Panretinal handheld OCT angiography for pediatric retinal imaging.

Comprehensive visualization of retina morphology is essential in the diagnosis and management of retinal diseases in pediatric populations. Conventional imaging techniques often face challenges in effectively capturing the peripheral retina, primarily due to the limitations in current optical designs, which lack the necessary field of view to characterize the far periphery. To address this gap, our study introduces a novel ultra-widefield optical coherence tomography angiography (OCTA) system. This system, specifically tailored for pediatric applications, incorporates an ultrahigh-speed 800 kHz swept-source laser. The system's innovative design achieves a 140° field of view while maintaining excellent optical performance. Over the last 15 months, we have conducted 379 eye examinations on 96 babies using this system. It demonstrates marked efficacy in the diagnosis of retinopathy of prematurity, providing detailed and comprehensive peripheral retinal angiography. The capabilities of the ultra-widefield handheld OCTA system in enhancing the clarity and thoroughness of retina vascularization assessments have significantly improved the precision of diagnoses and the customization of treatment strategies. Our findings underscore the system's potential to advance pediatric ophthalmology and broaden the scope of retinal imaging.

Use of an artificial intelligence-generated vascular severity score improved plus disease diagnosis in retinopathy of prematurity.

OBJECTIVE: To evaluate whether providing clinicians with an artificial intelligence-based vascular severity score (AI-VSS) improves consistency in diagnosis of plus disease in retinopathy of prematurity (ROP). DESIGN: This is a multi-reader diagnostic accuracy imaging study. PARTICIPANTS: Eleven ROP experts (4 pediatric ophthalmologists, 7 retina specialists), 9 of which had been in practice for 10 or more years. METHODS: Retcam (Natus Medical Incorporated) fundus images were obtained from premature infants during routine ROP screening as part of the Imaging and Informatics in ROP study between January 2012 and July 2020. From all available exams, a subset of 150 eye exams from 110 infants were selected for grading. An AI-VSS was assigned to each set of images using the i-ROP DL system. The clinicians were asked to diagnose plus disease for each exam and assign an estimated VSS (range 1-9) at baseline, and then again one month later with AI-VSS assistance. A reference standard diagnosis (RSD) was assigned to each eye exam from the i-ROP study based on 3 masked expert labels and the ophthalmoscopic diagnosis. MAIN OUTCOME MEASURE: Mean linearly weighted kappa for plus disease diagnosis compared to the RSD. Area under the receiver operating characteristic and precision-recall curves (AUROC, AUPR) for 1-9 labels compared to RSD for plus disease. RESULTS: Expert agreement improved significantly from substantial (κ: 0.69 [0.59, 0.75]) to near perfect (κ: 0.81 [0.71, 0.86]) when AI-VSS was integrated. Additionally, there was a significant improvement in plus disease discrimination as measured by mean [95% confidence interval] AUROC (0.94 [0.92, 0.96] to 0.98 [0.96, 0.99], difference: 0.04 [0.01, 0.06]) and AUPR (0.86 [0.81, 0.90] to 0.95 [0.91, 0.97], difference: 0.09 [0.03, 0.14]). CONCLUSIONS: Providing ROP clinicians with an AI-based measurement of vascular severity in ROP was associated with both improved plus disease diagnosis and improved continuous severity labeling, as compared to a reference standard diagnosis for plus disease. If implemented in practice, AI-VSS could reduce inter-observer variability and standardize treatment for infants with ROP.

P-Score: A Reference-Image-Based Clinical Grading Scale for Vascular Change in Retinopathy of Prematurity.

PURPOSE: The International Classification of Retinopathy of Prematurity Third Edition (ICROP3) acknowledged that plus-like ROP vascular changes occur along a spectrum. Historically, clinician-experts demonstrate variable agreement for plus diagnosis. We developed a 9-photo reference-image set for grading plus-like changes and compared intergrader agreement of the set to standard grading with no-plus/pre-plus/plus. DESIGN: Retinal photographic grading and expert consensus opinion PARTICIPANTS: Development: 34 international ICROP3 committee members. VALIDATION: 30 ophthalmologists with ROP expertise (15 ICROP3 committee members, 15 non-ICROP3 members) METHODS: Nine ROP fundus images (P1 through P9) representing increasing degrees of zone I vascular tortuosity and dilation, based on ICROP3-committee's 34 members' gradings and consensus image review, were used to establish standard photographs for the "Plus (P) Score." Study participants graded 150 fundus photographs two ways, separated by a 1-week washout period: (1) no-plus/pre-plus/plus disease, (2) choosing the closest P-Score image. MAIN OUTCOME MEASURES: Intergrader agreement measured by intraclass correlation coefficient (ICC) RESULTS: Intergrader agreement was higher using P-Score (ICC 0.75, 95% CI 0.71-0.79) than no-plus/pre-plus/plus (ICC 0.67, 95% CI 0.62-0.72). Mean P-Scores for images whose mode gradings were no-plus, pre-plus, and plus, were 2.5 (SD 0.7), 4.8 (SD 0.8), and 7.4 (SD 0.8), respectively. CONCLUSIONS: Intergrader agreement of plus-like vascular change in ROP using the P-Score is high. We recommend incorporation of this 9-image reference set into ICROP3 and clinician daily practice alongside zone/stage/plus. P-score is not yet meant to replace plus diagnosis for treatment decisions, but its use at our institutions has permitted better comparison between examinations for progression and regression, communication between examiners, and documentation of vascular change without fundus imaging. P-score also could provide more detailed ROP classification for clinical trials, consistent with the spectrum of plus-like change that is now formally part of ICROP.

Isolated Retinal Neovascularization in Retinopathy of Prematurity: Clinical Associations and Prognostic Implications.

OBJECTIVE: Isolated retinal neovascularization (IRNV) is a common finding in patients with stage 2 and 3 retinopathy of prematurity (ROP). This study aimed to further classify the clinical course and significance of these lesions (previously described as "popcorn" based on clinical appearance) in patients with ROP as visualized with ultrawidefield OCT (UWF-OCT). DESIGN: Single center, retrospective case series. PARTICIPANTS: Images were collected from 136 babies in the Oregon Health and Science University neonatal intensive care unit. METHODS: A prototype UWF-OCT device captured en face scans (>140°), which were reviewed for the presence of IRNV along with standard zone, stage, and plus classification. In a cross-sectional analysis we compared demographics and the clinical course of eyes with and without IRNV. Longitudinally, we compared ROP severity using a clinician-assigned vascular severity score (VSS) and compared the risk of progression among eyes with and without IRNV using multivariable logistic regression. MAIN OUTCOME MEASURES: Differences in clinical demographics and disease progression between patients with and without IRNV. RESULTS: Of the 136 patients, 60 developed stage 2 or worse ROP during their disease course, 22 of whom had IRNV visualized on UWF-OCT (37%). On average, patients with IRNV had lower birth weights (BWs) (660.1 vs. 916.8 g, P = 0.001), gestational age (GA) (24.9 vs. 26.1 weeks, P = 0.01), and were more likely to present with ROP in zone I (63.4% vs. 15.8%, P < 0.001). They were also more likely to progress to stage 3 (68.2% vs. 13.2%, P < 0.001) and receive treatment (54.5% vs. 15.8%, P = 0.002). Eyes with IRNV had a higher peak VSS (5.61 vs. 3.73, P < 0.001) and averaged a higher VSS throughout their disease course. On multivariable logistic regression, IRNV was independently associated with progression to stage 3 (P = 0.02) and requiring treatment (P = 0.03), controlling for GA, BW, and initial zone 1 disease. CONCLUSIONS: In this single center study, we found that IRNV occurs in higher risk babies and was an independent risk factor for ROP progression and treatment. These findings may have implications for OCT-based ROP classifications in the future. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Data on electroconvulsive seizure in mice, effects of anesthesia on immediate early gene expression.

Although electroconvulsive therapy (ECT) is one of the most effective treatments for severe mood and psychotic disorders, the mechanisms underlying its therapeutic effects remain unknown. Electroconvulsive stimulation (ECS), the animal model for ECT, can be used to investigate the potential therapeutic mechanisms of ECT in rodents. ECS produces numerous effects in the brain, such as increasing levels of growth factors, inducing dendritic sprouting, and stimulating neurogenesis. It also induces high-level expression of immediate early genes (IEGs) that have been implicated in the pathogenesis of schizophrenia, such as early growth response 3 (Egr3) and activity-regulated cytoskeleton-associated protein (Arc), a validated downstream target of Egr3 [1-3]. However, the effect of isoflurane anesthesia preceding ECS on IEG response in mice has not been well characterized. This article provides immunofluorescent data of the activity responsive IEG ARC in the dorsal and ventral dentate gyrus of wildtype (WT) mice following ECS with or without anesthesia, as well as following sham ECS. The data in this article relate to a published article that employed serial ECS in mice to investigate the requirement of Egr3 in the neurobiological effects of this model of ECT [4]. The ability to study the effects of serial ECS has been limited in mice due to high rates of mortality during seizure. Administration of isoflurane anesthesia prior to ECS significantly reduces rodent mortality, irrespective of the number of times ECS is applied [5]. Since general anesthesia is administered to patients prior to ECT, use of isoflurane prior to ECS also more closely models the clinical use of ECT [6].

Detection of occult thrombosis in individuals with Fontan circulation by cardiac MRI.

OBJECTIVE: Identifying thrombus formation in Fontan circulation has been highly variable, with reports between 17 and 33%. Initially, thrombus detection was mainly done through echocardiograms. Delayed-enhancement cardiac MRI is emerging as a more effective imaging technique for thrombus identification. This study aims to determine the prevalence of occult cardiac thrombosis in patients undergoing clinically indicated cardiac MRI. METHODS: A retrospective chart review of children and adults in the Duke University Hospital Fontan registry who underwent delayed-enhancement cardiac MRI. Individuals were excluded if they never received a delayed-enhancement cardiac MRI or had insufficient data. Demographic characteristics, native heart anatomy, cardiac MRI measurements, and thromboembolic events were collected for all patients. RESULTS: In total, 119 unique individuals met inclusion criteria with a total of 171 scans. The median age at Fontan procedure was 3 (interquartile range 1, 4) years. The majority of patients had dominant systemic right ventricle. Cardiac function was relatively unchanged from the first cardiac MRI to the third cardiac MRI. While 36.4% had a thrombotic event by history, only 0.5% (1 patient) had an intracardiac thrombus detected by delayed-enhancement cardiac MRI. CONCLUSIONS: Despite previous echocardiographic reports of high prevalence of occult thrombosis in patients with Fontan circulation, we found very low prevalence using delayed-enhancement cardiac MRI. As more individuals are reaching adulthood after requiring early Fontan procedures in childhood, further work is needed to develop thrombus-screening protocols as a part of anticoagulation management.

Reversing immunosuppression in the tumor microenvironment of fibrolamellar carcinoma via PD-1 and IL-10 blockade.

Fibrolamellar carcinoma (FLC) is a rare liver tumor driven by the DNAJ-PKAc fusion protein that affects healthy young patients. Little is known about the immune response to FLC, limiting rational design of immunotherapy. Multiplex immunohistochemistry and gene expression profiling were performed to characterize the FLC tumor immune microenvironment and adjacent non-tumor liver (NTL). Flow cytometry and T cell receptor (TCR) sequencing were performed to determine the phenotype of tumor-infiltrating immune cells and the extent of T cell clonal expansion. Fresh human FLC tumor slice cultures (TSCs) were treated with antibodies blocking programmed cell death protein-1 (PD-1) and interleukin-10 (IL-10), with results measured by cleaved caspase-3 immunohistochemistry. Immune cells were concentrated in fibrous stromal bands, rather than in the carcinoma cell compartment. In FLC, T cells demonstrated decreased activation and regulatory T cells in FLC had more frequent expression of PD-1 and CTLA-4 than in NTL. Furthermore, T cells had relatively low levels of clonal expansion despite high TCR conservation across individuals. Combination PD-1 and IL-10 blockade signficantly increased cell death in human FLC TSCs. Immunosuppresion in the FLC tumor microenvironment is characterized by T cell exclusion and exhaustion, which may be reversible with combination immunotherapy.

Multinational External Validation of Autonomous Retinopathy of Prematurity Screening.

Importance: Retinopathy of prematurity (ROP) is a leading cause of blindness in children, with significant disparities in outcomes between high-income and low-income countries, due in part to insufficient access to ROP screening. Objective: To evaluate how well autonomous artificial intelligence (AI)-based ROP screening can detect more-than-mild ROP (mtmROP) and type 1 ROP. Design, Setting, and Participants: This diagnostic study evaluated the performance of an AI algorithm, trained and calibrated using 2530 examinations from 843 infants in the Imaging and Informatics in Retinopathy of Prematurity (i-ROP) study, on 2 external datasets (6245 examinations from 1545 infants in the Stanford University Network for Diagnosis of ROP [SUNDROP] and 5635 examinations from 2699 infants in the Aravind Eye Care Systems [AECS] telemedicine programs). Data were taken from 11 and 48 neonatal care units in the US and India, respectively. Data were collected from January 2012 to July 2021, and data were analyzed from July to December 2023. Exposures: An imaging processing pipeline was created using deep learning to autonomously identify mtmROP and type 1 ROP in eye examinations performed via telemedicine. Main Outcomes and Measures: The area under the receiver operating characteristics curve (AUROC) as well as sensitivity and specificity for detection of mtmROP and type 1 ROP at the eye examination and patient levels. Results: The prevalence of mtmROP and type 1 ROP were 5.9% (91 of 1545) and 1.2% (18 of 1545), respectively, in the SUNDROP dataset and 6.2% (168 of 2699) and 2.5% (68 of 2699) in the AECS dataset. Examination-level AUROCs for mtmROP and type 1 ROP were 0.896 and 0.985, respectively, in the SUNDROP dataset and 0.920 and 0.982 in the AECS dataset. At the cross-sectional examination level, mtmROP detection had high sensitivity (SUNDROP: mtmROP, 83.5%; 95% CI, 76.6-87.7; type 1 ROP, 82.2%; 95% CI, 81.2-83.1; AECS: mtmROP, 80.8%; 95% CI, 76.2-84.9; type 1 ROP, 87.8%; 95% CI, 86.8-88.7). At the patient level, all infants who developed type 1 ROP screened positive (SUNDROP: 100%; 95% CI, 81.4-100; AECS: 100%; 95% CI, 94.7-100) prior to diagnosis. Conclusions and Relevance: Where and when ROP telemedicine programs can be implemented, autonomous ROP screening may be an effective force multiplier for secondary prevention of ROP.

An Analysis of Solicitations From Predatory Journals in Ophthalmology.

PURPOSE: To evaluate trends associated with email communication from potentially predatory publishers to faculty in ophthalmology. DESIGN: Cross-sectional study METHODS: Ophthalmologists (n = 14) from various subspecialties and institutions were recruited to participate. Participants identified unsolicited emails that they had received originating from publishers in May 2021. Information collected included details on email contents and publisher organizations. Trends in communications from predatory publishers were evaluated. RESULTS: Over a 30-day study period, a total of 1813 emails were received from 383 unique publishers and 696 unique journals, with a mean (SD) of 4.73 (2.46) emails received per day per participant. Of the 1813 emails identified, 242 (13%) emails were invitations to conferences, whereas 1440 (80%) were solicitations for article submissions to open-access, pay-to-publish journals. A total of 522 (29.0%) emails were related to ophthalmology, and reference to a prior publication of the participant occurred in 262 emails (14%). Of the 696 unique journals identified, 174 (25%) journals were indexed on PubMed and 426 (61%) were listed on Beall's list. When comparing journals that were listed on PubMed vs those that were not, PubMed indexed journals had a higher impact factor (2.1 vs 1.5, P = .002), were less likely to use "greetings" (76% vs 91%, P < .001), had fewer spelling/grammar errors (40% vs 51%, P = .01), and were less likely to offer rapid publication (16% vs 25%, P = .02). CONCLUSIONS: Unsolicited requests to publish occur frequently and may diminish the quality of the scientific literature. We encourage individuals in ophthalmology to be aware of these trends in predatory publishing.

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.

The effects of short-term, progressive exercise training on disease activity in smouldering multiple myeloma and monoclonal gammopathy of undetermined significance: a single-arm pilot study.

BACKGROUND: High levels of physical activity are associated with reduced risk of the blood cancer multiple myeloma (MM). MM is preceded by the asymptomatic stages of monoclonal gammopathy of undetermined significance (MGUS) and smouldering multiple myeloma (SMM) which are clinically managed by watchful waiting. A case study (N = 1) of a former elite athlete aged 44 years previously indicated that a multi-modal exercise programme reversed SMM disease activity. To build from this prior case study, the present pilot study firstly examined if short-term exercise training was feasible and safe for a group of MGUS and SMM patients, and secondly investigated the effects on MGUS/SMM disease activity. METHODS: In this single-arm pilot study, N = 20 participants diagnosed with MGUS or SMM were allocated to receive a 16-week progressive exercise programme. Primary outcome measures were feasibility and safety. Secondary outcomes were pre- to post-exercise training changes to blood biomarkers of MGUS and SMM disease activity- monoclonal (M)-protein and free light chains (FLC)- plus cardiorespiratory and functional fitness, body composition, quality of life, blood immunophenotype, and blood biomarkers of inflammation. RESULTS: Fifteen (3 MGUS and 12 SMM) participants completed the exercise programme. Adherence was 91 ± 11%. Compliance was 75 ± 25% overall, with a notable decline in compliance at intensities > 70% V̇O2PEAK. There were no serious adverse events. There were no changes to M-protein (0.0 ± 1.0 g/L, P =.903), involved FLC (+ 1.8 ± 16.8 mg/L, P =.839), or FLC difference (+ 0.2 ± 15.6 mg/L, P =.946) from pre- to post-exercise training. There were pre- to post-exercise training improvements to diastolic blood pressure (- 3 ± 5 mmHg, P =.033), sit-to-stand test performance (+ 5 ± 5 repetitions, P =.002), and energy/fatigue scores (+ 10 ± 15%, P =.026). Other secondary outcomes were unchanged. CONCLUSIONS: A 16-week progressive exercise programme was feasible and safe, but did not reverse MGUS/SMM disease activity, contrasting a prior case study showing that five years of exercise training reversed SMM in a 44-year-old former athlete. Longer exercise interventions should be explored in a group of MGUS/SMM patients, with measurements of disease biomarkers, along with rates of disease progression (i.e., MGUS/SMM to MM). REGISTRATION: https://www.isrctn.com/ISRCTN65527208 (14/05/2018).

Chorioretinal Anastomosis and Retinal Detachment with Laser Photocoagulation Treated Incontinentia Pigmenti.

PURPOSE: To describe a case of incontinentia pigmenti in which chorioretinal anastomosis occurred after laser photocoagulation, which was ultimately complicated by tractional and rhegmatogenous detachment. METHODS: Observational case report. RESULTS: A 2-month-old was referred to ophthalmology for a rash characteristic of incontinentia pigmenti due to concern for ocular involvement and was found to have peripheral avascular retina with early neovascularization. Following several rounds of panretinal photocoagulation, a chorioretinal anastomosis was noted on follow up fluorescein angiography in the left eye. Subsequently, a tractional retinal detachment formed and was treated initially with a lens sparing pars plana vitrectomy, endolaser, and scleral buckle. Despite treatment, it progressed to a combined tractional/rhegmatogenous detachment and was deemed inoperable. CONCLUSION: Chorioretinal anastomosis is a rare complication of laser photocoagulation.

Genome-wide association identifies novel ROP risk loci in a multiethnic cohort.

We conducted a genome-wide association study (GWAS) in a multiethnic cohort of 920 at-risk infants for retinopathy of prematurity (ROP), a major cause of childhood blindness, identifying 1 locus at genome-wide significance level (p < 5×10-8) and 9 with significance of p < 5×10-6 for ROP ≥ stage 3. The most significant locus, rs2058019, reached genome-wide significance within the full multiethnic cohort (p = 4.96×10-9); Hispanic and European Ancestry infants driving the association. The lead single nucleotide polymorphism (SNP) falls in an intronic region within the Glioma-associated oncogene family zinc finger 3 (GLI3) gene. Relevance for GLI3 and other top-associated genes to human ocular disease was substantiated through in-silico extension analyses, genetic risk score analysis and expression profiling in human donor eye tissues. Thus, we identify a novel locus at GLI3 with relevance to retinal biology, supporting genetic susceptibilities for ROP risk with possible variability by race and ethnicity.

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.

Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity: Insights from a Multimodal Deep Learning Approach.

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 (FiO2). 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 FiO2 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 FiO2 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.

Assessing the Impact of Image Quality on Deep Learning Classification of Infectious Keratitis.

Objective: To investigate the impact of corneal photograph quality on convolutional neural network (CNN) predictions. Design: A CNN trained to classify bacterial and fungal keratitis was evaluated using photographs of ulcers labeled according to 5 corneal image quality parameters: eccentric gaze direction, abnormal eyelid position, over/under-exposure, inadequate focus, and malpositioned light reflection. Participants: All eligible subjects with culture and stain-proven bacterial and/or fungal ulcers presenting to Aravind Eye Hospital in Madurai, India, between January 1, 2021 and December 31, 2021. Methods: Convolutional neural network classification performance was compared for each quality parameter, and gradient class activation heatmaps were generated to visualize regions of highest influence on CNN predictions. Main Outcome Measures: Area under the receiver operating characteristic and precision recall curves were calculated to quantify model performance. Bootstrapped confidence intervals were used for statistical comparisons. Logistic loss was calculated to measure individual prediction accuracy. Results: Individual presence of either light reflection or eyelids obscuring the corneal surface was associated with significantly higher CNN performance. No other quality parameter significantly influenced CNN performance. Qualitative review of gradient class activation heatmaps generally revealed the infiltrate as having the highest diagnostic relevance. Conclusions: The CNN demonstrated expert-level performance regardless of image quality. Future studies may investigate use of smartphone cameras and image sets with greater variance in image quality to further explore the influence of these parameters on model performance. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Generative Artificial Intelligence Through ChatGPT and Other Large Language Models in Ophthalmology: Clinical Applications and Challenges.

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.