Cardio-metabolic risk modeling and assessment through sensor-based measurements

Area of Science:

• Biomedical Engineering
• Preventive Cardiology
• Health Informatics

Background:

• Cardio-metabolic diseases pose a significant global health burden.
• Effective risk assessment is crucial for disease prevention in the general population.
• Current assessment methods may have limitations in accessibility and continuous monitoring.

Purpose of the Study:

• To define a strategy for out-of-hospital cardio-metabolic risk assessment.
• To utilize data from contactless sensors for risk evaluation.
• To correlate sensor-based measurements with established clinical risk factors.

Main Methods:

• Structural Equation Modeling (SEM) was employed to identify latent cardio-metabolic risk variables.
• Key variables included anthropometric, glycolipidic, and vascular function factors.
• Sensor-based measurements were developed to correlate with these clinical latent variables.

Main Results:

• The developed strategy accurately identified subjects with one or more cardio-metabolic risk factors.
• The system achieved an accuracy of 82.4%, sensitivity of 82.5%, and specificity of 82.1% in a cohort of 68 healthy volunteers.
• Results were derived from the EU-funded SEMEOTICONS project.

Conclusions:

• Preliminary findings support the utility of self-monitoring systems for cardio-metabolic risk prevention.
• Contactless sensor technology offers a promising avenue for accessible, out-of-hospital risk assessment.
• Further validation and implementation of these systems could enhance public health strategies.