ATLANTA — One of the challenges in early detection of hematological malignancies—and potential improvement in long-term survival—is heterogeneity in clinical presentation.
Researchers from the Atlanta VAMC, Emory University and the Georgia Institute of Technology advise, however, that chronic inflammation is a key driver in hematologic cancers and is known to induce compensatory microvascular changes. “High-resolution, non-invasive retinal imaging can allow the quantification of microvascular changes for the early detection of hematological malignancies,” they suggested.
Their study, published in the European Journal of Cancer evaluated RetHemo, an explainable AI tool predicting hematological malignancy onset up to 10 years before diagnosis using retinal imaging in 1237 UK Biobank patients. Retinal vasculature features, such as curvature, tortuosity and branching angles were extracted from segmented vessels, arteries and veins to enable high-risk subgroup identification. As a result, the tool outperformed traditional clinical predictors, the researchers reported.1
They said RetHemo demonstrated significant predictive performance for leukemia (c-index = 0.611, HR = 2.45, 95% CI: 1.27-4.75, p = 0.027), myeloma (c-index = 0.636, HR = 6.69, 95% CI: 2.06-21.65, p = 0.006).
“Unsupervised hierarchical clustering based on retinal vasculature features identified distinct high-risk subgroups for leukemia (p = 0.013), myeloma (p < 0.001), and lymphoma (p = 0.034),” the authors wrote. “Serum proteomics analysis revealed significantly elevated levels of inflammatory proteins, including ITGAL and SLAMF7, in high-risk patients. Comparison with clinical variables showed that RetHemo outperformed traditional clinical and hematologic parameters in stratifying at-risk individuals.”
The authors said their findings support the potential of AI-driven retinal biomarkers as a novel prognostic tool for early detection of hematological malignancies, “enabling timely intervention and improved patient outcomes.”
- .Singh A, Nooka AK, Modanwal G, Jain N, Dhodapkar MV, Arepalli S, Lonial S, Madabhushi A. AI-informed retinal biomarkers predict 10-year risk of onset of multiple hematological malignancies. Eur J Cancer. 2025 Oct 16;229:115752. doi: 10.1016/j.ejca.2025.115752. Epub 2025 Aug 30. PMID: 40925094; PMCID: PMC12434684.