Using machine learning, artificial intelligence (AI) is finding new ways to analyze tens of thousands of ocular images in various states of disease progression and find patterns never before seen.

US-based researchers say they’ve used AI to quantify central visual field (VF) patterns in glaucoma, which can be used to improve the prediction of central VF worsening compared with only using global indices alone, according to a publication in the journal Ophthalmology. To achieve this, the AI studied 13,951 10-2 tests from 13,951 eyes for cross-sectional analyses and images of 1,191 eyes with at least five reliable 10-2 tests at six or more month intervals. It also used 24-2 VF within three months of the initial 10-2 tests to stage eyes into mild, moderate or severe functional loss.

It found 17 distinct central VF patterns, which could be divided into four categories: isolated superior loss, isolated inferior loss, diffuse loss and other loss patterns. Four of the five patterns preserved the less vulnerable inferotemporal zone, while they lost most of the remaining more vulnerable zone, the researchers noted. They explained that that “inclusion of coefficients from central VFs archetypical patterns strongly improved the prediction of central VF mean deviation slope than using only the global indices of two baseline VFs. Eyes with baseline VFs with more superonasal and inferonasal loss were more likely to have worsening mean deviation over time.”