ABSTRACT
Glaucoma is an eye disease characterized by an increase in Intraocular Pressure (IOP) which affects the eye and causes blindness. It is a degenerative disease that damages the nerve fiber layer in the retina of the eye. Its mechanisms are not fully known and there is no fully-effective strategy to prevent visual impairment and blindness. However, if detected early and treatment is carried out at an early stage, it is possible to slow glaucomatous progression and improve the quality of life of possible victims. Despite the great amount of heterogeneous data that has become available for detecting glaucoma, the measures available for early diagnosis are still insufficient, due to the complexity of disease progression and the difficulties in obtaining sufficient measurements. This research aims to develop a framework using visual field data for the detection and prediction of glaucomatous retinal diseases. Classification and regression trees (CART) due its flexibility to continuously check multiple conditions make it a suitable tool to effectively exploit the available data. The processes performed on visual field data include; observation, region extraction and variable preparation, segmentation, classification, etc. Rules set by an ophthalmologist were used as the split criterions which eventually help to detect whether glaucoma was positive or negative.
