Redefining cardiometabolic biomarkers in the big data era: toward a personalized medicine-centered reconstruction of risk prediction models

Description

Xin-zhe Jiang and colleagues argue that heart-and-metabolism risk prediction needs rebuilding in the big-data era. Today's models lean on group averages and fixed cut-offs for cholesterol, glucose, and blood pressure, which misses how differently people progress. Their 2026 perspective proposes treating biomarkers as moving anchors tracing a person's trajectory, network state, and treatment response, rather than one-off pass-or-fail readings.

The framework stitches together repeated biomarker monitoring, multi-omics data, wearable sensors, and health records, then adds causal inference, personal reference ranges, and self-updating models. Digital twins, computational stand-ins for a patient's biology, would let doctors test treatments on a model first. The authors are candid about the hurdles: merging messy data, handling gaps, keeping models clear and fair, and satisfying regulators. Their closing priorities include long-term biomarker banks, shared data systems, diverse validation cohorts, and decision tools doctors will use.

Catalog record

Source: https://europepmc.org/article/MED/PMC13457394