Classifying and quantifying changes in papilloedema using machine learning

Joseph Branco; Jui-Kai Wang; Tobias Elze; Mona K Garvin; Louis R Pasquale; Randy Kardon; Brian Woods; David Szanto; Mark J Kupersmith

doi:10.1136/bmjno-2023-000503

Back

Classifying and quantifying changes in papilloedema using machine learning

Journal article

Open access

Peer reviewed

Classifying and quantifying changes in papilloedema using machine learning

Joseph Branco, Jui-Kai Wang, Tobias Elze, Mona K Garvin, Louis R Pasquale, Randy Kardon, Brian Woods, David Szanto and Mark J Kupersmith

BMJ neurology open, Vol.6(1), e000503

06/26/2024

DOI: 10.1136/bmjno-2023-000503

PMCID: PMC11216071

PMID: 38952840

Files and links (1)

url

https://doi.org/10.1136/bmjno-2023-000503View

Published (Version of record) Open Access

Abstract

Background Machine learning (ML) can differentiate papilloedema from normal optic discs using fundus photos. Currently, papilloedema severity is assessed using the descriptive, ordinal Frisén scale. We hypothesise that ML can quantify papilloedema and detect a treatment effect on papilloedema due to idiopathic intracranial hypertension. Methods We trained a convolutional neural network to assign a Frisén grade to fundus photos taken from the Idiopathic Intracranial Hypertension Treatment Trial (IIHTT). We applied modified subject-based fivefold cross-validation to grade 2979 longitudinal images from 158 participants’ study eyes (ie, the eye with the worst mean deviation) in the IIHTT. Compared with the human expert-determined grades, we hypothesise that ML-estimated grades can also demonstrate differential changes over time in the IIHTT study eyes between the treatment (acetazolamide (ACZ) plus diet) and placebo (diet only) groups. Findings The average ML-determined grade correlated strongly with the reference standard (r=0.76, p<0.001; mean absolute error=0.54). At the presentation, treatment groups had similar expert-determined and ML-determined Frisén grades. The average ML-determined grade for the ACZ group (1.7, 95% CI 1.5 to 1.8) was significantly lower (p=0.0003) than for the placebo group (2.3, 95% CI 2.0 to 2.5) at the 6-month trial outcome. Interpretation Supervised ML of fundus photos quantified the degree of papilloedema and changes over time reflecting the effects of ACZ. Given the increasing availability of fundus photography, neurologists will be able to use ML to quantify papilloedema on a continuous scale that incorporates the features of the Frisén grade to monitor interventions.

Ophthalmology

Vision

NEUROOPHTHALMOLOGY

Original research

Details

Title: Subtitle: Classifying and quantifying changes in papilloedema using machine learning
Creators: Joseph Branco - New York Medical College
Jui-Kai Wang - University of Iowa
Tobias Elze - Harvard Medical School
Mona K Garvin - University of Iowa
Louis R Pasquale - Icahn School of Medicine at Mount Sinai
Randy Kardon - University of Iowa
Brian Woods - Cork University Hospital
David Szanto - Stony Brook University
Mark J Kupersmith - New York Medical College
Resource Type: Journal article
Publication Details: BMJ neurology open, Vol.6(1), e000503
DOI: 10.1136/bmjno-2023-000503
PMID: 38952840
PMCID: PMC11216071
NLM abbreviation: BMJ Neurol Open
ISSN: 2632-6140
eISSN: 2632-6140
Publisher: BMJ Publishing Group Ltd
Grant note: I01RX003797; I50 RX003002 / U.S. Department of Veterans Affairs (http://dx.doi.org/10.13039/100000738) N/A / The New York Eye and Ear Infirmary Foundation N/A / Research to Prevent Blindness, Inc., New York EY032522; R01 EY015473 / NEI
Language: English
Date published: 06/26/2024
Academic Unit: Electrical and Computer Engineering; Iowa Neuroscience Institute; Ophthalmology and Visual Sciences
Record Identifier: 9984651158702771

Metrics

6 Record Views

4 Times Cited - Web of Science