Reinforcement Learning-Driven Personalized Guided Breathing for Blood Pressure Reduction
Abstract
We present a real-time reinforcement learning system that personalizes guided breathing using Pulse Transit Time and EEG feedback. In a three-month feasibility study, adaptive breathing doubled the systolic pressure reduction of slow fixed-rate breathing, demonstrating effectiveness and sustained benefit.
Fields of Study & Subjects
Non-Invasive Vital Sign Monitoring
Heart Rate Variability and Autonomic Control
Blood Pressure and Hypertension Studies
Publication details
- Publication date
- 27 February 2026
- Language
- EN
- Document type
- Preprint