Frontiers in Cardiovascular Medicine · Published 2026-07-28 · DOI 10.3389/fcvm.2026.1846105
Xin-zhe Jiang, Li-jiao Guo, Ming-tian Zhang, Guang-ling Ji, Hong-tao Liu, Yue Zheng, Jie Zhou
Conventional cardiometabolic risk prediction models rely primarily on population-derived averages and static biomarker thresholds, which inadequately capture individual biological heterogeneity and the dynamic nature of disease progression. Recent advances in multi-omics technologies, wearable sensing, and electronic health records have created new opportunities to move beyond static risk assessment toward individualized and longitudinal disease characterization. In this perspective article, we argue that cardiometabolic biomarkers should be redefined from isolated diagnostic indicators into dynamic biological anchors that reflect temporal trajectories, network-level biological states, and evolving responses to intervention. We propose an integrated translational framework that combines longitudinal biomarker monitoring, multimodal data integration, causal inference, personalized reference intervals, and adaptive risk prediction within a continuously learning precision medicine ecosystem. Within this framework, digital twin models serve as computational representations of individual biological states, enabling dynamic risk assessment and hypothesis generation for personalized intervention strategies.We further discuss key challenges that should be addressed before clinical implementation, including multimodal data harmonization, missing-data management, model interpretability, external validation, algorithmic fairness, data governance, and regulatory oversight. Finally, we outline practical priorities for future development, including longitudinal biomarker repositories, interoperable data infrastructures, diverse validation cohorts, clinician-facing decision-support systems, and prospective evaluation of adaptive biomarker-guided interventions. This perspective article reframes cardiometabolic biomarkers as dynamic components of individualized disease monitoring and decision-making systems, providing a conceptual roadmap for the next generation of precision cardiovascular medicine.
Abstract from DOAJ. Public domain (CC0 1.0).
Read the article at the publisher →
Jiang, X., Guo, L., Zhang, M., et al. (2026). Redefining cardiometabolic biomarkers in the big data era: toward a personalized medicine-centered reconstruction of risk prediction models. Frontiers in Cardiovascular Medicine. https://doi.org/10.3389/fcvm.2026.1846105