Accelerometry-Derived Digital Biomarkers for Cardiometabolic Risk: A Population-Representative Tabular Benchmark with Uncertainty Quantification
arXiv:2606.30702v1 Announce Type: new Abstract: Structured tabular data dominates clinical medicine, yet existing benchmarks fail to reflect real-world properties like complex survey sampling, demographic oversampling, and subgroup fairness. We introduce the NHANES Accelerometry Cardiometabolic Benchmark, derived from NHANES 2003-2006, comprising 1,381 adults with hip-worn accelerometry, fasting laboratory biomarkers, dietary intake, and anthropometrics. We evaluate three tabular learning methods -- ridge regression, XGBoost, and the foundation model TabPFN v2 -- to predict glycated haemoglobi
The proliferation of wearable sensors and the increasing maturity of AI/ML techniques for health data analysis are converging, enabling more sophisticated biomarker derivation.
This development allows for earlier and more widespread detection of cardiometabolic risk, moving towards preventative healthcare models and personalized interventions at scale.
Clinical medicine gains a new population-representative benchmark for non-invasive, objective risk assessment derived from everyday activity data, challenging reliance on traditional, episodic clinic visits.
- · Preventative healthcare industry
- · Wearable tech companies
- · Patients at risk of cardiometabolic diseases
- · Public health researchers
- · Traditional diagnostic labs relying solely on blood tests
- · Healthcare systems optimized for reactive treatment
- · Companies with less sophisticated data integration strategies
Widespread adoption of accelerometry-derived digital biomarkers in routine health screenings.
Insurance companies begin integrating these biomarkers for personalized premium adjustments and health management programs.
Public health policy shifts towards incentivizing activity and early intervention based on continuous digital biomarker monitoring, transforming health behaviors.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG