Validation of a Machine Learning Approach to the Analysis of Multifocal Electroretinograms for…

AI / informaticsTranslational vision science & technology· Jul 2026

Validation of a Machine Learning Approach to the Analysis of Multifocal Electroretinograms for Hydroxychloroquine Retinopathy.

Godfrey Wong, Gareth Mercer, Brian G Ballios, Tom Wright

RetinaAI / informaticsDiagnosisQ1IF 2.8

Machine learning algorithm accurately rules out hydroxychloroquine retinopathy in new patients.

Validation of a Machine Learning Approach to the Analysis of Multifocal Electroretinograms for Hydroxychloroquine Retinopathy.

Godfrey Wong … Tom Wright

Translational vision science & technology · Jul 2026 · Q1 in Ophthalmology

Purpose

This study evaluated the clinical utility of the Multifocal Electroretinogram Classification Interface (Multifocal Electroretinogram Classification Interface) algorithm by assessing its ability to predict hydroxychloroquine retinopathy compared with diagnoses derived from American Academy of Ophthalmology (Academy of Ophthalmology) guidelines.

Methods

Referred for hydroxychloroquine toxicity screening underwent perimetry, spectral-domain optical coherence tomography, fundus autofluorescence photography, and multifocal electroretinogram (mfERG) testing.

0.987

Results

0.987

The algorithm was very good at ruling out eye damage in new patients

More results

Using the decision trees, the temporal (n = 145) and novel (n = 300) datasets showed retinopathy prevalences of 12.4% and 9.7%, respectively.

Multifocal Electroretinogram Classification Interface yielded 63/145 (43.4%) and 115/300 (38.3%) false-positive cases, respectively.

“

Conclusion · 1 of 2

Multifocal Electroretinogram Classification Interface retained high sensitivity and negative predictive value when validated against temporally distinct cohorts using a clinical definition of hydroxychloroquine toxicity.

Conclusion · 2 of 2

This suggests Multifocal Electroretinogram Classification Interface's potential as a screening tool for hydroxychloroquine retinopathy.

Validation of a Machine Learning Approach to the Analysis of Multifocal Electroretinograms for Hydroxychloroquine Retinopathy.

Validation of a Machine Learning Approach to the Analysis of Multifocal Electroretinograms for Hydroxychloroquine Retinopathy.

Related papers