Predicting Longitudinal Visual Field Progression With Class Imbalanced Data

Glaucoma is the leading cause of irreversible blindness worldwide. The clinical standard for glaucoma diagnosis and progression tracking remains visual field (VF) testing via standard automated perimetry. One outstanding challenge of many ophthalmic prediction tasks is the issue of class imbalance, where the majority class outnumbers the minority class(es). Although this issue has been reported in several prior studies on the prediction of VF progression or glaucoma, it has not been addressed in the context of longitudinal VF data. In this work, we proposed, VF-Transformer, a transformer-based framework for VF progression prediction based on longitudinal VF examination results. In particular, we addressed the class imbalance issue by incorporating our proposed inverted class-dependent temperature (ICDT) loss and weight normalization. The proposed framework was developed and evaluated on a public VF dataset and further validated on an external hospital dataset, using accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) as evaluation metrics. Extensive experiments and comparisons with existing state-of-the-art methods and class imbalance handling strategies confirmed the effectiveness of the proposed framework in predicting VF progression in the presence of class imbalance.

Authors

• Ling Chen University of Technology Sydney
• Chun-Hung Chen
• Wei Wang
• Da-Wen Lu
• Vincent S. Tseng

Keywords

• Transformers
• Glaucoma
• Training
• Feature extraction
• Bioinformatics
• Standards
• Visualization
• Sensitivity
• Temperature sensors
• Temperature dependence
• Imbalanced Data
• Visual Field Progression
• Class-imbalanced Data
• Longitudinal Visual Field
• Receiver Operating Characteristic Curve
• Extensive Experiments
• Class Imbalance
• Perimetry
• Minority Class
• Prediction Framework
• Glaucoma Progression
• Cause Of Blindness Worldwide
• Presence Of Imbalance
• Hospital Dataset
• Deep Learning
• Machine Learning Models
• Short-term Memory
• Binary Classification
• Forecasting
• Positive Cases
• External Test Set
• Binary Cross-entropy Loss
• Long Short-term Memory
• Oversampling Methods
• Severe Group
• External Test
• Cross-entropy Loss
• Humphrey Field Analyzer
• Transformer Encoder
• Convolutional Long Short-term Memory
• Visual field progression prediction
• transformer-based network
• Humans
• Visual Fields
• Disease Progression
• Visual Field Tests
• ROC Curve
• Algorithms
• Databases, Factual