A quick test with active learning algorithms might give physicians a novel method to measure contrast sensitivity (CS) when evaluating patients before cataract surgery, according to Augustine Bannerman, an undergraduate research assistant, and Filippos Vingopoulos, MD, both from the Harvard Retinal Imaging Laboratory at Massachusetts Eye and Ear in Boston.
“Contrast sensitivity function [CSF] testing could also be a helpful addition to the usual cataract evaluation to enhance surgical decision-making, particularly in patients with subjective visible complaints despite well visible acuity [VA],” Bannerman said.
In accordance with Bannerman, surgical decision-making in the lead-up to cataract surgery relies on subjective visual impairment and not on objective clinically measured visual function outcomes.
In mild of this, Bannerman and his colleagues embraced previous research on the strong correlation between CS and subjective visible impairment and vision-related daily activities, then went a step additional to bypass the present imperfections that limit the CS testing used clinically.
Investigators included 167 eyes, of which 58 eyes were cataractous, 77 were controls, and 32 were pseudophakic, in a study to characterize CSF in patients with cataract and people who were pseudophakic utilizing a novel CSF test with active learning algorithms.
Participants’ vision was assessed utilizing the Manifold Contrast Vision Meter (Adaptive Sensory Technology).
Visually related cataract was outlined as 2+ nuclear sclerosis and a VA of greater than 20/50, pseudophakic patients had posterior phase intraocular lenses while controls had no more than 1+ nuclear sclerosis and no visual complaints.
The first outcomes had been the realm below the log CSF (AULCSF), contrast acuity (CA), and CS thresholds at 1, 1.5, 3, 6, 12, and 18 cycles/degree (cpd).
The so-called quick CSF test makes use of “a Bayesian active learning algorithm that maximizes data extraction over a really massive set of doable combos of distinction and spatial frequency that in the end creates a curve separating visible from invisible stimuli with great test-related repeatability and testing instances of two to five minutes per eye,” Bannerman said.
The investigators reported that the presence of cataract was related to considerably decreased AULCSF (P = .04) and contrast threshold at 6 cpd (P = .01) in contrast with controls.
A fascinating finding, according to Bannerman, was that even in a subgroup of cataractous eyes with excellent VA (≥ 20/25), the contrast threshold at 6 cpd was still decreased considerably (P = .02).
The 6-cpd spatial frequency appears vital, he said: The decrease or larger spatial frequencies weren’t affected by cataract.
These contrast sensitivity deficits detected with the short CSF test would have been missed with the traditional Pelli-Robson contrast testing, he added.
Pseudophakic eyes didn’t have considerably different contrast outcomes measures in contrast with the controls.
The quick CSF test detected disproportionate important contrast deficits at 6 cpd within the varied metrics evaluated in cataractous eyes and even in those with good VA, the authors noted.
“CSF testing could also be a helpful addition to straightforward cataract analysis to reinforce surgical decision-making particularly in patients with subjective visual complaints regardless of good VA,” they said.
A potential area of study may be to carry out the short CSF test in pseudophakic eyes with various kinds of intraocular lenses, the authors said.
An ongoing study will show the improved CSF after cataract surgery and evaluate that with enhancement in VA.