Comparing code-free and bespoke deep learning approaches in ophthalmology.

AIM: Code-free deep learning (CFDL) allows clinicians without coding expertise to build high-quality artificial intelligence (AI) models without writing code. In this review, we comprehensively review the advantages that CFDL offers over bespoke expert-designed deep learning (DL). As exemplars, we use the following tasks: (1) diabetic retinopathy screening, (2) retinal multi-disease classification, (3) surgical video classification, (4) oculomics and (5) resource management. METHODS: We performed a search for studies reporting CFDL applications in ophthalmology in MEDLINE (through PubMed) from inception to June 25, 2023, using the keywords 'autoML' AND 'ophthalmology'. After identifying 5 CFDL studies looking at our target tasks, we performed a subsequent search to find corresponding bespoke DL studies focused on the same tasks. Only English-written articles with full text available were included. Reviews, editorials, protocols and case reports or case series were excluded. We identified ten relevant studies for this review. RESULTS: Overall, studies were optimistic towards CFDL's advantages over bespoke DL in the five ophthalmological tasks. However, much of such discussions were identified to be mono-dimensional and had wide applicability gaps. High-quality assessment of better CFDL applicability over bespoke DL warrants a context-specific, weighted assessment of clinician intent, patient acceptance and cost-effectiveness. We conclude that CFDL and bespoke DL are unique in their own assets and are irreplaceable with each other. Their benefits are differentially valued on a case-to-case basis. Future studies are warranted to perform a multidimensional analysis of both techniques and to improve limitations of suboptimal dataset quality, poor applicability implications and non-regulated study designs. CONCLUSION: For clinicians without DL expertise and easy access to AI experts, CFDL allows the prototyping of novel clinical AI systems. CFDL models concert with bespoke models, depending on the task at hand. A multidimensional, weighted evaluation of the factors involved in the implementation of those models for a designated task is warranted.

Quality of hydroxychloroquine retinopathy screening at a Canadian teaching hospital.

PURPOSE: To assess the quality of hydroxychloroquine (HCQ)-induced retinopathy screening at a Canadian tertiary center, we concentrate on risk factor documentation within the electronic health record, in accordance with the 2016 AAO guidelines. METHODS: We performed a retrospective quality assessment study based on chart review of patients who underwent screening for HCQ-induced retinopathy at the Centre Hospitalier de l'Université de Montréal (CHUM) from 2016 to 2019. We evaluated four key risk factors for HCQ-induced retinopathy: daily dose, duration of use, renal disease, and tamoxifen use, using a three-tier grading system (ideal, adequate, inadequate) for documentation assessment. Pareto and root cause analyses were conducted to identify potential improvement solutions. RESULTS: Documentation quality varied in our study: daily dosage was 33% ideal, 31% appropriate, and 36% inappropriate. Duration of use documentation was 75% ideal, 2% adequate, and 24% inadequate. Renal disease documentation was only 6% ideal, with 62% adequate and 32% of charts lacking any past medical history. Among women's charts, tamoxifen use wasn't documented at all, with 65% adequately documenting medication lists. Pareto analysis indicated that improving renal disease and tamoxifen documentation could reduce 64% of non-ideal records, and enhancing daily dose documentation could decrease this by up to 90%. CONCLUSION: Accurate documentation of key risk factors is critical for HCQ-induced retinopathy screening, impacting both exam initiation and frequency. Our study identifies potential improvements in the screening process at the hospital, referring physician, and ophthalmologist levels. Implementing integrated pathways could enhance patient experience and screening effectiveness.

Zellweger Spectrum Disorder: Ophthalmic Findings from a New Natural History Study Cohort and Scoping Literature Review.

PURPOSE: Individuals with Zellweger spectrum disorder (ZSD) manifest a spectrum of clinical phenotypes but almost all have retinal degeneration leading to blindness. The onset, extent, and progression of retinal findings have not been well described. It is crucial to understand the natural history of vision loss in ZSD to define reliable endpoints for future interventional trials. Herein, we describe ophthalmic findings in the largest number of ZSD patients to date. DESIGN: Retrospective review of longitudinal data from medical charts and review of cross-sectional data from the literature. PARTICIPANTS: Sixty-six patients with ZSD in the retrospective cohort and 119 patients reported in the literature, divided into 4 disease phenotypes based on genotype or clinical severity. METHODS: We reviewed ophthalmology records collected from the retrospective cohort (Clinicaltrials.gov NCT01668186) and performed a scoping review of the literature for ophthalmic findings in patients with ZSD. We extracted available ophthalmic data and analyzed by age and disease severity. MAIN OUTCOME MEASURES: Visual acuity (VA), posterior and anterior segment descriptions, nystagmus, refraction, electroretinography findings, visual evoked potentials, and OCT results and images. RESULTS: Visual acuity was worse at younger ages in those with severe disease compared with older patients with intermediate to mild disease for all 78 participants analyzed, with a median VA of 0.93 logarithm of the minimum angle of resolution (Snellen 20/320). Longitudinal VA data revealed slow loss over time and legal blindness onset at an average age of 7.8 years. Funduscopy showed retinal pigmentation, macular abnormalities, small or pale optic discs, and attenuated vessels with higher prevalence in milder severity groups and did not change with age. Electroretinography waveforms were diminished in 91% of patients, 46% of which were extinguished and did not change with age. OCT in milder patients revealed schitic changes in 18 of 23 individuals (age range 1.8 to 30 years), with evolution or stable macular edema. CONCLUSIONS: In ZSD, VA slowly deteriorates and is associated with disease severity, serial electroretinography is not useful for documenting vision loss progression, and intraretinal schitic changes may be common. Multiple systematic measures are required to assess retinal dystrophy accurately in ZSD, including functional vision measures. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Deep learning for ultra-widefield imaging: a scoping review.

PURPOSE: This article is a scoping review of published and peer-reviewed articles using deep-learning (DL) applied to ultra-widefield (UWF) imaging. This study provides an overview of the published uses of DL and UWF imaging for the detection of ophthalmic and systemic diseases, generative image synthesis, quality assessment of images, and segmentation and localization of ophthalmic image features. METHODS: A literature search was performed up to August 31st, 2021 using PubMed, Embase, Cochrane Library, and Google Scholar. The inclusion criteria were as follows: (1) deep learning, (2) ultra-widefield imaging. The exclusion criteria were as follows: (1) articles published in any language other than English, (2) articles not peer-reviewed (usually preprints), (3) no full-text availability, (4) articles using machine learning algorithms other than deep learning. No study design was excluded from consideration. RESULTS: A total of 36 studies were included. Twenty-three studies discussed ophthalmic disease detection and classification, 5 discussed segmentation and localization of ultra-widefield images (UWFIs), 3 discussed generative image synthesis, 3 discussed ophthalmic image quality assessment, and 2 discussed detecting systemic diseases via UWF imaging. CONCLUSION: The application of DL to UWF imaging has demonstrated significant effectiveness in the diagnosis and detection of ophthalmic diseases including diabetic retinopathy, retinal detachment, and glaucoma. DL has also been applied in the generation of synthetic ophthalmic images. This scoping review highlights and discusses the current uses of DL with UWF imaging, and the future of DL applications in this field.

Blink detection and magnetic force generation for correction of lagophthalmos, with specific regard to implant compatibility testing.

PURPOSE: The overall goal was to restore a normal and synchronous blink in unilateral lagophthalmos. We describe the biocompatibility profiling of a novel ferromagnetic implant used for electromagnetic eyelid force generation. METHODS: A non-contact blink detection system and an electromagnetic stimulation system were designed and tested. A modified Lester-Burch speculum equipped with strain gauge technology was used in blinking force measurement. Samarium-cobalt magnets were prototyped and coated with parylene-C. Biocompatibility testing was performed using NIH/3T3 mouse fibroblast cells with MTT colorimetric assay cytotoxic quantification. OUTCOME MEASURES: Cellular viability and interleukin concentrations. RESULTS: Our system was capable of detecting 95.5 ± 3.6% of blinks in various lighting conditions. Using our force measuring device, the difference between non-paralyzed and paralyzed orbicularis oculi (OO) for normal and forceful blinking closure was 40.4 g and 101.9 g, respectively. A 16.6 × 5.0 × 1.5 mm curved shaped samarium cobalt eyelid implant was successfully developed and showed a reproducible blink at 100 ms with full corneal coverage with external eyelid taping. Compared to gold weights, parylene-C coated samarium cobalt implants showed not only excellent cell viability (82.0 ± 4.9% vs. 88.4 ± 0.9%, respectively, p > .05), but also below detection threshold for pro-inflammatory marker concentrations (interleukin-6 < 2 pg/mL and interleukin-10 < 3 pg/mL). CONCLUSIONS: We demonstrated excellent in-vitro biocompatibility of our parylene-C coated samarium cobalt implants. We believe that our novel approach can improve the quality-of-life of affected individuals and provides new understanding of blinking biomechanics.

The prognostic value of peripheral retinal nonperfusion in diabetic retinopathy using ultra-widefield fluorescein angiography.

PURPOSE: To investigate the prognostic value of peripheral retinal nonperfusion in patients with diabetic retinopathy using ultra-widefield fluorescein angiography (UWFA). METHODS: A cross-sectional study included 78 treatment-naïve eyes with nonproliferative and proliferative diabetic retinopathy (NPDR and PDR). Eyes were divided into three groups: mild/moderate NPDR (n = 31), severe NPDR (n = 31), and PDR (n = 16). Three nonperfusion variables were calculated reflecting the proportion of nonperfused to visible retina based on initial UWFA: central nonperfusion (CNP) index, peripheral nonperfusion (PNP) index, and PNP ratio. The relationships between these indices and central subfield thickness (CST) and spectacle-corrected visual acuity (SCVA) were evaluated. RESULTS: CNP and PNP indices were significantly higher in the PDR group vs. mild/moderate NPDR group (p = 0.007 and 0.008, respectively) but not in the PDR group vs. severe NPDR group (p = 0.149 and p = 0.535, respectively). A significant linear correlation was found between the CNP and PNP indices in both severe NPDR and PDR groups (R2 = 0.141, p = 0.041, and R2 = 0.311, p = 0.025, respectively). Nonperfusion predominance was not statistically correlated with the presence of macular edema (p = 0.058) or disorganization of retinal inner layers (p = 1). In the severe NPDR group, there was a moderately positive correlation between CNP index and CST (rs = 0.496, p = 0.019) and no correlation between CNP index and SCVA when controlling for CST (p = 0.160). In the PDR group, a strong negative correlation between PNP ratio and CST was found (rs = -0.659, p = 0.014), but no correlation was observed between CNP index, CST, and SCVA. In the PDR group, a positive correlation was found between PNP index, PNP ratio, and SCVA (rs = 0.549, p = 0.027, and rs = 0.626, p = 0.010, respectively), even after controlling for CST (rs = 0.599, p = 0.040). CONCLUSIONS: Higher amounts of retinal nonperfusion are seen in patients with more severe retinopathy. Increased CNP is associated with macular thickening and subsequent vision loss. Having predominantly PNP was independently associated with worse VA, regardless of macular thickness. Further studies are needed to investigate the role of PNP in vision loss in diabetic retinopathy.

360-degree intra-operative laser retinopexy for the prevention of retinal re-detachment in patients treated with primary pars plana vitrectomy.

PURPOSE: To investigate the effect of 360° intra-operative laser retinopexy (ILR) for the prevention of retinal re-detachment in patients treated with pars plana vitrectomy (PPV) for primary rhegmatogenous retinal detachment (RRD). METHODS: A retrospective single-institution cohort study was performed. Consecutive patients with primary uncomplicated RRD who underwent 23-gauge PPV with gas endotamponade between July 2013 and July 2016 were included in the study (n = 151). Two cohorts were compared: one which received laser retinopexy only around identified tears/holes/lattice zones (Control group, n = 86), and one which received additional 360° intra-operative laser retinopexy (360° ILR group, n = 65). RESULTS: Retinal re-detachment was seen in 4/65 eyes (6%) in the 360° ILR group compared to 18/86 eyes (21%) in the control group. In multiple logistic regression, the 360° ILR was associated with a 75% reduction in the odds of retinal re-detachment compared to control (OR = 0.248, 95% CI [0.079-0.772], p = 0.016). There was no statistically significant difference in the incidence of epiretinal membrane formation between the two groups. CONCLUSIONS: Intra-operative 360° laser retinopexy during PPV with gas endotamponade resulted in a significant reduction in the odds of postoperative retinal re-detachment in eyes with uncomplicated primary RRD.

Vision-Language Models for Feature Detection of Macular Diseases on Optical Coherence Tomography.

Importance: Vision-language models (VLMs) are a novel artificial intelligence technology capable of processing image and text inputs. While demonstrating strong generalist capabilities, their performance in ophthalmology has not been extensively studied. Objective: To assess the performance of the Gemini Pro VLM in expert-level tasks for macular diseases from optical coherence tomography (OCT) scans. Design, Setting, and Participants: This was a cross-sectional diagnostic accuracy study evaluating a generalist VLM on ophthalmology-specific tasks using the open-source Optical Coherence Tomography Image Database. The dataset included OCT B-scans from 50 unique patients: healthy individuals and those with macular hole, diabetic macular edema, central serous chorioretinopathy, and age-related macular degeneration. Each OCT scan was labeled for 10 key pathological features, referral recommendations, and treatments. The images were captured using a Cirrus high definition OCT machine (Carl Zeiss Meditec) at Sankara Nethralaya Eye Hospital, Chennai, India, and the dataset was published in December 2018. Image acquisition dates were not specified. Exposures: Gemini Pro, using a standard prompt to extract structured responses on December 15, 2023. Main Outcomes and Measures: The primary outcome was model responses compared against expert labels, calculating F1 scores for each pathological feature. Secondary outcomes included accuracy in diagnosis, referral urgency, and treatment recommendation. The model's internal concordance was evaluated by measuring the alignment between referral and treatment recommendations, independent of diagnostic accuracy. Results: The mean F1 score was 10.7% (95% CI, 2.4-19.2). Measurable F1 scores were obtained for macular hole (36.4%; 95% CI, 0-71.4), pigment epithelial detachment (26.1%; 95% CI, 0-46.2), subretinal hyperreflective material (24.0%; 95% CI, 0-45.2), and subretinal fluid (20.0%; 95% CI, 0-45.5). A correct diagnosis was achieved in 17 of 50 cases (34%; 95% CI, 22-48). Referral recommendations varied: 28 of 50 were correct (56%; 95% CI, 42-70), 10 of 50 were overcautious (20%; 95% CI, 10-32), and 12 of 50 were undercautious (24%; 95% CI, 12-36). Referral and treatment concordance were very high, with 48 of 50 (96%; 95 % CI, 90-100) and 48 of 49 (98%; 95% CI, 94-100) correct answers, respectively. Conclusions and Relevance: In this study, a generalist VLM demonstrated limited vision capabilities for feature detection and management of macular disease. However, it showed low self-contradiction, suggesting strong language capabilities. As VLMs continue to improve, validating their performance on large benchmarking datasets will help ascertain their potential in ophthalmology.

Medical education with large language models in ophthalmology: custom instructions and enhanced retrieval capabilities.

Foundation models are the next generation of artificial intelligence that has the potential to provide novel use cases for healthcare. Large language models (LLMs), a type of foundation model, are capable of language comprehension and the ability to generate human-like text. Researchers and developers have been tuning LLMs to optimise their performance in specific tasks, such as medical challenge problems. Until recently, tuning required technical programming expertise, but the release of custom generative pre-trained transformers (GPTs) by OpenAI has allowed users to tune their own GPTs with natural language. This has the potential to democratise access to high-quality bespoke LLMs globally. In this review, we provide an overview of LLMs, how they are tuned and how custom GPTs work. We provide three use cases of custom GPTs in ophthalmology to demonstrate the versatility and effectiveness of these tools. First, we present 'EyeTeacher', an educational aid that generates questions from clinical guidelines to facilitate learning. Second, we built 'EyeAssistant', a clinical support tool that is tuned with clinical guidelines to respond to various physician queries. Lastly, we design 'The GPT for GA', which offers clinicians a comprehensive summary of emerging management strategies for geographic atrophy by analysing peer-reviewed documents. The review underscores the significance of custom instructions and information retrieval in tuning GPTs for specific tasks in ophthalmology. We also discuss the evaluation of LLM responses and address critical aspects such as privacy and accountability in their clinical application. Finally, we discuss their potential in ophthalmic education and clinical practice.

Comparing code-free deep learning models to expert-designed models for detecting retinal diseases from optical coherence tomography.

BACKGROUND: Code-free deep learning (CFDL) is a novel tool in artificial intelligence (AI). This study directly compared the discriminative performance of CFDL models designed by ophthalmologists without coding experience against bespoke models designed by AI experts in detecting retinal pathologies from optical coherence tomography (OCT) videos and fovea-centered images. METHODS: Using the same internal dataset of 1,173 OCT macular videos and fovea-centered images, model development was performed simultaneously but independently by an ophthalmology resident (CFDL models) and a postdoctoral researcher with expertise in AI (bespoke models). We designed a multi-class model to categorize video and fovea-centered images into five labels: normal retina, macular hole, epiretinal membrane, wet age-related macular degeneration and diabetic macular edema. We qualitatively compared point estimates of the performance metrics of the CFDL and bespoke models. RESULTS: For videos, the CFDL model demonstrated excellent discriminative performance, even outperforming the bespoke models for some metrics: area under the precision-recall curve was 0.984 (vs. 0.901), precision and sensitivity were both 94.1% (vs. 94.2%) and accuracy was 94.1% (vs. 96.7%). The fovea-centered CFDL model overall performed better than video-based model and was as accurate as the best bespoke model. CONCLUSION: This comparative study demonstrated that code-free models created by clinicians without coding expertise perform as accurately as expert-designed bespoke models at classifying various retinal pathologies from OCT videos and images. CFDL represents a step forward towards the democratization of AI in medicine, although its numerous limitations must be carefully addressed to ensure its effective application in healthcare.

Generative artificial intelligence in ophthalmology: current innovations, future applications and challenges.

The rapid advancements in generative artificial intelligence are set to significantly influence the medical sector, particularly ophthalmology. Generative adversarial networks and diffusion models enable the creation of synthetic images, aiding the development of deep learning models tailored for specific imaging tasks. Additionally, the advent of multimodal foundational models, capable of generating images, text and videos, presents a broad spectrum of applications within ophthalmology. These range from enhancing diagnostic accuracy to improving patient education and training healthcare professionals. Despite the promising potential, this area of technology is still in its infancy, and there are several challenges to be addressed, including data bias, safety concerns and the practical implementation of these technologies in clinical settings.

Automated Machine Learning versus Expert-Designed Models in Ocular Toxoplasmosis: Detection and Lesion Localization Using Fundus Images.

PURPOSE: Automated machine learning (AutoML) allows clinicians without coding experience to build their own deep learning (DL) models. This study assesses the performance of AutoML in detecting and localizing ocular toxoplasmosis (OT) lesions in fundus images and compares it to expert-designed models. METHODS: Ophthalmology trainees without coding experience designed AutoML models using 304 labelled fundus images. We designed a binary model to differentiate OT from normal and an object detection model to visually identify OT lesions. RESULTS: The AutoML model had an area under the precision-recall curve (AuPRC) of 0.945, sensitivity of 100%, specificity of 83% and accuracy of 93.5% (vs. 94%, 86% and 91% for the bespoke models). The AutoML object detection model had an AuPRC of 0.600 with a precision of 93.3% and recall of 56%. Using a diversified external validation dataset, our model correctly labeled 15 normal fundus images (100%) and 15 OT fundus images (100%), with a mean confidence score of 0.965 and 0.963, respectively. CONCLUSION: AutoML models created by ophthalmologists without coding experience were comparable or better than expert-designed bespoke models trained on the same dataset. By creatively using AutoML to identify OT lesions on fundus images, our approach brings the whole spectrum of DL model design into the hands of clinicians.

Foundation models in ophthalmology.

Foundation models represent a paradigm shift in artificial intelligence (AI), evolving from narrow models designed for specific tasks to versatile, generalisable models adaptable to a myriad of diverse applications. Ophthalmology as a specialty has the potential to act as an exemplar for other medical specialties, offering a blueprint for integrating foundation models broadly into clinical practice. This review hopes to serve as a roadmap for eyecare professionals seeking to better understand foundation models, while equipping readers with the tools to explore the use of foundation models in their own research and practice. We begin by outlining the key concepts and technological advances which have enabled the development of these models, providing an overview of novel training approaches and modern AI architectures. Next, we summarise existing literature on the topic of foundation models in ophthalmology, encompassing progress in vision foundation models, large language models and large multimodal models. Finally, we outline major challenges relating to privacy, bias and clinical validation, and propose key steps forward to maximise the benefit of this powerful technology.

The role of saliency maps in enhancing ophthalmologists' trust in artificial intelligence models.

PURPOSE: Saliency maps (SM) allow clinicians to better understand the opaque decision-making process in artificial intelligence (AI) models by visualising the important features responsible for predictions. This ultimately improves interpretability and confidence. In this work, we review the use case for SMs, exploring their impact on clinicians' understanding and trust in AI models. We use the following ophthalmic conditions as examples: (1) glaucoma, (2) myopia, (3) age-related macular degeneration, and (4) diabetic retinopathy. METHOD: A multi-field search on MEDLINE, Embase, and Web of Science was conducted using specific keywords. Only studies on the use of SMs in glaucoma, myopia, AMD, or DR were considered for inclusion. RESULTS: Findings reveal that SMs are often used to validate AI models and advocate for their adoption, potentially leading to biased claims. Overlooking the technical limitations of SMs, and the conductance of superficial assessments of their quality and relevance, was discerned. Uncertainties persist regarding the role of saliency maps in building trust in AI. It is crucial to enhance understanding of SMs' technical constraints and improve evaluation of their quality, impact, and suitability for specific tasks. Establishing a standardised framework for selecting and assessing SMs, as well as exploring their relationship with other reliability sources (e.g. safety and generalisability), is essential for enhancing clinicians' trust in AI. CONCLUSION: We conclude that SMs are not beneficial for interpretability and trust-building purposes in their current forms. Instead, SMs may confer benefits to model debugging, model performance enhancement, and hypothesis testing (e.g. novel biomarkers).

Democratizing Vitreoretinal Surgery Training With a Portable and Affordable Virtual Reality Simulator in the Metaverse.

Purpose: The purpose of this study was to develop and validate RetinaVR, an affordable, portable, and fully immersive virtual reality (VR) simulator for vitreoretinal surgery training. Methods: We built RetinaVR as a standalone app on the Meta Quest 2 VR headset. It simulates core vitrectomy, peripheral shaving, membrane peeling, and endolaser application. In a validation study (n = 20 novices and experts), we measured: efficiency, safety, and module-specific performance. We first explored unadjusted performance differences through an effect size analysis. Then, a linear mixed-effects model was used to isolate the impact of age, sex, expertise, and experimental run on performance. Results: Experts were significantly safer in membrane peeling but not when controlling for other factors. Experts were significantly better in core vitrectomy, even when controlling for other factors (P = 0.014). Heatmap analysis of endolaser applications showed more consistent retinopexy among experts. Age had no impact on performance, but male subjects were faster in peripheral shaving (P = 0.036) and membrane peeling (P = 0.004). A learning curve was demonstrated with improving efficiency at each experimental run for all modules. Repetition also led to improved safety during membrane peeling (P = 0.003), and better task-specific performance during core vitrectomy (P = 0.038), peripheral shaving (P = 0.011), and endolaser application (P = 0.043). User experience was favorable to excellent in all spheres. Conclusions: RetinaVR demonstrates potential as an affordable, portable training tool for vitreoretinal surgery. Its construct validity is established, showing varying performance in a way that correlates with experimental runs, age, sex, and level of expertise. Translational Relevance: Fully immersive VR technology could revolutionize surgical training, making it more accessible, especially in developing nations.

Trends and Clinical Outcomes of Fungal Keratitis in Canada: A 20-year Retrospective Multicentre Study.

PURPOSE: An increase in fungal and particularly filamentous keratitis has been observed in many geographic areas, mostly in contact lens wearers. This study seeks to characterize long-term trends in fungal keratitis in a continental climate area to provide guidance for diagnosis and treatment. DESIGN: Retrospective multicentric case series. METHODS: Cases of microbiology-confirmed fungal keratitis from 2003 to 2022 presenting to tertiary care centers across Canada were included. Charts were reviewed for patient demographics, risk factors, visual acuity, and treatments undertaken. RESULTS: A total of 138 patients were identified: 75 had yeast keratitis while 63 had filamentous keratitis. Patients with yeast keratitis had more ocular surface disease (79% vs 28%) while patients with filamentous keratitis wore more refractive contact lenses (78% vs 19%). Candida species accounted for 96% of all yeast identified, while Aspergillus (32%) and Fusarium (26%) were the most common filamentous fungi species. The mean duration of treatment was 81 ± 96 days. Patients with yeast keratitis did not have significantly improved visual acuity with medical treatment (1.8 ± 1 LogMAR to 1.9 ± 1.5 LogMAR, P = .9980), in contrast to patients with filamentous keratitis (1.4 ± 1.2 LogMAR to 1.1 ± 1.3 LogMAR, P = .0093). CONCLUSIONS: Fungal keratitis is increasing in incidence, with contact lenses emerging as one of the leading risk factors. Significant differences in the risk factors and visual outcomes exist between yeast keratitis and filamentous keratitis which may guide diagnosis and treatment.

Artificial Intelligence to Facilitate Clinical Trial Recruitment in Age-Related Macular Degeneration.

Objective: Recent developments in artificial intelligence (AI) have positioned it to transform several stages of the clinical trial process. In this study, we explore the role of AI in clinical trial recruitment of individuals with geographic atrophy (GA), an advanced stage of age-related macular degeneration, amidst numerous ongoing clinical trials for this condition. Design: Cross-sectional study. Subjects: Retrospective dataset from the INSIGHT Health Data Research Hub at Moorfields Eye Hospital in London, United Kingdom, including 306 651 patients (602 826 eyes) with suspected retinal disease who underwent OCT imaging between January 1, 2008 and April 10, 2023. Methods: A deep learning model was trained on OCT scans to identify patients potentially eligible for GA trials, using AI-generated segmentations of retinal tissue. This method's efficacy was compared against a traditional keyword-based electronic health record (EHR) search. A clinical validation with fundus autofluorescence (FAF) images was performed to calculate the positive predictive value of this approach, by comparing AI predictions with expert assessments. Main Outcome Measures: The primary outcomes included the positive predictive value of AI in identifying trial-eligible patients, and the secondary outcome was the intraclass correlation between GA areas segmented on FAF by experts and AI-segmented OCT scans. Results: The AI system shortlisted a larger number of eligible patients with greater precision (1139, positive predictive value: 63%; 95% confidence interval [CI]: 54%-71%) compared with the EHR search (693, positive predictive value: 40%; 95% CI: 39%-42%). A combined AI-EHR approach identified 604 eligible patients with a positive predictive value of 86% (95% CI: 79%-92%). Intraclass correlation of GA area segmented on FAF versus AI-segmented area on OCT was 0.77 (95% CI: 0.68-0.84) for cases meeting trial criteria. The AI also adjusts to the distinct imaging criteria from several clinical trials, generating tailored shortlists ranging from 438 to 1817 patients. Conclusions: This study demonstrates the potential for AI in facilitating automated prescreening for clinical trials in GA, enabling site feasibility assessments, data-driven protocol design, and cost reduction. Once treatments are available, similar AI systems could also be used to identify individuals who may benefit from treatment. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.