Unsupervised Machine Learning Shows Change in Visual Field Loss in the Idiopathic Intracranial Hypertension Treatment Trial

Hiten Doshi, Elena Solli, Tobias Elze, Louis R. Pasquale, Michael Wall, Mark J. Kupersmith

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Purpose: We previously reported that archetypal analysis (AA), a type of unsupervised machine learning, identified and quantified patterns of visual field (VF) loss in idiopathic intracranial hypertension (IIH), referred to as archetypes (ATs). We assessed whether AT weight changes over time are consistent with changes in conventional global indices, whether visual outcome or treatment effects are associated with select AT, and whether AA reveals residual VF defects in eyes deemed normal after treatment. Design: Analysis of data collected from a randomized controlled trial. Participants: Two thousand eight hundred sixty-two VFs obtained from 165 participants during the Idiopathic Intracranial Hypertension Treatment Trial (IIHTT). Methods: We applied a 14-AT model derived from IIHTT VFs. We examined changes in individual AT weights over time for all study eyes and evaluated differences between treatment groups. We created an AT change score to assess overall VF change from baseline. We tested threshold baseline AT weights for association with VF outcome and treatment effect at 6 months. We determined the abnormal ATs with meaningful weight at outcome for VFs with a mean deviation (MD) of –2.00 dB or more. Main Outcome Measures: Individual AT weighting coefficients and MD. Results: Archetype 1 (a normal VF pattern) showed the greatest weight change for all study eyes, increasing from 11.9% (interquartile range [IQR], 0.44%–24.1%) at baseline to 31.2% (IQR, 16.0%–45.5%) at outcome (P < 0.001). Archetype 1 weight change (r = 0.795; P < 0.001) and a global score of AT change (r = 0.988; P < 0.001) correlated strongly with MD change. Study eyes with baseline AT2 (a mild diffuse VF loss pattern) weight of 44% or more (≥ 1 standard deviation more than the mean) showed higher AT2 weights at outcome than those with AT2 weight of < 44% at baseline (P < 0.001). Only the latter group showed a significant acetazolamide treatment effect. Archetypal analysis revealed residual VF loss patterns, most frequently representing mild diffuse loss and an enlarged blind spot in 64 of 66 study eyes with MD of –2.00 dB or more at outcome. Conclusions: Archetypal analysis provides a quantitative approach to monitoring VF changes in IIH. Baseline AT features may be associated with treatment response and VF outcome. Archetypal analysis uncovers residual VF defects not otherwise revealed by MD.

Original languageEnglish
Pages (from-to)903-911
Number of pages9
JournalOphthalmology
Volume129
Issue number8
DOIs
StatePublished - Aug 2022

Keywords

  • Archetypal analysis
  • Idiopathic intracranial hypertension
  • Machine learning
  • Visual fields

Fingerprint

Dive into the research topics of 'Unsupervised Machine Learning Shows Change in Visual Field Loss in the Idiopathic Intracranial Hypertension Treatment Trial'. Together they form a unique fingerprint.

Cite this