Introduction of Infection Prevention Tracheal Intubation Protocol during the COVID-19 Pandemic Is Not Associated with First-Pass Success Rates of Endotracheal Intubation in the Emergency Department: A Before-and-After Comparative Study

Background Since there is a limited ability to identify the need for intubation in the ICU, the objective of this study was to develop and validate an interpretable machine learning (ML) model to predict the need for intubation in ICU patients. Methods Seven widely used ML algorithms were applied to develop and validate prediction models. Adult patients from the Medical Information Mart for Intensive Care IV database who stayed in the ICU for longer than 24 hours were involved in developing the model. The model was then externally validated in the eICU-CRD database. In addition, the SHapley Additive exPlanations (SHAP) method was employed to illustrate the effects of the individual features attributed to the prediction model. Results A total of 11988 patients were included in the final cohort for this study. Among the seven constructed models, the CatBoost model achieved the best performance (AUC: 0.863). In the external validation, the efficacy of our model was also observed (AUC: 0.722). The Glasgow Coma Scale (GCS), body mass index (BMI), arterial partial pressure of oxygen (PaO2) and respiratory rate (RR) were the top 4 features of the CatBoost model with the greatest impact. Conclusions We have demonstrated the potential of machine-learning approaches for predicting the need for intubation in ICU patients. The SHAP method could improve the interpretability of machine-learning models and help clinicians better understand the reasoning behind the outcome. Trial registration: Not applicable.

show abstract

Impact of the Coronavirus Pandemic on Patients Requiring Tracheal Intubation by Helicopter Emergency Medical Services: A Retrospective, Single-Center, Observational Study

Hayashi,

Kikuchi,

Hishinuma

et al. 2024

JCM

View full text Add to dashboard Cite

Background/Objectives: The impacts of the coronavirus disease 2019 (COVID-19) pandemic on patients using helicopter emergency medical services (HEMS) regarding tracheal intubation and patient management remain unclear. Thus, we aimed to investigate this matter in Japan. Methods: In this retrospective, observational study, we analyzed 2277 patients who utilized HEMS in Tochigi Prefecture during 2018–2022. We included only patients who required tracheal intubation. We categorized patients from February 2020 to January 2022 in the pandemic group and those from February 2018 to January 2020 in the control group. We compared the interval from arrival at the scene to leaving the scene (on-scene time) and secondary variables between the two groups. Results: A total of 278 eligible patients were divided into the pandemic group (n = 127) and the control group (n = 151). The on-scene time was lower during the pandemic than that before (25.64 ± 9.19 vs. 27.83 ± 8.74 min, p = 0.043). The percentage of patients using midazolam was lower (11.8% vs. 22.5%, p = 0.02) and that of patients using rocuronium bromide was higher (29.1% vs. 6.0%, p < 0.001) during the pandemic. In contrast, the type of intervention other than tracheal intubation and the type of transportation to the hospital did not differ between the groups. Conclusions: The COVID-19 pandemic was associated with changes in the mission time of and the frequency of certain drugs administered by the HEMS. However, the type of intervention and the type of transportation did not differ. Further research is needed on changes in patient prognosis and condition due to the effects of the COVID-19 pandemic.

show abstract

Introduction of Infection Prevention Tracheal Intubation Protocol during the COVID-19 Pandemic Is Not Associated with First-Pass Success Rates of Endotracheal Intubation in the Emergency Department: A Before-and-After Comparative Study

Cited by 3 publications

References 51 publications

Development and external validation of an interpretable machine learning model for the prediction of intubation in the intensive care unit

Development and external validation of an interpretable machine learning model for the prediction of intubation in the intensive care unit

Development and Validation of an Interpretable Machine Learning Model for the Prediction of Intubation in the Intensive Care Unit

Impact of the Coronavirus Pandemic on Patients Requiring Tracheal Intubation by Helicopter Emergency Medical Services: A Retrospective, Single-Center, Observational Study

Contact Info

Product

Resources

About