Use of an Artificial Intelligence-Generated Vascular Severity Score Improved Plus Disease Diagnosis in Retinopathy of Prematurity.

PURPOSE: To evaluate whether providing clinicians with an artificial intelligence (AI)-based vascular severity score (VSS) improves consistency in the diagnosis of plus disease in retinopathy of prematurity (ROP). DESIGN: Multireader diagnostic accuracy imaging study. PARTICIPANTS: Eleven ROP experts, 9 of whom had been in practice for 10 years or more. 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 examinations, a subset of 150 eye examinations from 110 infants were selected for grading. An AI-based VSS was assigned to each set of images using the i-ROP DL system (Siloam Vision). The clinicians were asked to diagnose plus disease for each examination and to assign an estimated VSS (range, 1-9) at baseline, and then again 1 month later with AI-based VSS assistance. A reference standard diagnosis (RSD) was assigned to each eye examination from the Imaging and Informatics in ROP study based on 3 masked expert labels and the ophthalmoscopic diagnosis. MAIN OUTCOME MEASURES: Mean linearly weighted κ value for plus disease diagnosis compared with RSD. Area under the receiver operating characteristic curve (AUC) and area under the precision-recall curve (AUPR) for labels 1 through 9 compared with RSD for plus disease. RESULTS: Expert agreement improved significantly, from substantial (κ value, 0.69 [0.59, 0.75]) to near perfect (κ value, 0.81 [0.71, 0.86]), when AI-based VSS was integrated. Additionally, a significant improvement in plus disease discrimination was achieved as measured by mean AUC (from 0.94 [95% confidence interval (CI), 0.92-0.96] to 0.98 [95% CI, 0.96-0.99]; difference, 0.04 [95% CI, 0.01-0.06]) and AUPR (from 0.86 [95% CI, 0.81-0.90] to 0.95 [95% CI, 0.91-0.97]; difference, 0.09 [95% CI, 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 with an RSD for plus disease. If implemented in practice, AI-based VSS could reduce interobserver variability and could standardize treatment for infants with ROP. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

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.

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.

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.

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.

Hidden Flaws Behind Expert-Level Accuracy of Multimodal GPT-4 Vision in Medicine.

Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges - an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V performs comparatively to human physicians regarding multi-choice accuracy (81.6% vs. 77.8%). GPT-4V also performs well in cases where physicians incorrectly answer, with over 78% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (35.5%), most prominent in image comprehension (27.2%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such multimodal AI models into clinical workflows.

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.

Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine.

Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges-an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V performs comparatively to human physicians regarding multi-choice accuracy (81.6% vs. 77.8%). GPT-4V also performs well in cases where physicians incorrectly answer, with over 78% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (35.5%), most prominent in image comprehension (27.2%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such multimodal AI models into clinical workflows.

The HEALthy Brain and Child Development Study (HBCD): NIH collaboration to understand the impacts of prenatal and early life experiences on brain development.

The human brain undergoes rapid development during the first years of life. Beginning in utero, a wide array of biological, social, and environmental factors can have lasting impacts on brain structure and function. To understand how prenatal and early life experiences alter neurodevelopmental trajectories and shape health outcomes, several NIH Institutes, Centers, and Offices collaborated to support and launch the HEALthy Brain and Child Development (HBCD) Study. The HBCD Study is a multi-site prospective longitudinal cohort study, that will examine human brain, cognitive, behavioral, social, and emotional development beginning prenatally and planned through early childhood. Influenced by the success of the ongoing Adolescent Brain Cognitive DevelopmentSM Study (ABCD Study®) and in partnership with the NIH Helping to End Addiction Long-term® Initiative, or NIH HEAL Initiative®, the HBCD Study aims to establish a diverse cohort of over 7000 pregnant participants to understand how early life experiences, including prenatal exposure to addictive substances and adverse social environments as well as their interactions with an individual's genes, can affect neurodevelopmental trajectories and outcomes. Knowledge gained from the HBCD Study will help identify targets for early interventions and inform policies that promote resilience and mitigate the neurodevelopmental effects of adverse childhood experiences and environments.