. Author manuscript; available in PMC: 2022 Jul 1.

Published in final edited form as: Ophthalmology. 2020 Dec 25;128(7):1016–1026. doi: 10.1016/j.ophtha.2020.12.020

Table 8.

Number of eyes marked as progressing by the network, non-progressing by the reference algorithm the network was trained on, and progressing by another reference algorithm. The first column indicates models trained on visual field and clinical data with respect to different reference algorithms and the first row indicates how different reference algorithms marked eyes.

	Reference
Model	MD Slope	VFI Slope	PLR
Trained using MD Slope	0	7	10
Trained using VFI Slope	9	0	17
Trained using PLR	12	13	0

MD = Mean Deviation, PLR = Pointwise Linear Regression, VFI = Visual Field Index.