Machine learning algorithms can predict rapid glaucoma progression
Eyes that will undergo rapid glaucoma progression can be identified based on an initial visual field (VF) test using machine learning algorithms (MLA), according to a study. In this retrospective analysis of longitudinal data, 175,786 VFs, including 22,925 initial VFs, from 14,217 patients who completed ≥5 reliable VFs were included. Of the initial VFs, 8.6% (1968 eyes) underwent rapid progression. Rapid progression was most accurately predicted when the support vector machine model was trained on initial VF data; models trained on the first 2 VFs performed no better.
Variables in the initial VF most strongly associated with rapid progression included older age and higher pattern standard deviation.
The authors concluded that utilizing more clinical data into this model could potentially predict patients likely to progress rapidly with more accuracy.
Shuldiner SR, Boland MV, Ramulu PY, et al. Predicting eyes at risk for rapid glaucoma progression based on an initial visual field test using machine learning. PLoS One. 2021 Apr 16;16(4):e0249856. DOI: 10.1371/journal.pone.0249856. PMID: 33861775.
Grandin Library Building
Six Leigh Street
Clinton, New Jersey 08809