Auto-GlaKG: Automated Biomarker Reasoning for Explainable Glaucoma Detection
Organizations: Department of Genetics, Washington University in St. Louis, St. Louis, MO 63110, USA · Department of Computer Science, Southern Methodist University, Dallas, TX 75205, USA · Department of Health Data Science and Artificial Intelligence, University of Texas Health Science Center at Houston, Houston, TX 77030, USA · Houston Methodist Neal Cancer Center, Houston Methodist Research Institute, Houston, TX 77030, USA ·
Abstract
Interpretable glaucoma detection requires a transparent connection between fundus images, clinically meaningful biomarkers, and diagnostic predictions. Knowledge graph (KG) reasoning provides this structure, but performance measured using annotated biomarkers does not establish performance when only images are available. We present Auto-GlaKG, an automated framework that combines image-based biomarker prediction with fixed clinical-prior rules. A ResNet50 network predicts the cup-to-disc ratio (CDR) and six morphological signs using biomarker supervision, and a KG reasoner aggregates their signed rule contributions into a glaucoma score. On 689 fundus images evaluated using stratified, group-aware five-fold cross-validation, Auto-GlaKG achieves a pooled area under the receiver operating characteristic curve (AUC) of 0.951 (95% confidence interval: 0.931--0.969), with sensitivity of 0.970 and specificity of 0.779. The matched image classifier also achieves an AUC of 0.951, while the rule stage adds 0.2~ms per image. Replacing predicted CDR with its annotation increases fold-mean AUC from 0.953 to 0.995. The framework provides an explicit rule-level account of image-based predictions and identifies CDR estimation as a priority for validation using independently measured biomarkers.
Figures & tables
| Rule | Condition | Dir. | |
|---|---|---|---|
| CDR high | G | 3 | |
| CDR moderate | G | 2 | |
| CDR normal | N | 3 | |
| Rim thinning | Present | G | 3 |
| Notching | Present | G | 3 |
| ISNT violated | Present | G | 2 |
| Method | AUC [95% CI] | Fold AUC | AUPRC | Acc | BalAcc | Sens | Spec | Prec | F1 | MCC | Brier | ECE | Sens@95Spec |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ResNet50 | 0.951 [0.929, 0.970] | 0.955 | 0.910 | 0.907 | 0.920 | 0.893 | 0.934 | 0.927 | 0.810 | 0.075 | 0.058 | 0.724 | |
| Auto-GlaKG (hard) | 0.938 [0.914, 0.960] | 0.943 | 0.900 | 0.888 | 0.937 | 0.840 | 0.905 | 0.921 | 0.786 | 0.088 | 0.075 | 0.604 | |
| Auto-GlaKG (soft) | 0.951 [0.931, 0.969] | 0.962 | 0.897 | 0.874 | 0.970 | 0.779 | 0.877 | 0.921 | 0.782 | 0.087 | 0.090 | 0.658 | |
| Auto-GlaKG (hard) + Image | 0.949 [0.927, 0.968] | 0.961 | 0.903 | 0.897 | 0.920 | 0.874 | 0.923 | 0.922 | 0.794 | 0.082 | 0.070 | 0.700 | |
| Auto-GlaKG (soft) + Image | 0.946 [0.925, 0.967] | 0.955 | 0.912 | 0.901 | 0.944 | 0.859 | 0.916 | 0.930 | 0.811 | 0.072 | 0.044 | 0.600 |