Causal-RetiGraph: Cross-Cohort Retinal Support and Same-Subject Pathway Analysis for Diabetic Retinopathy
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present Causal-RetiGraph, a new method that connects detailed features from retinal images with systemic health data to better understand diabetic retinopathy (DR). They create a retinal phenotype by combining vessel maps, lesion data, and biomarkers, and link this to systemic factors like blood sugar and blood pressure from a large health survey (NHANES). Their approach accurately identifies DR from images and highlights important bodily pathways related to blood sugar and kidney function as key to the disease. This work helps clarify how eye changes relate to overall health in DR without mixing image evidence and systemic mediation.
Diabetic retinopathyRetinal phenotypeNHANESVessel mapsLesion evidenceAutoMorph biomarkersHbA1cGlycaemic pathwaysMicrovascular injuryCausal mediation
Authors
Inam Ullah, Imran Razzak, Shoaib Jameel
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.