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.

Predictors of True Scaphoid Fractures in Children.

BACKGROUND: The scaphoid is the most commonly fractured carpal bone in children. True scaphoid fractures have proven to be difficult to diagnose, as they may not be apparent on initial imaging. Children with clinical suspicion of a scaphoid fracture may be treated with continued immobilization, even in the absence of radiographic evidence of a fracture. The purpose of this study is to identify predictors of true scaphoid fractures in children to help guide management. METHODS: This study is a retrospective cohort study of children presenting to a tertiary pediatric hospital with hand or wrist injuries. Patients were grouped based on the presence of a true scaphoid fractures (confirmed on imaging) or those with clinical suspicion of a scaphoid fracture alone (no radiographic evidence of fracture). Demographic and clinical characteristics were compared with univariate and multivariate statistics to identify fracture predictors. RESULTS: One hundred and thirty patients were included in the study: 57 in the true scaphoid fracture group and 73 in the clinical scaphoid fracture group. Patients with a true scaphoid fracture were older than those with a clinical scaphoid fracture (median age [interquartile range], 14.2 [13.0-15.4] vs 12.9 [11.9-14.4], P = .01). Men were more likely to sustain a true scaphoid fracture (65.0% vs 35.0%, P = .01). Older age and male sex were shown to be independent predictors of true scaphoid fractures (odds ratio [95% confidence interval], 1.25 [1.03-1.50] and 2.93 [1.39-6.17], respectively). CONCLUSIONS: In the pediatric population, older age and male children may be at increased risk of true scaphoid fractures. This may help guide decisions surrounding further imaging and treatment.

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.

Assessing the medical reasoning skills of GPT-4 in complex ophthalmology cases.

BACKGROUND/AIMS: This study assesses the proficiency of Generative Pre-trained Transformer (GPT)-4 in answering questions about complex clinical ophthalmology cases. METHODS: We tested GPT-4 on 422 Journal of the American Medical Association Ophthalmology Clinical Challenges, and prompted the model to determine the diagnosis (open-ended question) and identify the next-step (multiple-choice question). We generated responses using two zero-shot prompting strategies, including zero-shot plan-and-solve+ (PS+), to improve the reasoning of the model. We compared the best-performing model to human graders in a benchmarking effort. RESULTS: Using PS+ prompting, GPT-4 achieved mean accuracies of 48.0% (95% CI (43.1% to 52.9%)) and 63.0% (95% CI (58.2% to 67.6%)) in diagnosis and next step, respectively. Next-step accuracy did not significantly differ by subspecialty (p=0.44). However, diagnostic accuracy in pathology and tumours was significantly higher than in uveitis (p=0.027). When the diagnosis was accurate, 75.2% (95% CI (68.6% to 80.9%)) of the next steps were correct. Conversely, when the diagnosis was incorrect, 50.2% (95% CI (43.8% to 56.6%)) of the next steps were accurate. The next step was three times more likely to be accurate when the initial diagnosis was correct (p<0.001). No significant differences were observed in diagnostic accuracy and decision-making between board-certified ophthalmologists and GPT-4. Among trainees, senior residents outperformed GPT-4 in diagnostic accuracy (p≤0.001 and 0.049) and in accuracy of next step (p=0.002 and 0.020). CONCLUSION: Improved prompting enhances GPT-4's performance in complex clinical situations, although it does not surpass ophthalmology trainees in our context. Specialised large language models hold promise for future assistance in medical decision-making and diagnosis.

Long-term outcomes of iris-sutured subluxated intraocular lenses.

PURPOSE: This study evaluated the long-term outcomes of managing posterior chamber intra-ocular lens (IOL) (PCIOL) subluxation through pars plana vitrectomy (PPV) with IOL iris suturing. SETTINGS AND DESIGN: Retrospective chart review. METHODS: Patients who underwent PPV with iris-sutured IOL (IS-IOL) for IOL subluxation between January 2008 and April 2021 at a tertiary center with a minimum of 6 months of follow-up were included. The patients were divided into two groups: those who had prior PPV and those who had not undergone the procedure. RESULTS: A total of 54 patients underwent iris suturing of a subluxated IOL. Among them, 36 (66%) had previously undergone PPV, while 18 patients (33%) had not. The etiology of PCIOL subluxation was uncertain in 20 (37.0%), prior PPV in 17 (32%), and following complicated cataract surgery in 11 (20%) cases. The mean time between original IOL insertion and IS-IOL was 6.1 ± 7.0 years. The mean follow-up duration was 46.8 ± 39.7 months. The mean post-operative best corrected visual acuity (BCVA) was logMAR 0.43 ± 0.52 at final follow-up, a significant improvement from pre-operative BCVA. Vision was significantly better in the group with no prior PPV (logMAR 0.54 ± 0.59 vs. 0.21 ± 0.23 at final follow-up, P = 0.026). At final follow-up, 34 (63%) eyes had BCVA of 20/40 or better. The most common complication was cystoid macular edema, attributed to the IS-IOL in 13 (21.4%) eyes, 11 (68.6%) of which resolved or improved. CONCLUSIONS: The management of posterior chamber IOL subluxations with PPV and iris suturing of the subluxated IOL is a safe technique that provides excellent long-term visual outcomes.

Development and deployment of a smartphone application for diagnosing trachoma: Leveraging code-free deep learning and edge artificial intelligence.

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 diagnosing trachoma from field-collected conjunctival images and compares it to expert-designed DL models. METHODS: Two ophthalmology trainees without coding experience carried out AutoML model design using a publicly available image data set of field-collected conjunctival images (1656 labeled images). We designed two binary models to differentiate trachomatous inflammation-follicular (TF) and trachomatous inflammation-intense (TI) from normal. We then integrated an Edge model into an Android application using Google Firebase to make offline diagnoses. RESULTS: The AutoML models showed high diagnostic properties in the classification tasks that were comparable or better than the bespoke DL models. The TF model had an area under the precision-recall curve (AuPRC) of 0.945, sensitivity of 87%, specificity of 88%, and accuracy of 88%. The TI model had an AuPRC of 0.975, sensitivity of 95%, specificity of 92%, and accuracy of 93%. Through the Android app and using an external dataset, the AutoML model had an AuPRC of 0.875, sensitivity of 83%, specificity of 81%, and accuracy of 83%. CONCLUSION: AutoML models created by ophthalmologists without coding experience were comparable or better than bespoke models trained on the same dataset. Using AutoML to create models and edge computing to deploy them into smartphone-based apps, our approach brings the whole spectrum of DL model design into the hands of clinicians. This approach has the potential to democratize access to artificial intelligence.

The role of optical coherence tomography angiography in dome-shaped maculopathy.

PURPOSE: To demonstrate the role of optical coherence tomography angiography (OCT-A) in the management of dome-shaped maculopathy (DSM). METHODS: Retrospective case review. RESULTS: A 52-year-old woman was referred to our retina service for potential bilateral choroidal neovascular membrane (CNVM) and blurry vision bilaterally. Initial spectacle-corrected visual acuity (VA) was 20/30-2 in the right eye (RE) and 20/30+2 in the left eye (LE). DSM was diagnosed on OCT. In both eyes, OCT B-scan passing through the fovea showed shallow, irregular RPE elevation (SIRE) suspicious of occult (type 1) CNVM. The outer retina and choriocapillaris angiograms showed a zone of nonexudative CNVM in the RE and exudative CNVM in the LE. Given the persistent SRF with CNVM in the LE, we elected to perform intravitreal injections of ranibizumab 0.5 mg on a treat and extend regimen. Upon the most recent follow-up, the best corrected VA improved to 20/20 in the LE with no persisting SRF. CONCLUSION: We present a case where assessing disease progression, the development of CNVM and evaluating the efficiency of therapies were realized through the application of novel OCT-A technology. This diagnostic tool may be used to guide clinicians in their management of DSM, as demonstrated through our experience. OCT-A can also make it possible to visualize nonexudative CNVM lesions that may be missed on traditional imaging assessments.

Paracentral Acute Middle Maculopathy in Migraines with Aura.

Paracentral acute middle maculopathy (PAMM) has recently been described following episodes of migraine. In this report, we present a case of PAMM and describe the role of en face optical coherence tomography (OCT). A 75-year-old woman presented with subjective vision loss over a 2-week period in the right eye. She was known for migraines with aura that presented with progressive spreading of positive and negative visual phenomena which usually resolved in under an hour. Her recent migraine episode was "atypical," as it lasted 3 days. She also experienced a monocular central scotoma with "black spots and jagged, zig-zag edges." The positive auras resolved spontaneously, whereas the central scotoma persisted. Spectral domain OCT showed an area of perifoveal hyperreflectivity from the inner plexiform to the outer plexiform layers consistent with PAMM. The mid-retina en face OCT and OCT angiography demonstrated an ovoid focal patch of hyperreflectivity with flow interruption, characteristic of globular PAMM. We diagnosed her with migraines with aura and presumed retinal vasospasm, complicated by retinal ischemia in the form of globular PAMM. Acute retinal ischemia, which may require urgent neurovascular workup and giant cell arteritis evaluation, must be considered in patients with migraines alongside persistent visual changes. Diagnosing PAMM requires a high level of suspicion since it can present without significant changes in visual acuity, visual fields, and fundus photographs. With the inclusion of en face OCT in the clinicians' diagnostic armamentarium, the slightest signs of retinal ischemic changes, such as PAMM, become evident.

Capabilities of GPT-4 in ophthalmology: an analysis of model entropy and progress towards human-level medical question answering.

BACKGROUND: Evidence on the performance of Generative Pre-trained Transformer 4 (GPT-4), a large language model (LLM), in the ophthalmology question-answering domain is needed. METHODS: We tested GPT-4 on two 260-question multiple choice question sets from the Basic and Clinical Science Course (BCSC) Self-Assessment Program and the OphthoQuestions question banks. We compared the accuracy of GPT-4 models with varying temperatures (creativity setting) and evaluated their responses in a subset of questions. We also compared the best-performing GPT-4 model to GPT-3.5 and to historical human performance. RESULTS: GPT-4-0.3 (GPT-4 with a temperature of 0.3) achieved the highest accuracy among GPT-4 models, with 75.8% on the BCSC set and 70.0% on the OphthoQuestions set. The combined accuracy was 72.9%, which represents an 18.3% raw improvement in accuracy compared with GPT-3.5 (p<0.001). Human graders preferred responses from models with a temperature higher than 0 (more creative). Exam section, question difficulty and cognitive level were all predictive of GPT-4-0.3 answer accuracy. GPT-4-0.3's performance was numerically superior to human performance on the BCSC (75.8% vs 73.3%) and OphthoQuestions (70.0% vs 63.0%), but the difference was not statistically significant (p=0.55 and p=0.09). CONCLUSION: GPT-4, an LLM trained on non-ophthalmology-specific data, performs significantly better than its predecessor on simulated ophthalmology board-style exams. Remarkably, its performance tended to be superior to historical human performance, but that difference was not statistically significant in our study.

Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of Its Successes and Shortcomings.

Purpose: Foundation models are a novel type of artificial intelligence algorithms, in which models are pretrained at scale on unannotated data and fine-tuned for a myriad of downstream tasks, such as generating text. This study assessed the accuracy of ChatGPT, a large language model (LLM), in the ophthalmology question-answering space. Design: Evaluation of diagnostic test or technology. Participants: ChatGPT is a publicly available LLM. Methods: We tested 2 versions of ChatGPT (January 9 "legacy" and ChatGPT Plus) on 2 popular multiple choice question banks commonly used to prepare for the high-stakes Ophthalmic Knowledge Assessment Program (OKAP) examination. We generated two 260-question simulated exams from the Basic and Clinical Science Course (BCSC) Self-Assessment Program and the OphthoQuestions online question bank. We carried out logistic regression to determine the effect of the examination section, cognitive level, and difficulty index on answer accuracy. We also performed a post hoc analysis using Tukey's test to decide if there were meaningful differences between the tested subspecialties. Main Outcome Measures: We reported the accuracy of ChatGPT for each examination section in percentage correct by comparing ChatGPT's outputs with the answer key provided by the question banks. We presented logistic regression results with a likelihood ratio (LR) chi-square. We considered differences between examination sections statistically significant at a P value of < 0.05. Results: The legacy model achieved 55.8% accuracy on the BCSC set and 42.7% on the OphthoQuestions set. With ChatGPT Plus, accuracy increased to 59.4% ± 0.6% and 49.2% ± 1.0%, respectively. Accuracy improved with easier questions when controlling for the examination section and cognitive level. Logistic regression analysis of the legacy model showed that the examination section (LR, 27.57; P = 0.006) followed by question difficulty (LR, 24.05; P < 0.001) were most predictive of ChatGPT's answer accuracy. Although the legacy model performed best in general medicine and worst in neuro-ophthalmology (P < 0.001) and ocular pathology (P = 0.029), similar post hoc findings were not seen with ChatGPT Plus, suggesting more consistent results across examination sections. Conclusion: ChatGPT has encouraging performance on a simulated OKAP examination. Specializing LLMs through domain-specific pretraining may be necessary to improve their performance in ophthalmic subspecialties. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Review of clinical trials addressing the Boston Keratoprosthesis.

OBJECTIVE: The Boston Keratoprosthesis (KPro) has gained recognition as an alternative for patients with severe corneal disease and a poor probability of success with traditional penetrating keratoplasty. This review summarizes the knowledge clinical trials have brought to KPro and discusses ongoing trials. DESIGN: Systematic review. METHODS: A literature review across PubMed, Ovid MEDLINE, Cochrane CENTRAL, and ClinicalTrials.gov was performed to identify relevant published clinical trials reporting on the KPro from all years up until September 2021. All published trials were included. RESULTS: There are 6 published and 6 ongoing clinical trials studying the Boston KPro. The number of patients included per trial ranged from 8 to 37. The average age of patients included per trial ranged from 39 to 62 years. Patients were followed for an average of 36.3 ± 41.8 months. Fifty percent (3 of 6) of KPro clinical trials were randomized. Indication for KPro was reported in 67% of trials (4 of 6), with primary KPro accounting for 22% of unique eyes (13 of 58) and KPro after corneal graft failure accounting for 41% of unique eyes (24 of 58), when reported. Using version 2 of the Cochrane risk-of-bias tool for randomized trials (RoB 2) to assess quality and risk of bias, 50% of trials (3 of 6) had a low risk of bias, 33% (2 of 6) had some bias concerns, and 17% (1 of 6) had a high risk of bias. CONCLUSIONS: There are few clinical trials published and underway on the Boston KPro, and none directly compare KPro outcomes with repeat corneal transplantation. There is a need for long-term clinical trials on the KPro to provide quality evidence for clinical decision making.

Acute retinal ischaemia associated with paracentral acute middle maculopathy detected on multimodal imaging: a premonitory sign of severe carotid occlusive disease.

A man in his 60s presented with a subacute paracentral scotoma and preserved visual acuity in the left eye. He was found to have a very subtle area of deep retinal whitening at the macula and multiple retinal cholesterol emboli. Optical coherence tomography (OCT) with En face imaging revealed globular paracentral acute middle maculopathy (PAMM). A diagnosis of PAMM associated with branch artery occlusion was made and the patient was immediately transferred to the nearest stroke centre. Investigations revealed severe carotid occlusive disease for which the patient underwent carotid endarterectomy. Paracentral scotomas in patients with little clinical findings on fundus examination should raise the suspicion for PAMM, which is easily identifiable on OCT. Eye care professionals must recognise PAMM as a possible sign of acute retinal arterial ischaemia-an ocular and systemic emergency that requires immediate referral to specialised stroke centres.

COVID-19 and the Rationale for Primary Selective Laser Trabeculoplasty and Diode Laser Transscleral Cyclophotocoagulation in Africa.

The recent COVID-19 pandemic has affected ophthalmologists' practices worldwide. Consequent global drug shortages and the limitations of medical glaucoma treatments in sub-Saharan Africa have highlighted the need for innovation in global ophthalmology to provide accessible, affordable, and effective glaucoma care. The role of lasers rather than medications for glaucoma patients in developing nations is emerging. Since lasers are easier to master than glaucoma surgery, it is pertinent to discuss the primary use of lasers in treating glaucoma in such nations. In particular, selective laser trabeculoplasty and diode laser transscleral cyclophotocoagulation seem to present a promising future for the treatment of glaucoma in Africa. In this report, we provide an evidence-based discussion exploring the emerging role of lasers in Africa.

Revisiting the Utility of Dilated Fundus Exams in Patients with Neovascular Age-Related Macular Degeneration Receiving Regular Intravitreal Injections.

Patients receiving regular anti-vascular endothelial growth factor (anti-VEGF) intravitreal injections for neovascular age-related macular degeneration (nAMD) routinely undergo dilated fundus examination (DFE) at each visit. In this paper, we review the current evidence on the utility of DFE in guiding treatment of established patients with nAMD and discuss novel treatment algorithms that defer DFE assessments with the advent of optical coherence tomography (OCT). We also debate on the value of DFE in the current sanitary context of COVID-19 and highlight important clinical scenarios where it must be performed.

Staged management of cardiac disease and concomitant early lung cancer: a 20-year single-center experience.

OBJECTIVES: The association of unstable heart disease and resectable lung cancer is rare. The impacts of staged management, cardiac surgery with cardiopulmonary bypass (CPB) versus angioplasty, on long-term survival and cancer recurrence remain debated. We report our experience using staged management. METHODS: From 1997 to 2016, 107 patients were treated at the Quebec Heart and Lung Institute: 72 underwent cardiac surgery with CPB (group 1), 35 were treated with angioplasty (group 2), followed by oncological pulmonary resection. RESULTS: Two postoperative deaths (3%) and 1 ischaemic heart complication (1%) were reported in group 1. One death (3%) was reported in group 2. Two-year overall survival was 82% (59/72) in group 1 and 80% (28/35) in group 2; 5-year overall survival was 62% (33/53) in group 1 and 63% (19/30) in group 2. Two-year disease-free survival in group 1 was 79% (57/72) and 77% (27/35) in group 2; 5-year disease-free survival was 58% (31/53) in group 1 and 60% (18/30) in group 2. The independent risk factors for death after thoracic surgery were transfusions (P = 0.004) and grade ≥3 complications (P = 0.034). Independent risk factors for recurrence included the cancer stage (P < 0.001) and, paradoxically, a shorter delay between cardiac and lung procedures (P = 0.031). CONCLUSIONS: When a staged management remains feasible after cardiac procedure, oncological outcomes of patients with cardiopathy and lung cancer are satisfactory. CPB does not seem to be deleterious. The delay between procedures should intuitively be as small as possible but not at the expense of good recovery after the cardiac procedure.

Systematic review of rigid and flexible esophagoscopy for pediatric esophageal foreign bodies.

BACKGROUND: Esophageal foreign body (EFB) is a common presentation in pediatric hospitals. Rigid and flexible esophagoscopy are both primary modalities used for EFB removal. By systematically reviewing the literature, we sought to assess success and complication rates of both rigid and flexible esophagoscopy in pediatric EFB retrieval. METHODS: A systematic search of the literature was performed in MEDLINE, Embase, Cochrane Database of Systematic Reviews, Web of Science, CINAHL. Two authors independently reviewed 74 abstracts and included studies that documented success rates of flexible and rigid esophagoscopy for EFB retrieval. The certainty and quality of the overall body of evidence was evaluated in accordance with the Grades of Recommendation, Assessment, Development and Evaluation approach. RESULTS: Five retrospective chart reviews published between 1993 and 2016 identified 955 patients with a mean age of 4.2 (range 3.2-5.3 years). Foreign bodies were localized to the upper esophagus in 69.6%, middle esophagus in 13.0% and lower esophagus in 11.5%. Coins (82.1%) and food boluses (8.5%) comprised the majority of EFB. The success rate of foreign body retrieval was 95.4% with rigid esophagoscopy and 97.4% with flexible esophagoscopy. Complication rates were 2.4% for rigid esophagoscopy and 3.4% for flexible esophagoscopy. Rates of successful foreign body retrieval (odds ratio [OR] = 1.9 [95% CI 0.9-3.8; p = 0.07]) and complications (OR = 0.9 [95% CI 0.3-2.3; p = 0.79]) were not significantly different across modalities. There were no mortalities in any of the studies analyzed. CONCLUSION: Flexible and rigid esophagoscopy are equally safe and effective for the retrieval of EFB in children. Otolaryngologists, gastroenterologists, and pediatric general surgeons can be consulted for foreign body retrieval depending on institutional policies and resource availability.