Purchase this article with an account.
Nara Gravina Ogata, Alessandro Adad Jammal, Felipe Medeiros; The Relationship Between Machine Learning-Derived Patterns of Visual Field Loss and Patient-Reported Disability in Glaucoma. Invest. Ophthalmol. Vis. Sci. 2018;59(9):5113. doi: https://doi.org/.
Download citation file:
© ARVO (1962-2015); The Authors (2016-present)
To investigate whether specific patterns of visual field loss, derived from unsupervised machine learning classification, are related to patient-reported disability in glaucoma.
The study included 575 patients with glaucoma damage in at least one eye. Patient-reported vision-related quality of life was assessed by the National Eye Institute Questionnaire (NEI VFQ-25) questionnaire. A latent class analysis procedure was used to divide subjects into two classes of disabled versus non-disabled based on NEI VFQ-25 results. Total deviation values for the right and left eye were extracted from the 52 locations measured by standard automated perimetry (SAP). An unsupervised machine learning classification method was used to classify visual field patterns in 17 non-mutually exclusive archetypes, according to a previously described method.
105 of the 575 (18%) of the subjects showed significant vision-related disability based on NEI VFQ-25 results. Among the 17 patterns of visual field loss, the presence of inferior paracentral defect was 4.6 times more common (P<0.001) and superior paracentral defects were 3.0 times more common (P=0.01) in patients with disability compared to those without disability.
Machine learning-derived patterns of visual field loss are related to patient-reported vision-related quality of life in glaucoma.
This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.
This PDF is available to Subscribers Only