Abstrakti
Cardiopulmonary resuscitation (CPR) is a crucial life-saving technique commonly administered to individuals experiencing cardiac arrest. Among the important aspects of CPR is ensuring the correct airway position of the patient, which is typically monitored by human tutors or supervisors. This study aims to utilize deep transfer learning for the detection of the patient's correct and incorrect airway position during cardiopulmonary resuscitation. To address the challenge of identifying the airway position, we curated a dataset consisting of 198 recorded video sequences, each lasting 6–8 s, showcasing both correct and incorrect airway positions during mouth-to-mouth breathing and breathing with an Ambu Bag. We employed six cutting-edge deep networks, namely DarkNet19, EfficientNetB0, GoogleNet, MobileNet-v2, ResNet50, and NasnetMobile. These networks were initially pre-trained on computer vision data and subsequently fine-tuned using the CPR dataset. The validation of the fine-tuned networks in detecting the patient's correct airway position during mouth-to-mouth breathing achieved impressive results, with the best sensitivity (98.8 %), specificity (100 %), and F-measure (97.2 %). Similarly, the detection of the patient's correct airway position during breathing with an Ambu Bag exhibited excellent performance, with the best sensitivity (100 %), specificity (99.8 %), and F-measure (99.7 %).
Alkuperäiskieli | englanti |
---|---|
Artikkeli | 104179 |
Lehti | Medical Engineering and Physics |
Vuosikerta | 129 |
Sivumäärä | 9 |
ISSN | 1350-4533 |
DOI - pysyväislinkit | |
Tila | Julkaistu - heinäk. 2024 |
OKM-julkaisutyyppi | A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä, vertaisarvioitu |
Lisätietoja
Publisher Copyright:
© 2024 The Author(s)
Tieteenalat
- 113 Tietojenkäsittely- ja informaatiotieteet
- 3111 Biolääketieteet
Pääsy asiakirjaan
10.1016/j.medengphy.2024.104179Lisenssi: CC BY
Patient’s airway monitoringLopullinen julkaistu versio, 7,74 MBLisenssi: CC BY
Siteeraa tätä
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
Marhamati, M., Dorry, B., Imannezhad, S., Hussain, M. A., Neshat, A. A., Kalmishi, A. (2024). Patient's airway monitoring during cardiopulmonary resuscitation using deep networks. Medical Engineering and Physics, 129, Artikkeli 104179. https://doi.org/10.1016/j.medengphy.2024.104179
Marhamati, Mahmoud ; Dorry, Behnam ; Imannezhad, Shima et al. / Patient's airway monitoring during cardiopulmonary resuscitation using deep networks. Julkaisussa: Medical Engineering and Physics. 2024 ; Vuosikerta 129.
@article{a9e87891ca32422897ca0a42008e7c32,
title = "Patient's airway monitoring during cardiopulmonary resuscitation using deep networks",
abstract = "Cardiopulmonary resuscitation (CPR) is a crucial life-saving technique commonly administered to individuals experiencing cardiac arrest. Among the important aspects of CPR is ensuring the correct airway position of the patient, which is typically monitored by human tutors or supervisors. This study aims to utilize deep transfer learning for the detection of the patient's correct and incorrect airway position during cardiopulmonary resuscitation. To address the challenge of identifying the airway position, we curated a dataset consisting of 198 recorded video sequences, each lasting 6–8 s, showcasing both correct and incorrect airway positions during mouth-to-mouth breathing and breathing with an Ambu Bag. We employed six cutting-edge deep networks, namely DarkNet19, EfficientNetB0, GoogleNet, MobileNet-v2, ResNet50, and NasnetMobile. These networks were initially pre-trained on computer vision data and subsequently fine-tuned using the CPR dataset. The validation of the fine-tuned networks in detecting the patient's correct airway position during mouth-to-mouth breathing achieved impressive results, with the best sensitivity (98.8 %), specificity (100 %), and F-measure (97.2 %). Similarly, the detection of the patient's correct airway position during breathing with an Ambu Bag exhibited excellent performance, with the best sensitivity (100 %), specificity (99.8 %), and F-measure (99.7 %).",
keywords = "Artificial intelligence, Cardiopulmonary resuscitation, CPR, Deep learning, Transfer learning, 113 Computer and information sciences, 3111 Biomedicine",
author = "Mahmoud Marhamati and Behnam Dorry and Shima Imannezhad and Hussain, {Mohammad Arafat} and Neshat, {Ali Asghar} and Abulfazl Kalmishi and Mohammad Momeny",
note = "Publisher Copyright: {\textcopyright} 2024 The Author(s)",
year = "2024",
month = jul,
doi = "10.1016/j.medengphy.2024.104179",
language = "English",
volume = "129",
journal = "Medical Engineering and Physics",
issn = "1350-4533",
publisher = "ELSEVIER SCI IRELAND LTD",
}
Marhamati, M, Dorry, B, Imannezhad, S, Hussain, MA, Neshat, AA, Kalmishi, A 2024, 'Patient's airway monitoring during cardiopulmonary resuscitation using deep networks', Medical Engineering and Physics, Vuosikerta 129, 104179. https://doi.org/10.1016/j.medengphy.2024.104179
Patient's airway monitoring during cardiopulmonary resuscitation using deep networks. / Marhamati, Mahmoud; Dorry, Behnam; Imannezhad, Shima et al.
julkaisussa: Medical Engineering and Physics, Vuosikerta 129, 104179, 07.2024.
Tutkimustuotos: Artikkelijulkaisu › Artikkeli › Tieteellinen › vertaisarvioitu
TY - JOUR
T1 - Patient's airway monitoring during cardiopulmonary resuscitation using deep networks
AU - Marhamati, Mahmoud
AU - Dorry, Behnam
AU - Imannezhad, Shima
AU - Hussain, Mohammad Arafat
AU - Neshat, Ali Asghar
AU - Kalmishi, Abulfazl
AU - Momeny, Mohammad
N1 - Publisher Copyright:© 2024 The Author(s)
PY - 2024/7
Y1 - 2024/7
N2 - Cardiopulmonary resuscitation (CPR) is a crucial life-saving technique commonly administered to individuals experiencing cardiac arrest. Among the important aspects of CPR is ensuring the correct airway position of the patient, which is typically monitored by human tutors or supervisors. This study aims to utilize deep transfer learning for the detection of the patient's correct and incorrect airway position during cardiopulmonary resuscitation. To address the challenge of identifying the airway position, we curated a dataset consisting of 198 recorded video sequences, each lasting 6–8 s, showcasing both correct and incorrect airway positions during mouth-to-mouth breathing and breathing with an Ambu Bag. We employed six cutting-edge deep networks, namely DarkNet19, EfficientNetB0, GoogleNet, MobileNet-v2, ResNet50, and NasnetMobile. These networks were initially pre-trained on computer vision data and subsequently fine-tuned using the CPR dataset. The validation of the fine-tuned networks in detecting the patient's correct airway position during mouth-to-mouth breathing achieved impressive results, with the best sensitivity (98.8 %), specificity (100 %), and F-measure (97.2 %). Similarly, the detection of the patient's correct airway position during breathing with an Ambu Bag exhibited excellent performance, with the best sensitivity (100 %), specificity (99.8 %), and F-measure (99.7 %).
AB - Cardiopulmonary resuscitation (CPR) is a crucial life-saving technique commonly administered to individuals experiencing cardiac arrest. Among the important aspects of CPR is ensuring the correct airway position of the patient, which is typically monitored by human tutors or supervisors. This study aims to utilize deep transfer learning for the detection of the patient's correct and incorrect airway position during cardiopulmonary resuscitation. To address the challenge of identifying the airway position, we curated a dataset consisting of 198 recorded video sequences, each lasting 6–8 s, showcasing both correct and incorrect airway positions during mouth-to-mouth breathing and breathing with an Ambu Bag. We employed six cutting-edge deep networks, namely DarkNet19, EfficientNetB0, GoogleNet, MobileNet-v2, ResNet50, and NasnetMobile. These networks were initially pre-trained on computer vision data and subsequently fine-tuned using the CPR dataset. The validation of the fine-tuned networks in detecting the patient's correct airway position during mouth-to-mouth breathing achieved impressive results, with the best sensitivity (98.8 %), specificity (100 %), and F-measure (97.2 %). Similarly, the detection of the patient's correct airway position during breathing with an Ambu Bag exhibited excellent performance, with the best sensitivity (100 %), specificity (99.8 %), and F-measure (99.7 %).
KW - Artificial intelligence
KW - Cardiopulmonary resuscitation
KW - CPR
KW - Deep learning
KW - Transfer learning
KW - 113 Computer and information sciences
KW - 3111 Biomedicine
U2 - 10.1016/j.medengphy.2024.104179
DO - 10.1016/j.medengphy.2024.104179
M3 - Article
AN - SCOPUS:85194079562
SN - 1350-4533
VL - 129
JO - Medical Engineering and Physics
JF - Medical Engineering and Physics
M1 - 104179
ER -
Marhamati M, Dorry B, Imannezhad S, Hussain MA, Neshat AA, Kalmishi A et al. Patient's airway monitoring during cardiopulmonary resuscitation using deep networks. Medical Engineering and Physics. 2024 heinä;129:104179. doi: 10.1016/j.medengphy.2024.104179