The HeartTech Hub aims to improve prevention, early diagnosis and personalised care for hypertension, heart failure and atrial fibrillation. It combines real-world sensing, AI modelling and community-based cardiovascular imaging to address the limited physiological and behavioural information available between NHS visits. RADAR-base is a core component of its proposed longitudinal data infrastructure. This is intended to bridge the gap between healthcare encounters and the continuous, real-world signals needed for prevention research.

Objectives

The programme plans to extend NHS records with securely collected wearable, smartphone and connected-device data; harmonise heterogeneous measures; and develop multimodal risk indicators, cardiovascular digital twins and adaptive prevention strategies. It will investigate missing-data methods, predictive performance, screening and clinical decision support. The overarching ambition is to detect cardiovascular risk earlier and enable more timely, personalised interventions.

Challenge

Devices differ in sampling frequency, formats, reliability and measurement methods. Missing readings, sensor artefacts and participant disengagement can distort predictions, while sensitive NHS linkage demands robust governance, privacy and interoperability. Acceptability and accessibility across diverse communities are essential. Device-based observations must also be interpreted carefully to avoid confusing gaps in data capture with changes in underlying health.

RADAR-base solution

A bespoke mobile app will capture passive smartphone and wearable signals. A consented on-device conversational AI component is planned for structured health-history collection, with safeguards against providing clinical advice. RADAR-base will ingest, harmonise and temporally align data, supporting enrolment, consent and quality monitoring for gaps and sensor failures. Governed data linkage within the London Secure Data Environment will connect these streams to NHS records for risk modelling and personalised digital twins. The wider programme will explore intelligent MRI and echocardiography in community settings; patients, the public and clinicians will shape deployment. Combining these layers should create a research-ready foundation for longitudinal analysis across otherwise incompatible technologies.

Impact

The infrastructure could enable earlier identification of deterioration, improved risk stratification, targeted screening and personalised prevention. Integration of open-source sensing infrastructure, secure NHS environments and community imaging may support scalable, more accessible cardiovascular care.