From Cuffs to Code: Machine Learning in Non-Invasive Blood Pressure Monitoring.

Area of Science:

• Biomedical Engineering
• Artificial Intelligence in Healthcare
• Cardiovascular Monitoring

Background:

• Accurate blood pressure (BP) measurement is critical for managing hypertension and hypotension, common conditions often asymptomatic until organ damage occurs.
• Traditional cuff-based BP devices are bulky, inconvenient, and provide only intermittent readings, limiting continuous monitoring.
• The need for convenient, continuous BP monitoring is growing for proactive healthcare and patient-centered management.

Purpose of the Study:

• To provide a comprehensive overview of non-invasive BP measurement technologies.
• To emphasize emerging AI and ML-driven methods for BP estimation.
• To discuss trends in continuous and wearable BP monitoring solutions.

Main Methods:

• Review of existing literature on non-invasive BP measurement techniques.
• Focus on AI/ML approaches utilizing physiological signals like electrocardiography (ECG) and photoplethysmography (PPG).
• Analysis of technological evolution towards continuous and cuff-less BP monitoring.

Main Results:

• Significant interest in AI/ML for BP estimation from non-invasive signals.
• Potential for continuous, cuff-less BP monitoring via wearable devices.
• Advancements enabling more dynamic and patient-centered BP assessment.

Conclusions:

• AI and ML-driven technologies represent a significant evolution in non-invasive BP monitoring.
• Emerging solutions promise continuous, cuff-less BP assessment, enhancing patient care.
• Focus remains on conceptual and technological development, with clinical validation ongoing.