Journal article
Archetypal analysis of visual fields in optic neuritis reveals functional biomarkers associated with outcome and treatment response
Multiple sclerosis and related disorders, Vol.67, 104074
11/2022
DOI: 10.1016/j.msard.2022.104074
PMID: 35940021
Abstract
•Machine learning of visual fields from the Optic Neuritis Treatment Trial reveals new information about visual loss and recovery in optic neuritis.•Unsupervised machine learning using archetypal analysis provides a new way to monitor the changes in the visual fields of eyes with acute optic neuritis.•Archetypal analysis also identifies residual visual deficits, not apparent with conventional analysis, in eyes that have recovered.
Archetypal analysis (AA), a form of unsupervised machine learning, can identify quantifiable visual field (VF) patterns seen in optic neuritis (ON), known as archetypes (ATs). We hypothesized that AT weight changes over time would reflect the course of recovery and the effects of therapy in ON. We explored whether baseline AT weights would be associated with VF status at the clinical trial outcome and if ATs would indicate residual VF defects in eyes with mean deviation (MD) ≥ -2.00 at six months.
We used a published 16-AT model derived from 3892 Optic Neuritis Treatment Trial VFs (456 eyes) for all analyses. We measured AT weight changes over the six-month study period and used asymptotic regression to analyze the rate of change. We compared AT weights at six months between treatment groups. We evaluated associations between baseline AT weight thresholds and VF outcome or treatment effect. We calculated residual AT weights in eyes with MD ≥ -2.00 dB at six months.
Over six months, AT1 (a normal VF pattern) demonstrated the greatest median weight change, increasing from 0.00% (IQR 0.00–0.00%) at baseline to 60.0% (IQR 38.3–70.8%) at six months (p < 0.001). At outcome, the intravenous methylprednisolone (IVMP) group had the highest median AT1 weight (IVMP: 63.3%, IQR 51.3–72.8%; placebo: 56.2%, IQR 35.1–71.6%; prednisone 58.3%, IQR 35.1–71.6%; p = 0.019). Eyes with AT1 weight ≥ 19% at baseline had superior median MD values (-0.91 vs. -2.07 dB, p < 0.001) and AT1 weights (70.8% vs. 57.8% p < 0.001) at six months. Only eyes with AT1 weight < 19% at baseline showed a treatment benefit for IVMP, with a higher six-month median AT1 weight compared to placebo (p = 0.015) and prednisone (p = 0.016), and a higher median MD compared to placebo (p = 0.027). At six months, 182 (80.2%) VFs with MD ≥ -2.00 had at least one abnormal AT.
Changes in quantifiable, archetypal patterns of VF loss reflect recovery in ON. Machine learning analysis of the VFs in optic neuritis reveals associations with response to therapy and VF outcome, and uncovers residual deficits, not readily seen with standard evaluations.
[Display omitted] .
Details
- Title: Subtitle
- Archetypal analysis of visual fields in optic neuritis reveals functional biomarkers associated with outcome and treatment response
- Creators
- Elena Solli - Icahn School of Medicine at Mount SinaiHiten Doshi - Albert Einstein College of MedicineTobias Elze - Massachusetts Eye and Ear InfirmaryLouis R. Pasquale - Icahn School of Medicine at Mount SinaiJoseph Branco - New York Medical College, Valhalla, NY, United StatesMichael Wall - University of IowaMark Kupersmith - Icahn School of Medicine at Mount Sinai
- Resource Type
- Journal article
- Publication Details
- Multiple sclerosis and related disorders, Vol.67, 104074
- Publisher
- Elsevier B.V
- DOI
- 10.1016/j.msard.2022.104074
- PMID
- 35940021
- ISSN
- 2211-0348
- eISSN
- 2211-0356
- Language
- English
- Date published
- 11/2022
- Academic Unit
- Neurology; Ophthalmology and Visual Sciences
- Record Identifier
- 9984281656602771
Metrics
22 Record Views