Predicting visual field global and local parameters from OCT measurements using explainable machine learning
Open Access
- 16 February 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-18
Abstract
Glaucoma is characterised by progressive vision loss due to retinal ganglion cell deterioration, leading to gradual visual field (VF) impairment. The standard VF test may be impractical in some cases, where optical coherence tomography (OCT) can offer predictive insights into VF for multimodal diagnoses. However, predicting VF measures from OCT data remains challenging. To address this, five regression models were developed to predict VF measures from OCT, Shapley Additive exPlanations (SHAP) analysis was performed for interpretability, and a clinical software tool called OCT to VF Predictor was developed. To evaluate the models, a total of 268 glaucomatous eyes (86 early, 72 moderate, 110 advanced) and 226 normal eyes were included. The machine learning models outperformed recent OCT-based VF prediction deep learning studies, with correlation coefficients of 0.76, 0.80 and 0.76 for mean deviation, visual field index and pattern standard deviation, respectively. Introducing the pointwise normalisation and step-size concept, a mean absolute error of 2.51 dB was obtained in pointwise sensitivity prediction, and the grayscale prediction model yielded a mean structural similarity index of 77%. The SHAP-based analysis provided critical insights into the most relevant features for glaucoma diagnosis, showing promise in assisting eye care practitioners through an explainable AI tool.Keywords
Funding Information
- University of New South Wales
- National Health and Medical Research Council (1186915)
This publication has 61 references indexed in Scilit:
- Predicting Visual Fields From Optical Coherence Tomography via an Ensemble of Deep Representation LearnersAmerican Journal of Ophthalmology, 2022
- Viability of Performing Multiple 24-2 Visual Field Examinations at the Same Clinical Visit: The Frontloading Fields Study (FFS)American Journal of Ophthalmology, 2021
- Transparency and the Black Box Problem: Why We Do Not Trust AIPhilosophy & Technology, 2021
- A Strategy for Seeding Point Error Assessment for Retesting (SPEAR) in Perimetry Applied to Normal Subjects, Glaucoma Suspects, and Patients With GlaucomaAmerican Journal of Ophthalmology, 2021
- Ability of 24-2C and 24-2 Grids to Identify Central Visual Field Defects and Structure-Function Concordance in Glaucoma and SuspectsAmerican Journal of Ophthalmology, 2020
- Clinical Evaluation of Swedish Interactive Thresholding Algorithm–Faster Compared With Swedish Interactive Thresholding Algorithm–Standard in Normal Subjects, Glaucoma Suspects, and Patients With GlaucomaAmerican Journal of Ophthalmology, 2019
- Google Colaboratory2019
- Multiple imputation using chained equations: Issues and guidance for practiceStatistics in Medicine, 2010
- Categorizing the Stage of Glaucoma From Pre-Diagnosis to End-Stage DiseaseAmerican Journal of Ophthalmology, 2006
- Test-Retest Variability in Glaucomatous Visual FieldsAmerican Journal of Ophthalmology, 1989