Abstract

The wearable sensor platform proposed in CONVERGENCE is centred on energy efficient wearable proof-of-concepts at system level exploiting data analytics developed in a context driven approach (in contrast with more traditional research where the device level research and the data analytics are carried out on separate path, rarely converging). Here we choose realistic wearable form factors for our energy efficient systems such as wrist-based and patch-based devices. Their advancements, as autonomous systems is foreseen in CONVERGENCE to offer unique solutions for new generations of frictionless (non-invasive) quasi-continuous healthcare and environmental monitoring. At long term, the CONVERGENCE platform will form the basis for new generations of human-machine interfaces. Such energy efficient, wireless and multifunctional wearable systems will beneficially track and interact with the end-user through appropriate feedback channels on a daily basis. They will enable personalized advice and assistance promoting healthier lifestyle and improved healthcare prevention, far beyond what today’s wireless sensor networks are capable of providing.

Objectives

The CONVERGENCE project supports holistically - by multiple efforts at technology, system integration, algorithms and data analytics levels - the advancement of early detection, minimization of risks and prevention-based healthcare and lifestyle, based on the deployment of some focused embodiments of wearable technology for interactive monitoring and assessment. CONVERGENCE advocates success via a multidisciplinary and holistic vision of convergent wearable technology designed by engineers with the insight of medical professionals and exploiting strong scientific expertise of academic partners. CONVERGENCE endeavours to exploit these new technologies potential of multi-parameter continuous monitoring in everyday life for true preventive medicine and a new Quality-of-Life. Moreover, this initiative has the ambition to create and develop at European scale a diverse community and network of research partners to generate new research ideas and innovation.

Estimated results

A predictive personalized model for cardiovascular risk assessment: a patient-specific multiscale reduced-order blood flow model of the entire systemic circulation will be employed, which is personalized from a set of initial measurements (height, weight, BMI, gender, length of arms, legs, neck, head, etc.) and a set of continuous measurements derived from wearable sensors. These measurements are used together with the a priori personalized arterial geometry to run fully personalized hemodynamic computations. The outputs of the hemodynamic computations are: time-varying flow rate, pressure and cross-sectional area at all locations in the systemic arterial tree. Based on these quantities the measures of interest are extracted, which may be onset of hypertension, risk of CVD, central aortic blood pressure, severity of peripheral artery disease, severity of coarctation, etc.