Skip to content
Open access · OA via Europe PMC

Decoding the Bone-Eye Axis: Machine Learning for Age-Related Macular Degeneration Risk Prediction.

Cui X, Zhao Q, Hui J, Han Z, Yu-Wai-Man P, Han Q.

Cyborg and bionic systems (Washington, D.C.) · 2026

Abstract

Age-related macular degeneration (AMD) is a leading cause of irreversible vision loss, yet systemic determinants of its risk remain incompletely understood. Bone mineral density (BMD), a marker of skeletal and biological aging, may reflect shared pathways linking systemic and retinal degeneration. We investigated the association between BMD and AMD using a multilayered framework integrating epidemiological analyses, Mendelian randomization (MR), proteomic and metabolomic profiling, machine learning, and an experimental low-BMD model. Across 3 cohorts, including UK Biobank, National Health and Nutrition Examination Survey, and a hospital-based Tianjin cohort, lower BMD was consistently associated with higher AMD risk, although AMD ascertainment and BMD measurement differed across cohorts. Two-sample MR analyses provided supportive genetic evidence consistent with a modest potential contribution of higher BMD to lower AMD risk, while sensitivity analyses did not indicate strong evidence of reverse causality. Machine learning models identified BMD as a recurrent predictive contributor alongside age, but its incremental clinical utility requires formal evaluation using models with and without BMD. UK Biobank proteomic and metabolomic analyses revealed overlapping molecular signatures involving extracellular matrix remodeling, lipid transport, amino acid metabolism, and inflammatory pathways. Two-step MR prioritized circulating proteins including granzyme A, collagen type II alpha 1 chain, and NEL-like protein 1 as candidate molecular intermediates rather than established mechanistic mediators. In a glucocorticoid-induced low-BMD rat model, retinal alterations relevant to degeneration, including outer retinal thinning, vascular narrowing, and delayed visual-spatial performance, were observed, but these findings should not be interpreted as direct validation of AMD pathology. Overall, these findings support an association between lower BMD and AMD risk and suggest that BMD may act as an accessible marker of systemic aging processes related to retinal vulnerability.

◌ CITATION ONLY
Full text is not openly licensed for redistribution here. Read it at the source:

Read at source →

Provenance

Source
Europe PMC
DOI
10.34133/cbsystems.0676
Canonical
link ↗
Fetched
2026-10-10 MST

Cite this

APA
X, C., Q, Z., J, H., Z, H., P, Y., &amp; Q., H. (2026). Decoding the Bone-Eye Axis: Machine Learning for Age-Related Macular Degeneration Risk Prediction. <em>Cyborg and bionic systems (Washington, D.C.)</em>. https://doi.org/10.34133/cbsystems.0676
Vancouver
X C, Q Z, J H, Z H, P Y, Q. H. Decoding the Bone-Eye Axis: Machine Learning for Age-Related Macular Degeneration Risk Prediction. Cyborg and bionic systems (Washington, D.C.). 2026. doi:10.34133/cbsystems.0676.
BibTeX
@article{cui2026Decodi, title = {Decoding the Bone-Eye Axis: Machine Learning for Age-Related Macular Degeneration Risk Prediction.}, author = {Cui X and Zhao Q and Hui J and Han Z and Yu-Wai-Man P and Han Q.}, journal = {Cyborg and bionic systems (Washington, D.C.)}, year = {2026}, doi = {10.34133/cbsystems.0676}, }

Research neighborhood

References, citing works, and semantically nearest findings. Click a node to open it.

Related findings