Development and validation of an artificial intelligence algorithm for detecting vocal cords in video laryngoscopy.

Airway procedures in life-threatening situations are vital for saving lives. Video laryngoscopy (VL) is commonly performed during endotracheal intubation (ETI) in the emergency department. Artificial intelligence (AI) is widely used in the medical field, particularly to detect anatomical structures. This study aimed to develop an AI algorithm that detects vocal cords from VL images acquired during emergent situations. This retrospective study used VL images acquired in the emergency department to facilitate the ETI. The vocal cord image was labeled with a ground-truth bounding box. The dataset was divided into training and validation datasets. The algorithm was developed from a training dataset using the YOLOv4 model. The performance of the algorithm was evaluated using a test set. The test set was further divided into specific environments during the ETI for clinical subgroup analysis. In total, 20,161 images from 84 patients were used in this study. A total of 10,287, 5766, and 4108 images were used for the model training, validation, and test sets, respectively. The developed algorithm achieved F1 score 0.906, sensitivity 0.963, and specificity 0.842 in the validation set. The performance in the test set was F1 score 0.808, sensitivity 0.823, and specificity 0.804. We developed and validated an AI algorithm to detect vocal cords in VL. This algorithm demonstrated a high performance. The algorithm can be used to determine the vocal cord to ensure safe ETI.

Evaluation of the conventional and modified aerosol boxes during tracheal intubation in normal and difficult airways: a randomized, crossover, manikin simulation study.

The aim of this study was to evaluate conventional and modified aerosol boxes in terms of intubation time, first-pass intubation success, and mouth-to-mouth distance between the laryngoscopist and patient during tracheal intubation in simulated patients with normal and difficult airways. Sixteen anesthesiologists performed tracheal intubations with direct laryngoscope or three different videolaryngoscopes (McGRATH MAC videolaryngoscope, C-MAC videolaryngoscope, and Pentax-AWS) without an aerosol box or with a conventional or a modified aerosol boxes in simulated manikins with normal and difficult airways. Intubation time, first-pass intubation success, and mouth-to-mouth distance during tracheal intubation were recorded. Compared to no aerosol box, the use of a conventional aerosol box significantly increased intubation time in both normal and difficult airways (Bonferroni-corrected P-value (Pcorrected) = 0.005 and Pcorrected = 0.003, respectively). Intubation time was significantly shorter with the modified aerosol box than with the conventional one for both normal and difficult airways (Pcorrected = 0.003 and Pcorrected = 0.011, respectively). However, no significant differences were found in intubation time between no aerosol box and the modified aerosol box for normal and difficult airways (Pcorrected = 0.336 and Pcorrected = 0.112, respectively). The use of conventional or modified aerosol boxes significantly extended the mouth-to-mouth distances compared to not using an aerosol box during tracheal intubation with each laryngoscope (all Pcorrected < 0.05), and the distances were not different between the conventional and modified boxes in normal and difficult airways. The use of modified aerosol box did not increase intubation time and could help maintain a distance from the simulated patients with normal and difficult airways.

Association between prehospital field to emergency department delta shock index and in-hospital mortality in patients with torso and extremity trauma: A multinational, observational study.

Hemorrhage, a main cause of mortality in patients with trauma, affects vital signs such as blood pressure and heart rate. Shock index (SI), calculated as heart rate divided by systolic blood pressure, is widely used to estimate the shock status of patients with hemorrhage. The difference in SI between the emergency department and prehospital field can indirectly reflect urgency after trauma. We aimed to determine the association between delta SI (DSI) and in-hospital mortality in patients with torso or extremity trauma. Patients with DSI >0.1 are expected to be associated with high mortality. This retrospective, observational study used data from the Pan-Asian Trauma Outcomes Study. Patients aged 18-85 years with abdomen, chest, upper extremity, lower extremity, or external injury location were included. Patients from China, Indonesia, Japan, Philippines, Thailand, and Vietnam; those who were transferred from another facility; those who were transferred without the use of emergency medical service; those with prehospital cardiac arrest; those with unknown exposure and outcomes were excluded. The exposure and primary outcome were DSI and in-hospital mortality, respectively. The secondary and tertiary outcome was intensive care unit (ICU) admission and massive transfusion, respectively. Multivariate logistic regression analysis was performed to test the association between DSI and outcome. In total, 21,534 patients were enrolled according to the inclusion and exclusion criteria. There were 3,033 patients with DSI >0.1. The in-hospital mortality rate in the DSI >0.1 and ≤0.1 groups was 2.0% and 0.8%, respectively. In multivariate logistic regression analysis, the DSI ≤0.1 group was considered the reference group. The unadjusted and adjusted odds ratios of in-hospital mortality in the DSI >0.1 group were 2.54 (95% confidence interval [CI] 1.88-3.42) and 2.82 (95% CI 2.08-3.84), respectively. The urgency of traumatic hemorrhage can be determined using DSI, which can help hospital staff to provide proper trauma management, such as early trauma surgery or embolization.