitions for DR cohorts within retrospective studies. Variable definitions may limit generalizability and reproducibility of retrospective studies. More work is needed to standardize disease cohorts. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Applications of Deep Learning: Automated Assessment of Vascular Tortuosity in Mouse Models of Oxygen-Induced Retinopathy.

Objective: To develop a generative adversarial network (GAN) to segment major blood vessels from retinal flat-mount images from oxygen-induced retinopathy (OIR) and demonstrate the utility of these GAN-generated vessel segmentations in quantifying vascular tortuosity. Design: Development and validation of GAN. Subjects: Three datasets containing 1084, 50, and 20 flat-mount mice retina images with various stains used and ages at sacrifice acquired from previously published manuscripts. Methods: Four graders manually segmented major blood vessels from flat-mount images of retinas from OIR mice. Pix2Pix, a high-resolution GAN, was trained on 984 pairs of raw flat-mount images and manual vessel segmentations and then tested on 100 and 50 image pairs from a held-out and external test set, respectively. GAN-generated and manual vessel segmentations were then used as an input into a previously published algorithm (iROP-Assist) to generate a vascular cumulative tortuosity index (CTI) for 20 image pairs containing mouse eyes treated with aflibercept versus control. Main Outcome Measures: Mean dice coefficients were used to compare segmentation accuracy between the GAN-generated and manually annotated segmentation maps. For the image pairs treated with aflibercept versus control, mean CTIs were also calculated for both GAN-generated and manual vessel maps. Statistical significance was evaluated using Wilcoxon signed-rank tests (P ≤ 0.05 threshold for significance). Results: The dice coefficient for the GAN-generated versus manual vessel segmentations was 0.75 ± 0.27 and 0.77 ± 0.17 for the held-out test set and external test set, respectively. The mean CTI generated from the GAN-generated and manual vessel segmentations was 1.12 ± 0.07 versus 1.03 ± 0.02 (P = 0.003) and 1.06 ± 0.04 versus 1.01 ± 0.01 (P < 0.001), respectively, for eyes treated with aflibercept versus control, demonstrating that vascular tortuosity was rescued by aflibercept when quantified by GAN-generated and manual vessel segmentations. Conclusions: GANs can be used to accurately generate vessel map segmentations from flat-mount images. These vessel maps may be used to evaluate novel metrics of vascular tortuosity in OIR, such as CTI, and have the potential to accelerate research in treatments for ischemic retinopathies. Financial Disclosures: The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Usability and Clinician Acceptance of a Deep Learning-Based Clinical Decision Support Tool for Predicting Glaucomatous Visual Field Progression.

PRCIS: We updated a clinical decision support tool integrating predicted visual field (VF) metrics from an artificial intelligence model and assessed clinician perceptions of the predicted VF metric in this usability study. PURPOSE: To evaluate clinician perceptions of a prototyped clinical decision support (CDS) tool that integrates visual field (VF) metric predictions from artificial intelligence (AI) models. METHODS: Ten ophthalmologists and optometrists from the University of California San Diego participated in 6 cases from 6 patients, consisting of 11 eyes, uploaded to a CDS tool ("GLANCE", designed to help clinicians "at a glance"). For each case, clinicians answered questions about management recommendations and attitudes towards GLANCE, particularly regarding the utility and trustworthiness of the AI-predicted VF metrics and willingness to decrease VF testing frequency. MAIN OUTCOMES AND MEASURES: Mean counts of management recommendations and mean Likert scale scores were calculated to assess overall management trends and attitudes towards the CDS tool for each case. In addition, system usability scale scores were calculated. RESULTS: The mean Likert scores for trust in and utility of the predicted VF metric and clinician willingness to decrease VF testing frequency were 3.27, 3.42, and 2.64, respectively (1=strongly disagree, 5=strongly agree). When stratified by glaucoma severity, all mean Likert scores decreased as severity increased. The system usability scale score across all responders was 66.1±16.0 (43rd percentile). CONCLUSIONS: A CDS tool can be designed to present AI model outputs in a useful, trustworthy manner that clinicians are generally willing to integrate into their clinical decision-making. Future work is needed to understand how to best develop explainable and trustworthy CDS tools integrating AI before clinical deployment.

Applications of natural language processing in ophthalmology: present and future.

Advances in technology, including novel ophthalmic imaging devices and adoption of the electronic health record (EHR), have resulted in significantly increased data available for both clinical use and research in ophthalmology. While artificial intelligence (AI) algorithms have the potential to utilize these data to transform clinical care, current applications of AI in ophthalmology have focused mostly on image-based deep learning. Unstructured free-text in the EHR represents a tremendous amount of underutilized data in big data analyses and predictive AI. Natural language processing (NLP) is a type of AI involved in processing human language that can be used to develop automated algorithms using these vast quantities of available text data. The purpose of this review was to introduce ophthalmologists to NLP by (1) reviewing current applications of NLP in ophthalmology and (2) exploring potential applications of NLP. We reviewed current literature published in Pubmed and Google Scholar for articles related to NLP and ophthalmology, and used ancestor search to expand our references. Overall, we found 19 published studies of NLP in ophthalmology. The majority of these publications (16) focused on extracting specific text such as visual acuity from free-text notes for the purposes of quantitative analysis. Other applications included: domain embedding, predictive modeling, and topic modeling. Future ophthalmic applications of NLP may also focus on developing search engines for data within free-text notes, cleaning notes, automated question-answering, and translating ophthalmology notes for other specialties or for patients, especially with a growing interest in open notes. As medicine becomes more data-oriented, NLP offers increasing opportunities to augment our ability to harness free-text data and drive innovations in healthcare delivery and treatment of ophthalmic conditions.

Development of an Open-Source Annotated Glaucoma Medication Dataset From Clinical Notes in the Electronic Health Record.

Purpose: To describe the methods involved in processing and characteristics of an open dataset of annotated clinical notes from the electronic health record (EHR) annotated for glaucoma medications. Methods: In this study, 480 clinical notes from office visits, medical record numbers (MRNs), visit identification numbers, provider names, and billing codes were extracted for 480 patients seen for glaucoma by a comprehensive or glaucoma ophthalmologist from January 1, 2019, to August 31, 2020. MRNs and all visit data were de-identified using a hash function with salt from the deidentifyr package. All progress notes were annotated for glaucoma medication name, route, frequency, dosage, and drug use using an open-source annotation tool, Doccano. Annotations were saved separately. All protected health information (PHI) in progress notes and annotated files were de-identified using the published de-identifying algorithm Philter. All progress notes and annotations were manually validated by two ophthalmologists to ensure complete de-identification. Results: The final dataset contained 5520 annotated sentences, including those with and without medications, for 480 clinical notes. Manual validation revealed 10 instances of remaining PHI which were manually corrected. Conclusions: Annotated free-text clinical notes can be de-identified for upload as an open dataset. As data availability increases with the adoption of EHRs, free-text open datasets will become increasingly valuable for "big data" research and artificial intelligence development. This dataset is published online and publicly available at https://github.com/jche253/Glaucoma_Med_Dataset. Translational Relevance: This open access medication dataset may be a source of raw data for future research involving big data and artificial intelligence research using free-text.

Synthetic Medical Images for Robust, Privacy-Preserving Training of Artificial Intelligence: Application to Retinopathy of Prematurity Diagnosis.

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.

Electronic health record note review in an outpatient specialty clinic: who is looking?

Note entry and review in electronic health records (EHRs) are time-consuming. While some clinics have adopted team-based models of note entry, how these models have impacted note review is unknown in outpatient specialty clinics such as ophthalmology. We hypothesized that ophthalmologists and ancillary staff review very few notes. Using audit log data from 9775 follow-up office visits in an academic ophthalmology clinic, we found ophthalmologists reviewed a median of 1 note per visit (2.6 ± 5.3% of available notes), while ancillary staff reviewed a median of 2 notes per visit (4.1 ± 6.2% of available notes). While prior ophthalmic office visit notes were the most frequently reviewed note type, ophthalmologists and staff reviewed no such notes in 51% and 31% of visits, respectively. These results highlight the collaborative nature of note review and raise concerns about how cumbersome EHR designs affect efficient note review and the utility of prior notes in ophthalmic clinical care.

Extraction of Active Medications and Adherence Using Natural Language Processing for Glaucoma Patients.

Accuracy of medication data in electronic health records (EHRs) is crucial for patient care and research, but many studies have shown that medication lists frequently contain errors. In contrast, physicians often pay more attention to the clinical notes and record medication information in them. The medication information in notes may be used for medication reconciliation to improve the medication lists' accuracy. However, accurately extracting patient's current medications from free-text narratives is challenging. In this study, we first explored the discrepancies between medication documentation in medication lists and progress notes for glaucoma patients by manually reviewing patients' charts. Next, we developed and validated a named entity recognition model to identify current medication and adherence from progress notes. Lastly, a prototype tool for medication reconciliation using the developed model was demonstrated. In the future, the model has the potential to be incorporated into the EHR system to help with realtime medication reconciliation.

Early Outcomes in an Emerging Facial Nerve Center: The Oregon Health and Science University (OHSU) Experience.

OBJECTIVES: Nerve transfer (NT) and free gracilis muscle transfer (FGMT) are procedures for reanimation of the paralyzed face. Assessing the surgical outcomes of these procedures is imperative when evaluating the effectiveness of these interventions, especially when establishing a new center focused on the treatment of patients with facial paralysis. We desired to discuss the factors to consider when implementing a facial nerve center and the means by which the specialist can assess and analyze outcomes. METHODS: Patients with facial palsy secondary to multiple etiologies, including cerebellopontine angle tumors, head and neck carcinoma, and trauma, who underwent NT or FGMT between 2014 and 2019 were included. Primary outcomes were facial symmetry and smile excursion, calculated using FACE-gram and Emotrics software. Subjective quality of life outcomes, including the Facial Clinimetric Evaluation (FaCE) Scale and Synkinesis Assessment Questionnaire (SAQ), were also assessed. RESULTS: 14/22 NT and 6/6 FGMT patients met inclusion criteria having both pre-and postoperative photo documentation. NT increased oral commissure excursion from 0.4 mm (SD 5.3) to 2.9 mm (SD 6.8) (P = 0.05), and improved symmetry of excursion (P < 0.001) and angle (P < 0.001). FGMT increased oral commissure excursion from -1.4 mm (SD 3.9) to 2.1 mm (SD 3.7), (P = 0.02), and improved symmetry of excursion (P < 0.001). FaCE scores improved in NT patients postoperatively (P < 0.001). CONCLUSIONS: Measuring outcomes, critical analyses, and a multidisciplinary approach are necessary components when building a facial nerve center. At our emerging facial nerve center, we found NT and FGMT procedures improved smile excursion and symmetry, and improved QOL following NT in patients with facial palsy secondary to multiple etiologies.

Deepfakes in Ophthalmology: Applications and Realism of Synthetic Retinal Images from Generative Adversarial Networks.

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.

Single-Examination Risk Prediction of Severe Retinopathy of Prematurity.

BACKGROUND AND OBJECTIVES: Retinopathy of prematurity (ROP) is a leading cause of childhood blindness. Screening and treatment reduces this risk, but requires multiple examinations of infants, most of whom will not develop severe disease. Previous work has suggested that artificial intelligence may be able to detect incident severe disease (treatment-requiring retinopathy of prematurity [TR-ROP]) before clinical diagnosis. We aimed to build a risk model that combined artificial intelligence with clinical demographics to reduce the number of examinations without missing cases of TR-ROP. METHODS: Infants undergoing routine ROP screening examinations (1579 total eyes, 190 with TR-ROP) were recruited from 8 North American study centers. A vascular severity score (VSS) was derived from retinal fundus images obtained at 32 to 33 weeks' postmenstrual age. Seven ElasticNet logistic regression models were trained on all combinations of birth weight, gestational age, and VSS. The area under the precision-recall curve was used to identify the highest-performing model. RESULTS: The gestational age + VSS model had the highest performance (mean ± SD area under the precision-recall curve: 0.35 ± 0.11). On 2 different test data sets (n = 444 and n = 132), sensitivity was 100% (positive predictive value: 28.1% and 22.6%) and specificity was 48.9% and 80.8% (negative predictive value: 100.0%). CONCLUSIONS: Using a single examination, this model identified all infants who developed TR-ROP, on average, >1 month before diagnosis with moderate to high specificity. This approach could lead to earlier identification of incident severe ROP, reducing late diagnosis and treatment while simultaneously reducing the number of ROP examinations and unnecessary physiologic stress for low-risk infants.

Quantification of Early Neonatal Oxygen Exposure as a Risk Factor for Retinopathy of Prematurity Requiring Treatment.

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 (FiO2) were extracted manually from the EHR until 31 weeks postmenstrual age (PMA). Cumulative minimum, maximum, and mean oxygen saturation and FiO2 were calculated on a weekly basis. Random forest models were trained with 5-fold cross-validation using gestational age (GA) and cumulative minimum FiO2 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 FiO2 (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.