Beyond the Index: Association of AI-CO Central Image Area with Central Visual Field Damage in Glaucoma

Abstract

PurposeTo evaluate the associations of the numerical AI-CO center index and visually classified central dark-area extent with Humphrey 10-2 mean deviation (MD).

MethodsThis single-center retrospective study included 320 eyes of 169 patients with AI-CO imaging, broad-field 24-2F or 30-2 testing, and 10-2 testing. Both visual field examinations were performed within 365 days before or after AI-CO imaging. Two ophthalmologists independently classified central dark-area extent into five Levels (0-4). Analyses assessed Spearman correlations, areas under the receiver operating characteristic curve (AUCs), distributions across final central dark-area Levels, and interrater reliability. Patient-cluster bootstrap confidence intervals and a one-eye-per-patient sensitivity analysis addressed inclusion of both eyes.

ResultsAI-CO center correlated with 10-2 MD ({rho}=0.829; 95% CI, 0.773-0.873). AUCs for 10-2 MD below -2, -6, and -12 dB were 0.902, 0.939, and 0.961, respectively. The numbers of eyes in Levels 0-4 were 66, 57, 94, 53, and 50; median 10-2 MD values were -0.59, -1.48, -3.54, -6.24, and -18.15 dB, respectively. Quadratic-weighted kappa was 0.970 (95% CI, 0.958-0.981). Sensitivity analyses yielded broadly similar findings.

ConclusionsThe numerical AI-CO center index and visually classified central dark-area extent were associated with central visual field damage. Assessing the extent of dark regions in the central image alongside the numerical index may provide useful information for interpreting central visual field status from the AI-CO display.

Macular Retinal Ganglion Cell Counts and Central Visual Field Sensitivity in Glaucoma: A Comparison of Logarithmic and Linear Scales
GIAMPAOLO TROIANO, ARIANNA ASADI, STEFANO PIO +3
In Vivo29 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textGeneral medicinePMC
Association of Adduction-Induced Optic Nerve Head Strain with Visual Field Loss Progression in Myopic Normal-Tension Glaucoma: The Wenzhou Glaucoma Progression Study
D.-F. Chen, Z. Xiong, J. Zhang +9
medRxiv15 Oct 2026PreprintPublic domainFull textGeneral medicinemedRxiv
Visual Field and RNFL OCT Testing Among Rural and Urban Residents With Glaucoma
Suyoung Choi, Sean Y. T. Lin, Xiangxue Xiao +2
JAMA Ophthalmology29 Oct 2026Peer-reviewedLicence not statedFull textGeneral medicinePMC
Mitochondrial DNA Copy Number Is Associated With Visual Field Progression in Primary Open-Angle Glaucoma
A. H. Pham, K. M. Kane, D. R. da Costa +1
medRxiv5 Sep 2026PreprintAll rights reservedFull textGeneral medicinemedRxiv
Visual Cortex Activity and Retinal Changes in Primary Open-Angle Glaucoma: An fMRI and OCTA Study
Austėja Judickaitė, Arminas Zizas, Robertas Petrolis +5
Medicina (Kaunas, Lithuania)1 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeX RIS

BibTeX

@misc{kora2026beyond,
  title = {{Beyond the Index: Association of AI-CO Central Image Area with Central Visual Field Damage in Glaucoma}},
  author = {Y. KORA and H. Kora and T. Kora},
  howpublished = {medRxiv},
  year = {2026},
  month = oct,
  doi = {10.64898/2026.10.18.26365818},
  url = {https://www.medrxiv.org/content/10.64898/2026.10.18.26365818v1},
  note = {CC BY-NC-ND},
}

RIS

TY  - UNPB
TI  - Beyond the Index: Association of AI-CO Central Image Area with Central Visual Field Damage in Glaucoma
AU  - Y. KORA
AU  - H. Kora
AU  - T. Kora
PY  - 2026
DA  - 2026/10/18
PB  - medRxiv
DO  - 10.64898/2026.10.18.26365818
UR  - https://www.medrxiv.org/content/10.64898/2026.10.18.26365818v1
AB  - PurposeTo evaluate the associations of the numerical AI-CO center index and visually classified central dark-area extent with Humphrey 10-2 mean deviation (MD).  MethodsThis single-center retrospective study included 320 eyes of 169 patients with AI-CO imaging, broad-field 24-2F or 30-2 testing, and 10-2 testing. Both visual field examinations were performed within 365 days before or after AI-CO imaging. Two ophthalmologists independently classified central dark-area extent into five Levels (0-4). Analyses assessed Spearman correlations, areas under the receiver operating characteristic curve (AUCs), distributions across final central dark-area Levels, and interrater reliability. Patient-cluster bootstrap confidence intervals and a one-eye-per-patient sensitivity analysis addressed inclusion of both eyes.  ResultsAI-CO center correlated with 10-2 MD ({rho}=0.829; 95% CI, 0.773-0.873). AUCs for 10-2 MD below -2, -6, and -12 dB were 0.902, 0.939, and 0.961, respectively. The numbers of eyes in Levels 0-4 were 66, 57, 94, 53, and 50; median 10-2 MD values were -0.59, -1.48, -3.54, -6.24, and -18.15 dB, respectively. Quadratic-weighted kappa was 0.970 (95% CI, 0.958-0.981). Sensitivity analyses yielded broadly similar findings.  ConclusionsThe numerical AI-CO center index and visually classified central dark-area extent were associated with central visual field damage. Assessing the extent of dark regions in the central image alongside the numerical index may provide useful information for interpreting central visual field status from the AI-CO display.
ER  -

Abstract

Related

Cite