Staying Alive - CPR Quality Parameters from Wrist-worn Inertial Sensor Data with Evolutionary Fitted Sinusoidal Models
This work addresses the need for accurate CPR guidance for bystanders using smartphones or smartwatches, though it is incremental as it adapts an existing method to a new sensor placement.
The paper tackled the problem of estimating CPR quality parameters (chest compression frequency and depth) from wrist-worn inertial sensor data using a Differential Evolution-based sinusoidal model fitting method, achieving a low variance of ±2.0 cpm for compression frequency compared to a mannequin reference standard.
In this paper, a robust sinusoidal model fitting method based on the Differential Evolution (DE) algorithm for determining cardiopulmonary resuscitation (CPR) quality-parameters - naming chest compression frequency and depth - as measured by an inertial sensor placed at the wrist is presented. Once included into a smartphone or smartwatch app, the proposed algorithm will enable bystanders to improve CPR (as part of a continuous closed-loop support-system). By evaluating the precision of the model with data recorded by a Laerdal Resusci Anne mannequin as reference standard, a low variance for compression frequency of $\pm 2.0$ cpm has been found for the sensor placed at the wrist, making this previously unconsidered position a suitable alternative to the typical placement in the hand for CPR-training smartphone apps.