Prognosis prediction in retinal vein occlusion

Abstract

Retinal Vein Occlusion (RVO) is the most common retinal vascular occlusive disorder and is usually associated with visual loss to variable degrees. The most common cause of vision loss in eyes associated with RVO is macular oedema. In many cases, macular oedema (MO) can be successfully treated or managed with intravitreal injections of anti-VEGF agents[1, 2]. However, while many patients with RVO show an excellent response to treatment, others show no or only a partial response. Ophthalmologists at present have no way of predicting who will improve and who will not. This has profound implications, as treatment is costly and an injection into the eyeball carries a risk of blinding the eye in every 1:1000 cases. It would be better for patients and make more efficient use of NHS funds to avoid injections that are not necessary. Following an extensive literature review, it appears that most previous studies have focused on the diagnosis and classification of RVO. This may not be particularly useful since it is usually an easy diagnosis to make clinically[3]. Moreover, in many recent studies, the volumes of data exploited[4, 5]were relatively small, leading to low statistical power in confirming any robust prediction of vision. Additionally, methods involved in informing risk prediction are relatively complex. Therefore, it is unrealistic to expect ophthalmologists to replicate these methodologies for each patient, and such methods may not benefit them in their current state. Alternatively, if each optical coherence tomography (OCT) comes to a clinician with information about risk in terms of biomarkers, this could be more useful. Clinicians widely use OCT images, and they play an essential role in predicting the visual outcome in RVO. The proposed study applies novel methods using EMR and OCT scans for prognosis prediction that can help clinicians in decision-making regarding RVO. The novel proposed methods are investigated which uses feature extraction methods to predict prognosis.