Table 1 Demographics and clinical characteristics of the training group.

From: Deep learning approaches to predict 10-2 visual field from wide-field swept-source optical coherence tomography en face images in glaucoma

Number of eyes (patients)

3025 (1612)

Age, years

57.28 ± 15.26

Sex, Female

840 (52.11)

Best corrected visual acuity (logMAR)

0.15 ± 0.19

Intraocular pressure at test, mmHg

16.24 ± 4.37

Spherical equivalent, diopter

 − 1.78 ± 3.15

Axial length, mm

24.42 ± 1.68

Central corneal thickness, μm

543.00 ± 40.55

Lens status, Phakia

2392 (79.07)

Diabetes mellitus

234 (14.52)

Hypertension

452 (28.04)

Diagnosis

Normal

95

Glaucoma suspect

548

Ocular hypertension

169

Primary open-angle glaucoma

1640

Primary angle-closure glaucoma

216

Pseudoexfoliation glaucoma

164

Other secondary glaucoma

193

10-2 visual field

MD, dB

 − 5.08 ± 6.35

PSD, dB

4.32 ± 4.55

SS-OCT

OCT image quality value

58.48 ± 5.86

mGC/IPLT, μm

Average

61.88 ± 9.12

Superotemporal

62.15 ± 10.37

Superior

62.40 ± 9.65

Superonasal

67.52 ± 10.08

Inferonasal

63.83 ± 10.22

Inferior

56.53 ± 9.64

Inferotemporal

58.82 ± 12.25

cpRNFLT, μm

Average

82.53 ± 21.13

Temporal

72.18 ± 18.72

Superior

99.16 ± 30.39

Nasal

63.38 ± 17.15

Inferior

95.37 ± 35.12

  1. Values are presented as mean ± standard deviation (range) or number (%) unless otherwise indicated. logMAR  logarithm of the minimum angle of resolution; MD  mean deviation; PSD  pattern standard deviation; SS-OCT  swept-source optical coherence tomography; mGC/IPLT  macular ganglion cell/inner plexiform layer thickness; cpRNFLT  circumpapillary retinal nerve fiber layer thickness.
Back to article page