My publications connect an engineering approach to practical problems with mathematical reasoning and computational methods for human health. The work spans ensemble learning for retinal images, retinal–molecular associations, and interpretable causal models for fragmented biomedical data.
Characterises cross-sectional associations between retinal traits and lipidomic profiles in a generally healthy biobank population. Published in Scientific Reports (Nature Portfolio) on 27 October 2026.
A broad survey of retinal imaging and oculomics, mapping how ocular biomarkers can inform systemic, cardiovascular, and metabolic health.
Shows how architectural and data-level diversity in CNN ensembles improves robustness under class imbalance and limited medical imaging data.
Examines how ensemble diversity can mitigate data scarcity in diabetic retinopathy modelling and improve generalisation in clinical imaging settings.
Explores links between retinal microvascular traits and lipidomic profiles to identify candidate non-invasive biomarkers for cardiovascular risk.
Introduces Causal-RetiGraph, a biomedical informatics framework linking interpretable retinal graph phenotypes with NHANES-anchored pathway modelling for diabetic retinopathy.
Introduces a dual-edge spatial-Jacobian image graph framework for interpretable diabetic retinopathy grading by combining vessel-lesion spatial edges with Jacobian-based lesion-biomarker edges.
RetiSEM presents a causal modelling framework for fragmented biomedical data, designed to recover interpretable structure under incomplete, multimodal, and distributed evidence settings.
