A validated web-application (GFDC) for automatic classification of glaucomatous visual field defects using Hodapp-Parrish-Anderson criteria

Subjectivity and ambiguity of visual field classification limits the  accuracy and reliability of glaucoma diagnosis, prognostication, and  management decisions. Standardised rules for classifying glaucomatous  visual field defects exist, but these are labour-intensive and therefore  impractical for day-to-day clinical work. Here a web-application,  Glaucoma Field Defect Classifier (GFDC), for automatic application of  Hodapp-Parrish-Anderson, is presented and validated in a cross-sectional  study. GFDC exhibits perfect accuracy in classifying mild, moderate,  and severe glaucomatous field defects. GFDC may thereby improve the  accuracy and fairness of clinical decision-making in glaucoma. The  application and its source code are freely hosted online for clinicians  and researchers to use with glaucoma patients.