An evolutionary approach to continuously estimate CPR quality parameters from a wrist-worn inertial sensor

Abstract Cardiopulmonary resuscitation (CPR) is one of the most critical emergency interventions for sudden cardiac arrest. In this paper, a robust sinusoidal model-fitting method based on Evolution Strategy inspired algorithm CPR quality parameters – naming chest compression frequency and depth as measured by an inertial measurement unit (IMU) attached to wrist presented. The proposed approach will allow bystanders improve part continuous closed-loop support system once integrated into smartphone or smartwatch application. By evaluating model’s precision with data recorded training mannequin reference standard, variance $$\pm 2.22$$ ± 2.22 compressions per minute (cpm) has been found IMU wrist. It was that previously unconsidered position thus, use smartwatches suitable alternative typical placement phones in hand training.