ABSTRACT
Glaucoma is a common condition that relies on careful clinical assessment to diagnose and determine disease progression. There is growing evidence that glaucoma is associated not only with loss of retinal ganglion cells but also with degeneration of cortical and subcortical brain structures associated with vision and eye movements. The effect of glaucoma pathophysiology on eye movements is not well understood. In this review, we examine the evidence surrounding altered eye movements in glaucoma patients compared to healthy controls, with a focus on quantitative eye tracking studies measuring saccades, fixation, and optokinetic nystagmus in a range of visual tasks. The evidence suggests that glaucoma patients have alterations in several eye movement domains. Patients exhibit longer saccade latencies, which worsen with increasing glaucoma severity. Other saccadic abnormalities include lower saccade amplitude and velocity, and difficulty inhibiting reflexive saccades. Fixation is pathologically altered in glaucoma with reduced stability. Optokinetic nystagmus measures have also been shown to be abnormal. Complex visual tasks (eg reading, driving, and navigating obstacles), integrate these eye movements and result in behavioral adaptations. The review concludes with a summary of the evidence and recommendations for future research in this emerging field.
ABSTRACT
IMPORTANCE: Artificial intelligence (AI) algorithms are under development for use in diabetic retinopathy photo screening pathways. To be clinically acceptable, such systems must also be able to classify other fundus abnormalities and clinical features at the point of care. BACKGROUND: We aimed to develop an AI system that can detect several fundus pathologies and report relevant clinical features. DESIGN: Convolutional neural network training with retrospective data set. PARTICIPANTS: Colour fundus photos were obtained from publicly available fundus image databases. METHODS: Images were uploaded to a web-based AI platform for training and validation of AI classifiers. Separate classifiers were created for each fundus pathology and clinical feature. MAIN OUTCOME MEASURES: Accuracy, sensitivity, specificity and area under receiver operating characteristic curve (AUC) for each classifier. RESULTS: We obtained 4435 images from publicly available fundus image databases. AI classifiers were developed for each disease state above. Although statistical performance was limited by the small sample size, average accuracy was 89%, average sensitivity was 75%, average specificity was 89% and average AUC was 0.58. CONCLUSION AND RELEVANCE: This study is a proof-of-concept AI system that could be implemented within a diabetic photo-screening pathway. Performance was promising but not yet at the level that would be required for clinical application. We have shown that it is possible for clinicians to develop AI classifiers with no previous programming or AI knowledge, using standard laptop computers.
