Patient's airway monitoring during cardiopulmonary resuscitation using deep networks

• Published in: Medical engineering & physics 2024-07, Vol.129, p.104179, Article 104179
• Main Authors: Marhamati, Mahmoud, Dorry, Behnam, Imannezhad, Shima, Hussain, Mohammad Arafat, Neshat, Ali Asghar, Kalmishi, Abulfazl, Momeny, Mohammad
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Cardiopulmonary Resuscitation; CPR; Deep Learning; Humans; Monitoring, Physiologic - instrumentation; Monitoring, Physiologic - methods; Respiration; Transfer learning
• ISSN: 1350-4533; 1873-4030; 1873-4030
• DOI: 10.1016/j.medengphy.2024.104179

•Providing non-human expert feedback on CPR performance using artificial intelligence.•Detecting the correct and incorrect position of patient's airway during CPR administration.•Building a dataset consisting of 198 recorded video sequences, each lasting 6–8 s, showcasing airway positions.•Employing six cutting-edge deep networks to fine-tune using out CPR dataset.•Enhancing the effectiveness of emergency response teams long-term effects of CPR using deep transfer learning. 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 %).