Integrating Long-Read Sequencing with Imaging Biomarkers for Stroke Risk Prediction: Interpretability, Bias, and Real-World Performance with Implementation and Equity Considerations

Serunjogi Ruth

Department of Clinical Pharmacy Kampala International University Uganda

Email: ruth.serunjogi@studwc.kiu.ac.ug

ABSTRACT

Ischemic stroke remains a leading cause of mortality and long-term disability worldwide, with risk prediction constrained by incomplete characterization of biological heterogeneity and limited integration of high-dimensional data. Advances in long-read genomic sequencing and neuroimaging now enable comprehensive profiling of structural variants, haplotypes, epigenetic signals, and imaging biomarkers directly linked to cerebrovascular pathology. This paper examines the integration of long-read sequencing data with imaging biomarkers for stroke risk prediction, with particular emphasis on interpretability, bias, real-world performance, and equity-oriented implementation. We review methodological foundations for multimodal data fusion, feature extraction from long-read sequencing, and quantitative imaging biomarker analysis, highlighting the complementary biological insights each modality provides. We further analyze modeling strategies that balance predictive performance with clinical interpretability, including fairness-aware machine-learning approaches to address demographic and technical biases. Real-world validation challenges, external generalizability, calibration, and clinical utility are critically assessed, alongside governance, privacy, and regulatory considerations. By situating genomic imaging integration within healthcare system constraints and equity frameworks, this work outlines a translational pathway for responsible deployment. We conclude that integrative genomic imaging models hold substantial promise for improving stroke risk stratification, provided that interpretability, bias mitigation, and equitable access are embedded throughout model development and implementation.

Keywords: Ischemic stroke, Long-read sequencing, Imaging biomarkers, Multimodal risk prediction, Health equity and fairness

CITE AS: Serunjogi Ruth (2026). Integrating Long-Read Sequencing with Imaging Biomarkers for Stroke Risk Prediction: Interpretability, Bias, and Real-World Performance with Implementation and Equity Considerations. IAA Journal of Biological Sciences 14(1):87-97. https://doi.org/10.59298/IAAJB/2026/1418797