A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training System

The objective of this study was to develop a sound recognition-based cardiopulmonary resuscitation (CPR) training system that is accessible, cost-effective, easy-to-maintain and provides accurate CPR feedback. Beep-CPR, a novel device with accordion squeakers that emit high-pitched sounds during com...

Full description

Saved in:
Bibliographic Details
Main Authors: Dong Hyun Choi, Yoon Ha Joo, Ki Hong Kim, Jeong Ho Park, Hyunjin Joo, Hyoun-Joong Kong, Hyunju Lee, Kyoung Jun Song, Sungwan Kim
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Translational Engineering in Health and Medicine
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10613881/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037698156298240
author Dong Hyun Choi
Yoon Ha Joo
Ki Hong Kim
Jeong Ho Park
Hyunjin Joo
Hyoun-Joong Kong
Hyunju Lee
Kyoung Jun Song
Sungwan Kim
author_facet Dong Hyun Choi
Yoon Ha Joo
Ki Hong Kim
Jeong Ho Park
Hyunjin Joo
Hyoun-Joong Kong
Hyunju Lee
Kyoung Jun Song
Sungwan Kim
author_sort Dong Hyun Choi
collection DOAJ
description The objective of this study was to develop a sound recognition-based cardiopulmonary resuscitation (CPR) training system that is accessible, cost-effective, easy-to-maintain and provides accurate CPR feedback. Beep-CPR, a novel device with accordion squeakers that emit high-pitched sounds during compression, was developed. The sounds emitted by Beep-CPR were recorded using a smartphone, segmented into 2-second audio fragments, and then transformed into spectrograms. A total of 6,065 spectrograms were generated from approximately 40 minutes of audio data, which were then randomly split into training, validation, and test datasets. Each spectrogram was matched with the depth, rate, and release velocity of the compression measured at the same time interval by the ZOLL X Series monitor/defibrillator. Deep learning models utilizing spectrograms as input were trained using transfer learning based on EfficientNet to predict the depth (Depth model), rate (Rate model), and release velocity (Recoil model) of compressions. Results: The mean absolute error (MAE) for the Depth model was 0.30 cm (95% confidence interval [CI]: 0.27–0.33). The MAE of the Rate model was 3.6/min (95% CI: 3.2–3.9). For the Recoil model, the MAE was 2.3 cm/s (95% CI: 2.1–2.5). External validation of the models demonstrated acceptable performance across multiple conditions, including the utilization of a newly-manufactured device, a fatigued device, and evaluation in an environment with altered spatial dimensions. We have developed a novel sound recognition-based CPR training system, that accurately measures compression quality during training. Significance: Beep-CPR is a cost-effective and easy-to-maintain solution that can improve the efficacy of CPR training by facilitating decentralized at-home training with performance feedback.
format Article
id doaj-art-e2f0196bdedd43f1b4ca162908850842
institution DOAJ
issn 2168-2372
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Translational Engineering in Health and Medicine
spelling doaj-art-e2f0196bdedd43f1b4ca1629088508422025-08-20T02:56:47ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722024-01-011255055710.1109/JTEHM.2024.343344810613881A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training SystemDong Hyun Choi0https://orcid.org/0000-0001-6036-1404Yoon Ha Joo1https://orcid.org/0000-0002-2133-6297Ki Hong Kim2https://orcid.org/0000-0003-2115-0078Jeong Ho Park3https://orcid.org/0000-0001-6330-9820Hyunjin Joo4Hyoun-Joong Kong5Hyunju Lee6Kyoung Jun Song7Sungwan Kim8https://orcid.org/0000-0002-9318-849XDepartment of Biomedical Engineering, Seoul National University College of Medicine, Jongno, Seoul, South KoreaBiomedical Research Institute, Seoul National University Hospital, Jongno, Seoul, South KoreaDepartment of Emergency Medicine, Seoul National University Hospital, Jongno, Seoul, South KoreaDepartment of Emergency Medicine, Seoul National University Hospital, Jongno, Seoul, South KoreaInnovative Medical Technology Research Institute, Seoul National University Hospital, Jongno, Seoul, South KoreaDepartment of Transdisciplinary Medicine, Innovative Medical Technology Research Institute, Seoul National University Hospital, Jongno, Seoul, South KoreaLaboratory of Emergency Medical Services, Biomedical Research Institute, Seoul National University Hospital, Jongno, Seoul, South KoreaDepartment of Emergency Medicine, Seoul Metropolitan Boramae Medical Center, Dongjak, Seoul, South KoreaDepartment of Biomedical Engineering, Seoul National University College of Medicine, Jongno, Seoul, South KoreaThe objective of this study was to develop a sound recognition-based cardiopulmonary resuscitation (CPR) training system that is accessible, cost-effective, easy-to-maintain and provides accurate CPR feedback. Beep-CPR, a novel device with accordion squeakers that emit high-pitched sounds during compression, was developed. The sounds emitted by Beep-CPR were recorded using a smartphone, segmented into 2-second audio fragments, and then transformed into spectrograms. A total of 6,065 spectrograms were generated from approximately 40 minutes of audio data, which were then randomly split into training, validation, and test datasets. Each spectrogram was matched with the depth, rate, and release velocity of the compression measured at the same time interval by the ZOLL X Series monitor/defibrillator. Deep learning models utilizing spectrograms as input were trained using transfer learning based on EfficientNet to predict the depth (Depth model), rate (Rate model), and release velocity (Recoil model) of compressions. Results: The mean absolute error (MAE) for the Depth model was 0.30 cm (95% confidence interval [CI]: 0.27–0.33). The MAE of the Rate model was 3.6/min (95% CI: 3.2–3.9). For the Recoil model, the MAE was 2.3 cm/s (95% CI: 2.1–2.5). External validation of the models demonstrated acceptable performance across multiple conditions, including the utilization of a newly-manufactured device, a fatigued device, and evaluation in an environment with altered spatial dimensions. We have developed a novel sound recognition-based CPR training system, that accurately measures compression quality during training. Significance: Beep-CPR is a cost-effective and easy-to-maintain solution that can improve the efficacy of CPR training by facilitating decentralized at-home training with performance feedback.https://ieeexplore.ieee.org/document/10613881/Cardiopulmonary arrestsound recognitiondeep learningfeedback communications
spellingShingle Dong Hyun Choi
Yoon Ha Joo
Ki Hong Kim
Jeong Ho Park
Hyunjin Joo
Hyoun-Joong Kong
Hyunju Lee
Kyoung Jun Song
Sungwan Kim
A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training System
IEEE Journal of Translational Engineering in Health and Medicine
Cardiopulmonary arrest
sound recognition
deep learning
feedback communications
title A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training System
title_full A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training System
title_fullStr A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training System
title_full_unstemmed A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training System
title_short A Development of a Sound Recognition-Based Cardiopulmonary Resuscitation Training System
title_sort development of a sound recognition based cardiopulmonary resuscitation training system
topic Cardiopulmonary arrest
sound recognition
deep learning
feedback communications
url https://ieeexplore.ieee.org/document/10613881/
work_keys_str_mv AT donghyunchoi adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT yoonhajoo adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT kihongkim adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT jeonghopark adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT hyunjinjoo adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT hyounjoongkong adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT hyunjulee adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT kyoungjunsong adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT sungwankim adevelopmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT donghyunchoi developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT yoonhajoo developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT kihongkim developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT jeonghopark developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT hyunjinjoo developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT hyounjoongkong developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT hyunjulee developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT kyoungjunsong developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem
AT sungwankim developmentofasoundrecognitionbasedcardiopulmonaryresuscitationtrainingsystem