GlaKG: A Biomarker-Centric Fundus Knowledge Graph for Explainable Glaucoma Diagnosis and Risk Assessment

2026-07-06

AI Summary

This study addresses the limited clinical interpretability of existing black-box models in automated glaucoma diagnosis by proposing a biomarker-centric, auditable diagnostic framework. The authors construct a retinal fundus knowledge graph encompassing six entity types, eight relation types, and eleven clinical rules. Image embeddings extracted by ResNet50 are fused with knowledge graph–based reasoning through a post-processing weighted integration, yielding explicit and traceable diagnostic inference chains. Evaluated on a publicly available AI-annotated fundus dataset, the method achieves a binary classification F1 score of 0.9953 and a four-class risk stratification accuracy of 0.930 (weighted F1 = 0.922). Feature importance analysis further validates the critical contributions of both the knowledge graph structure and clinically relevant biomarkers to diagnostic performance.

Abstract

Glaucoma is a leading cause of irreversible blindness worldwide, yet most automated diagnosis systems rely on opaque deep-learning models that offer little clinical interpretability. We present GlaKG, a biomarker-centric fundus knowledge graph that integrates structural biomarkers, clinically grounded rules, and image features to produce traceable reasoning for glaucoma diagnosis and risk stratification. GlaKG encodes six entity types (Fundus Image, Optic Disc, Neural Rim, Pathology, Diagnosis, Risk Level), eight relation types, and 11 clinically validated rules into a unified graph, so that every prediction is accompanied by an explicit reasoning chain linking biomarker evidence to activated clinical rules. To keep knowledge-based reasoning strictly separate from label information, we adopt a post-processing fusion framework that combines ResNet50 image embeddings with a normalized KG reasoning-chain score via a tunable weight alpha, with all fitting confined to the training split. On a publicly available, AI-annotated fundus dataset, GlaKG reaches F1 = 0.9953 for binary glaucoma classification and 0.930 accuracy with 0.922 weighted F1 for four-class risk stratification; we report openly that the dataset's biomarker annotations are highly label-correlated, and therefore frame these figures as an upper bound attainable with clean structured biomarkers rather than as leakage-free image-only performance. Feature-importance analysis shows KG-derived and biomarker features contributing near-equally (51.1% vs. 48.9%), and the reasoning chain flags borderline cases by exposing low chain scores rather than failing silently. GlaKG's central contribution is therefore a clinically auditable reasoning framework that complements raw predictive performance by explicitly exposing the biomarker evidence and rule activations behind each decision.

Problem

• glaucoma diagnosis
• clinical interpretability
• knowledge graph
• biomarker
• explainable AI

Innovation

• knowledge graph
• biomarker-centric reasoning
• explainable AI
• glaucoma diagnosis
• clinical interpretability