Causal-RetiGraph: Cross-Cohort Retinal Support and Same-Subject Pathway Analysis for Diabetic Retinopathy

2026-07-06

AI Summary

This study addresses the unclear causal relationships among localized lesions, retinal vascular architecture, and systemic pathways in diabetic retinopathy (DR). The authors propose Causal-RetiGraph, a novel framework that integrates interpretable retinal graph-based phenotypes with systemic pathway models derived from the NHANES population cohort. Leveraging graph neural networks, Jacobian branching, and multimodal features—including vascular graphs, lesion evidence, AutoMorph biomarkers, and image embeddings—the method performs individualized mediation analysis. It achieves 0.9055 accuracy and 0.9711 AUROC in DR classification and identifies glycometabolism–kidney and glycometabolism–hemodynamic pathways as key mediators. Furthermore, five biomarkers, including HbA1c, emerge as the strongest DR-associated factors, enabling causal inference from imaging phenotypes to underlying systemic mechanisms.

Abstract

Diabetic retinopathy (DR) is a local retinal lesion process and a visible manifestation of systemic microvascular injury. Modern retinal AI can grade images accurately, but often leaves unanswered how local lesion evidence, retinal vascular structure, and systemic disease pathways are connected. This paper introduces \emph{Causal-RetiGraph}, a compact biomedical informatics framework that links retinal graph phenotypes with NHANES-anchored pathway modelling. The retinal-image fold constructs an interpretable $X1234$ phenotype from vessel maps, lesion evidence, image embeddings, and AutoMorph biomarkers through spatial $X_{12}$ and Jacobian $X_{34}$ branches. The NHANES fold models systemic exposures, covariates, a same-subject retinal mediator family $R^*$, and downstream outcome families. $X1234$ is used for retinal support and pathway prioritisation, while $R^*$ is used for participant-level pathway summaries. On the retinal fold, $X1234$ achieves 0.9055 binary DR accuracy and 0.9711 AUROC, with graded DR QWK of 0.8312. The results show that lesion and biomarker streams improve contextual retinal representation under scarce and imbalanced data. In NHANES, HbA1c, urine albumin, pulse pressure, fasting glucose, and systolic blood pressure are the strongest binary DR anchors. Participant-level pathway analysis identifies glycaemic--renal and glycaemic--haemodynamic pathways as the clearest mediator-style signals. These results suggest that retinal graph phenotypes can help prioritise systemic pathways in DR while preserving the distinction between image-derived support and same-subject mediation.

Problem

• Diabetic Retinopathy
• Retinal Lesions
• Systemic Pathways
• Causal Inference
• Multimodal Integration

Innovation

• Causal-RetiGraph
• retinal graph phenotype
• same-subject mediation
• cross-cohort integration
• pathway prioritization