Predicting Choroidal Nevus Transformation to Melanoma Using Machine Learning.

Purpose: To develop and validate machine learning (ML) models to predict choroidal nevus transformation to melanoma based on multimodal imaging at initial presentation. Design: Retrospective multicenter study. Participants: Patients diagnosed with choroidal nevus on the Ocular Oncology Service at Wills Eye Hospital (2007-2017) or Mayo Clinic Rochester (2015-2023). Methods: Multimodal imaging was obtained, including fundus photography, fundus autofluorescence, spectral domain OCT, and B-scan ultrasonography. Machine learning models were created (XGBoost, LGBM, Random Forest, Extra Tree) and optimized for area under receiver operating characteristic curve (AUROC). The Wills Eye Hospital cohort was used for training and testing (80% training-20% testing) with fivefold cross validation. The Mayo Clinic cohort provided external validation. Model performance was characterized by AUROC and area under precision-recall curve (AUPRC). Models were interrogated using SHapley Additive exPlanations (SHAP) to identify the features most predictive of conversion from nevus to melanoma. Differences in AUROC and AUPRC between models were tested using 10 000 bootstrap samples with replacement and results. Main Outcome Measures: Area under receiver operating curve and AUPRC for each ML model. Results: There were 2870 nevi included in the study, with conversion to melanoma confirmed in 128 cases. Simple AI Nevus Transformation System (SAINTS; XGBoost) was the top-performing model in the test cohort [pooled AUROC 0.864 (95% confidence interval (CI): 0.864-0.865), pooled AUPRC 0.244 (95% CI: 0.243-0.246)] and in the external validation cohort [pooled AUROC 0.931 (95% CI: 0.930-0.931), pooled AUPRC 0.533 (95% CI: 0.531-0.535)]. Other models also had good discriminative performance: LGBM (test set pooled AUROC 0.831, validation set pooled AUROC 0.815), Random Forest (test set pooled AUROC 0.812, validation set pooled AUROC 0.866), and Extra Tree (test set pooled AUROC 0.826, validation set pooled AUROC 0.915). A model including only nevi with at least 5 years of follow-up demonstrated the best performance in AUPRC (test: pooled 0.592 (95% CI: 0.590-0.594); validation: pooled 0.656 [95% CI: 0.655-0.657]). The top 5 features in SAINTS by SHAP values were: tumor thickness, largest tumor basal diameter, tumor shape, distance to optic nerve, and subretinal fluid extent. Conclusions: We demonstrate accuracy and generalizability of a ML model for predicting choroidal nevus transformation to melanoma based on multimodal imaging. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Incisional choroidal surgery.

The choroid is a thin layer of highly vascular uveal tissue enclosed externally by sclera and internally by neurosensory retinal tissue. The choroid is a "middle layer" ocular tissue with anatomically challenging surgical access. The primary functional role of the choroid is to provide rapid, oxygenated, and nutrient-rich blood flow to both the highly metabolic retinal pigment epithelium and outer retina (i.e. photoreceptors) while simultaneously removing waste products. Historically, incisional choroidal surgery (ICS) has involved tumor biopsy or excision, removal of choroidal neovascular complex or autologous choroidal translocations; however, ICS also holds unique potential for novel and innovative approaches to address macular pathology. Using large-animal surgical studies, researchers have explored ICS with the objective of finding safer and more effective techniques to reduce surgical risks such as bleeding, tissue contraction, and scar tissue formation. We explore the relevant anatomy and embryology, existing surgical techniques, discuss the implications for retinal drug delivery, define ICS guiding principles, and offer a rationale for implementation of ICS into a vitreoretinal surgical practice. We also identify other future challenges and anticipate future innovations that will advance ICS.

Vision of the future: large language models in ophthalmology.

PURPOSE OF REVIEW: Large language models (LLMs) are rapidly entering the landscape of medicine in areas from patient interaction to clinical decision-making. This review discusses the evolving role of LLMs in ophthalmology, focusing on their current applications and future potential in enhancing ophthalmic care. RECENT FINDINGS: LLMs in ophthalmology have demonstrated potential in improving patient communication and aiding preliminary diagnostics because of their ability to process complex language and generate human-like domain-specific interactions. However, some studies have shown potential for harm and there have been no prospective real-world studies evaluating the safety and efficacy of LLMs in practice. SUMMARY: While current applications are largely theoretical and require rigorous safety testing before implementation, LLMs exhibit promise in augmenting patient care quality and efficiency. Challenges such as data privacy and user acceptance must be overcome before LLMs can be fully integrated into clinical practice.

Appropriateness of Ophthalmology Recommendations From an Online Chat-Based Artificial Intelligence Model.

Objective: To determine the appropriateness of ophthalmology recommendations from an online chat-based artificial intelligence model to ophthalmology questions. Patients and Methods: Cross-sectional qualitative study from April 1, 2023, to April 30, 2023. A total of 192 questions were generated spanning all ophthalmic subspecialties. Each question was posed to a large language model (LLM) 3 times. The responses were graded by appropriate subspecialists as appropriate, inappropriate, or unreliable in 2 grading contexts. The first grading context was if the information was presented on a patient information site. The second was an LLM-generated draft response to patient queries sent by the electronic medical record (EMR). Appropriate was defined as accurate and specific enough to serve as a surrogate for physician-approved information. Main outcome measure was percentage of appropriate responses per subspecialty. Results: For patient information site-related questions, the LLM provided an overall average of 79% appropriate responses. Variable rates of average appropriateness were observed across ophthalmic subspecialties for patient information site information ranging from 56% to 100%: cataract or refractive (92%), cornea (56%), glaucoma (72%), neuro-ophthalmology (67%), oculoplastic or orbital surgery (80%), ocular oncology (100%), pediatrics (89%), vitreoretinal diseases (86%), and uveitis (65%). For draft responses to patient questions via EMR, the LLM provided an overall average of 74% appropriate responses and varied by subspecialty: cataract or refractive (85%), cornea (54%), glaucoma (77%), neuro-ophthalmology (63%), oculoplastic or orbital surgery (62%), ocular oncology (90%), pediatrics (94%), vitreoretinal diseases (88%), and uveitis (55%). Stratifying grades across health information categories (disease and condition, risk and prevention, surgery-related, and treatment and management) showed notable but insignificant variations, with disease and condition often rated highest (72% and 69%) for appropriateness and surgery-related (55% and 51%) lowest, in both contexts. Conclusion: This LLM reported mostly appropriate responses across multiple ophthalmology subspecialties in the context of both patient information sites and EMR-related responses to patient questions. Current LLM offerings require optimization and improvement before widespread clinical use.

Trends in Myopia and High Myopia from 1966 to 2019 in Olmsted County, Minnesota.

PURPOSE: To investigate the prevalence of myopia and high myopia in Olmsted County, Minnesota, from 1966 to 2019. DESIGN: Retrospective, cross-sectional, trend study. METHODS: Manifest refractions or lens prescription were converted to spherical equivalent (SE) to estimate the prevalence of adult myopia and high myopia. Age, sex, race, and visual acuity were recorded. Subjects with an SE of -0.5 diopters (D) or less were considered to have myopia; those with an SE of -6.0 D or less were considered to have high myopia. Exclusion criteria included visually significant cataract, pseudophakia, prior refractive surgery, or age less than 18 years. RESULTS: Among 81,706 sampled subjects, the myopia prevalence increased from 33.9% (95% CI, 31.1-36.8) in the 1960s to 57.1% (95% CI, 56.6-57.6) in the 2010s (P < .001). The high myopia prevalence increased from 2.8% (95% CI, 1.95-3.98) in the 1960s to 8.3% (95% CI, 8.08-8.62) in the 2010s (P < .001). Both male (32.0%-55.1%, P < .001) and female (40.6%-58.5%, P < .001) subjects experienced increasing myopia prevalence from the 1960s to the 2010s; both male (2.6%-7.4%, P < .001) and female (3.4%-9.1%, P < .001) subjects also had higher high myopia prevalence rates from the 1960s through the 2010s. Increasing myopia and high myopia prevalence was detected by decade in nearly all age groups (excluding 18- to 24-year-old high myopia subjects). White and Asian subjects had the highest myopia prevalence, whereas Black subjects had the lowest. From the 2000s to the 2010s, White (53.3%-57.0%, P < .001) and Black (41.0%-47.0%, P = .001) subjects had significant increases in myopia prevalence. The mean SE decreased from the 1960s (-0.42 D; 95% CI, -0.59 to +2.49) to the 2010s (-1.85 D; 95% CI, -1.88 to +2.96) (P < .001). CONCLUSIONS: From 1966 to 2019 in Olmsted County, Minnesota, there was a 68% and 199% increase in myopia and high myopia prevalence, respectively.

Obstructive Sleep Apnea Associated With Increased Failure Rate of Ptosis Repair.

PURPOSE: This study investigates how Obstructive sleep apnea (OSA) affects the outcomes of ptosis repair. We hypothesized that patients with OSA have an increased rate of reoperation after ptosis repair. METHODS: This retrospective cohort study included patients age >18 from the Mayo Clinic who underwent ptosis repair by levator advancement or Müller muscle-conjunctiva resection between 2018 and 2021. Outcomes were measured at 1 to 3 months of follow-up with surgical failure defined as asymmetry or unsatisfactory eyelid height requiring revision surgery within 1 year. RESULTS: A total of 577 patients met the inclusion criteria. There was a statistically significant difference in surgical failure between patients with OSA and those without (20.5% vs. 13.1%, p = 0.02). Patients with OSA showed a statistically significant difference in risk of revision by a factor of 1.70 (95% CI: 1.06-2.07). Revisions were attributed to unsatisfactory eyelid height in 72.6% of patients and eyelid asymmetry in 21.1%. All patients who had revision surgery had satisfactory outcomes. On logistic regression analysis, when adjusting for age and sex, OSA was significantly associated with ptosis revision ( p = 0.007). CONCLUSIONS: OSA increases risk of surgical failure and need for revision surgery in patients undergoing blepharoptosis repair but is not a sole risk factor.

Clinical Characteristics and Outcomes of Endophthalmitis Before and During the COVID-19 Pandemic.

Purpose: To evaluate the clinical characteristics and visual acuity outcomes of patients who presented with endophthalmitis prior to and during the coronavirus disease 2019 (COVID-19) pandemic. Methods: This multicenter retrospective case series with historical controls included consecutive patients presenting with any form of endophthalmitis from March 1, 2019 to September 1, 2019 (pre-COVID-19) and from March 1, 2020 to September 1, 2020 (COVID-19) at Mayo Clinic Rochester (MCR), Health System (MCHS), Arizona (MCA), and Florida (MCF) sites. Cases were divided into "pre-COVID-19" versus "COVID-19" groups depending on when they first presented with endophthalmitis. Results: Twenty-eight cases of endophthalmitis presented to all Mayo Clinic sites during the study period. Of these, 10 patients presented during the first six months of the COVID-19 pandemic. During the same six-month period the year prior, 18 patients presented with endophthalmitis. Endophthalmitis etiology (post-injection, post-cataract extraction, post-glaucoma filtering surgery, post-pars plana vitrectomy, endogenous, and others) was similar between both groups (P = 0.34), as was post-injection endophthalmitis rate (P = 0.69), days to presentation (P = 0.07), initial management (P = 0.11), culture-positivity rate (P = 0.70), and need for subsequent pars plana vitrectomy (P = 1). Visual acuity outcomes were similar between both groups at six months, however, the mean LogMAR visual acuity at presentation was worse in the COVID-19 group compared to the pre-COVID-19 group (2.44 vs 1.82; P = 0.026). Conclusion: Clinical characteristics and the post-injection endophthalmitis rate were similar during both periods, however, patients presented with worse vision during the pandemic suggesting that the pandemic may have contributed to delayed presentation, regardless, outcomes are still poor.

Trends in Ophthalmology Practice Consolidation: 2015-2022.

PURPOSE: To quantify trends in ophthalmology practice consolidation in the United States. DESIGN: A retrospective cross-sectional study. PARTICIPANTS: Providers in the Centers for Medicare and Medicaid Services (CMS) National Downloadable File with a primary specialty designation of ophthalmology. METHODS: We used the CMS database to determine national practice consolidation trends in ophthalmology on individual physician and group practice levels and analyzed by region, sex, and years spent in practice. We used the Cochran-Armitage test to determine the statistical significance of practice size differences between 2015 and 2022. MAIN OUTCOME MEASURES: Temporal practice size trends for physicians and practices in ophthalmology and regional, sex-specific, and age-related trends. RESULTS: Between 2015 and 2022, the number of ophthalmologists decreased from 17 656 to 17 615 (-0.2%), whereas the number of practices decreased from 7149 to 5890 (-18%). The percentage of ophthalmologists in practices of 1 to 2 members decreased from 35% to 28%, whereas those in groups of 50 or more increased from 7% to 11%. The percentage of practices with 1 to 2 members decreased from 75% to 71%, and those with 50 or more increased from 0.2% to 0.4%. Consolidation trends were significant on individual ophthalmologist (P < 0.001) and group practice (P < 0.001) levels. All regions, sexes, and subgroups of years spent in practice demonstrated consolidation (P < 0.001). The Northeast showed the greatest increase in groups of 50 or more physicians (+7%) between 2015 and 2022. Proportionally fewer female than male ophthalmologists were associated with practice sizes of 1 to 2 members in 2015 (29% and 36%, respectively) and 2022 (23% and 30%, respectively). Proportionally fewer ophthalmologists with 0 to 10 years of experience in practice were associated with practice sizes of 1 to 2 members than those with more than 30 years in practice in 2015 (18% and 48%, respectively) and 2022 (14% and 40%, respectively). CONCLUSIONS: Ophthalmology has undergone practice consolidation from 2015 to 2022. A decrease in the proportion of physicians affiliated with smaller practice sizes seems to have occurred. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Differentiating intradiploic orbital dermoid and epidermoid cysts utilizing clinical features and machine learning.

Purpose: The purpose of this study was to characterize intradiploic dermoid and epidermoid orbital cysts to determine any differences in clinical, radiographic, or surgical features. Methods: A retrospective review was performed of patients presenting with intradiplopic dermoid or epidermoid cysts. Additionally, a complete review of the literature was performed to identify cases of intradiplopic orbital dermoid and epidermoid cysts. Data collected included age, sex, presenting symptoms, location of intradiplopic cyst, ophthalmic findings, treatment, and follow-up. Clinical features of dermoid versus epidermoid cyst were compared. Additionally, machine-learning algorithms were developed to predict histopathology based on clinical features. Results: There were 55 cases of orbital intradiploic cysts, 49 from literature review and six from our cohort. Approximately 31% had dermoid and 69% had epidermoid histopathology. Average age of patients with dermoid cysts was significantly lesser than that of patients with epidermoid cysts (23 vs. 35 years, respectively; P = 0.048). There was no difference between sex predilection, presenting symptoms, radiographic findings, or surgical treatment of dermoids and epidermoids. The majority of patients (64%) underwent craniotomy for surgical removal. Machine-learning algorithms KStar and Neural Network were able to distinguish dermoid from epidermoid with accuracies of 76.3% and 69%, respectively. Conclusion: Orbital intradiploic cysts are more commonly epidermoid in origin. Dermoid cysts presented in younger patients; however, there were no other significant differences in features including ophthalmic or radiographic findings. Despite similar features, machine learning was able to identify dermoid versus epidermoid with good accuracy. Future studies may examine the role of machine learning for clinical guidance as well as new surgical options for intervention.

Ocular Toxicity of Targeted Anticancer Agents.

The proliferation of targeted anticancer agents over the last two decades has revolutionized cancer treatment and improved survival in many previously refractory malignancies. However, many agents are associated with characteristic ophthalmic adverse effects. It is important that ophthalmologists recognize and maintain a high index of suspicion for these side effects in patients on targeted therapy. Most ophthalmic adverse effects can be treated with specific ocular therapy without discontinuation of cancer treatment, although it is important to be aware of the life-threatening and vision-threatening circumstances that would require therapy cessation in conjunction with the patient's oncologist. This review aims to summarize the ophthalmic adverse effects of targeted and hormonal anticancer agents and briefly describe their management.

Diagnostic and prognostic biomarker potential of kallikrein family genes in different cancer types.

PURPOSE: The aim of this study was to compare and contrast the expression of all members of the Kallikrein (KLK) family of genes across 15 cancer types and to evaluate their utility as diagnostic and prognostic biomarkers. RESULTS: Severe alterations were found in the expression of different Kallikrein genes across various cancers. Interestingly, renal clear cell and papillary carcinomas have similar kallikrein expression profiles, whereas, chromophobe renal cell carcinoma has a unique expression profile. Several KLK genes have excellent biomarker potential (AUC > 0.90) for chromophobe renal cell carcinoma (KLK2, KLK3, KLK4, KLK7, KLK15), renal papillary carcinoma (KLK1, KLK6, KLK7), clear cell renal cell carcinoma (KLK1, KLK6), thyroid carcinoma (KLK2, KLK4, KLK13, KLK15) and colon adenocarcinoma (KLK6, KLK7, KLK8, KLK10). Several KLK genes were significantly associated with mortality in clear cell renal cell carcinoma (KLK2: HR = 1.69; KLK4: HR = 1.63; KLK8: HR = 1.71; KLK10: HR = 2.12; KLK11: HR = 1.76; KLK14: HR = 1.86), papillary renal cell carcinoma (KLK6: HR = 3.38, KLK7: HR = 2.50), urothelial bladder carcinoma (KLK5: HR = 1.89, KLK6: HR = 1.71, KLK8: HR = 1.60), and hepatocellular carcinoma (KLK13: HR = 1.75). METHODS: The RNA-seq gene expression data were downloaded from The Cancer Genome Atlas (TCGA). Statistical analyses, including differential expression analysis, receiver operating characteristic curves and survival analysis (Cox proportional-hazards regression models) were performed. CONCLUSIONS: A comprehensive analysis revealed the changes in the expression of different KLK genes associated with specific cancers and highlighted their potential as a diagnostic and prognostic tool.

A Model to Study Thermal Energy Delivery to the Choroid: A Comparison of Surgical Devices.

PURPOSE: We measure and compare surgical devices using an ex vivo, temperature-controlled, choroidal incision model during thermal energy transfer with a high-resolution infrared camera. METHODS: Ex vivo porcine choroidal tissue specimens (n = 516) were isolated and placed on a temperature-regulated (37°C) perfusion platform. We tested the pulsed electron avalanche knife (PEAK), micropulse laser (MpL), continuous laser (CL), and bipolar cautery (BpC) at three energy settings (11 [low], 45 [medium], and 134 [high] mJ/mm). Each device was clamped to a stationary mechanical arm. Movement of tissue specimens beneath the surgical device was achieved using a stepping motor-driven x-y table. An infrared video camera measured orthogonal temperature variation in the surrounding tissue. RESULTS: Increased power resulted in greater lateral thermal spread using all modalities (P < 0.001). Mean (standard deviation) lateral thermal spread at low energy was smallest for the MpL at 0.0 (0.01) mm (P < 0.001), whereas BpC had the least collateral tissue damage at medium and high energies (0.02 [0.08] and 0.34 [0.22] mm, respectively; P < 0.001). Fluidics of the ex vivo system may limit thermal spread. The PEAK had the greatest thermal spread across all energy groups (P < 0.001), with clinically relevant variation between disposable blades. CONCLUSIONS: Our ex vivo model enabled direct comparison of threshold thermal tissue injury across four devices. MpL and BpC showed the least thermal damage. PEAK had a higher variation in energy delivery, but also has the advantage of more effective tissue cutting. TRANSLATIONAL RELEVANCE: Our ex vivo surgical device analysis provides thermal tissue injury predictions for choroidal surgery.