Staying Alive - CPR Quality Parameters from Wrist-worn Inertial Sensor Data with Evolutionary Fitted Sinusoidal Models

TL;DR

This paper introduces a robust sinusoidal model fitting method using Differential Evolution to accurately measure CPR quality parameters from wrist-worn inertial sensors, enabling improved real-time feedback via smartphones or smartwatches.

Contribution

It presents a novel DE-based sinusoidal fitting algorithm for wrist sensor data to determine CPR compression frequency and depth, suitable for mobile health applications.

Findings

Low variance in compression frequency measurement of ±2.0 cpm

Wrist placement is a viable alternative for CPR training sensors

Algorithm enables real-time CPR quality assessment in mobile devices

Abstract

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.