# Estimation of Compression Depth During CPR Using FMCW Radar with Deep Convolutional Neural Network

## TL;DR

A new radar and AI method accurately measures chest compression depth during CPR from a distance, potentially improving survival rates in emergencies.

## Contribution

Combining FMCW radar with DCNNs using Wigner–Ville distribution spectrograms improves compression depth estimation accuracy by 11.5%.

## Key findings

- FMCW radar with DCNNs achieves 0.447 cm RMSE in estimating chest compression depth.
- Wigner–Ville distribution-based models outperform STFT-based models by 11.5% in accuracy.
- The method supports real-time, non-contact CPR monitoring for out-of-hospital cardiac arrest.

## Abstract

What are the main findings?
A novel method using frequency-modulated continuous-wave radar enables remote measurement of chest compression depth during Cardiopulmonary Resuscitation (CPR);Deep convolutional neural network (DCNN) models trained on Wigner–Ville distribution spectrograms achieved the lowest RMSE of 0.447 cm, improving accuracy by 11.5% compared to short-time Fourier transform-based DCNNs.

A novel method using frequency-modulated continuous-wave radar enables remote measurement of chest compression depth during Cardiopulmonary Resuscitation (CPR);

Deep convolutional neural network (DCNN) models trained on Wigner–Ville distribution spectrograms achieved the lowest RMSE of 0.447 cm, improving accuracy by 11.5% compared to short-time Fourier transform-based DCNNs.

What is the implication of the main finding?
The proposed method can be integrated into consumer devices like smartphones for real-time CPR monitoring in out-of-hospital cardiac arrest scenarios;Accurate remote measurement of chest compression depth during Telecommunication-CPR can enhance CPR quality and improve patient survival rates.

The proposed method can be integrated into consumer devices like smartphones for real-time CPR monitoring in out-of-hospital cardiac arrest scenarios;

Accurate remote measurement of chest compression depth during Telecommunication-CPR can enhance CPR quality and improve patient survival rates.

Effective Cardiopulmonary Resuscitation (CPR) requires precise chest compression depth, but current out-of-hospital monitoring technologies face limitations. This study introduces a method using frequency-modulated continuous-wave (FMCW) radar to remotely and accurately monitor chest compressions. FMCW radar captures range, Doppler, and angular data, and we utilize micro-Doppler signatures for detailed motion analysis. By integrating Doppler shifts over time, chest displacement is estimated. We compare a regression model based on maximum Doppler frequency with deep convolutional neural networks (DCNNs) trained on spectrograms generated via short-time Fourier transform (STFT) and the Wigner–Ville distribution (WVD). The regression model achieved a root mean square error (RMSE) of 0.535 cm. The STFT-based DCNN improved accuracy with an RMSE of 0.505 cm, while the WVD-based DCNN achieved the best performance with an RMSE of 0.447 cm, representing an 11.5% improvement over the STFT-based DCNN. These findings highlight the potential of combining FMCW radar and deep learning to provide accurate, real-time chest compression depth measurement during CPR, supporting the development of advanced, non-contact monitoring systems for emergency medical response.