Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study

Authors

  • Qiangqiang Zhou Department of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, China
  • Xiaoya Liu The Third Affiliated Hospital of Soochow University, Changzhou, Jiangsu, China
  • Huifang Yun Department of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, China
  • Yahong Zhao Department of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, China
  • Kun Shu Department of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, China
  • Yong Chen Department of Anesthesiology, The Affiliated Changzhou Second People's Hospital of Nanjing Medical University, Changzhou, Jiangsu, China
  • Song Chen Department of Orthopedics, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou, Zhejiang Province, China

DOI:

https://doi.org/10.17305/bb.2023.9519

Keywords:

Random forest (RF), neural network (NN), extreme gradient boosting (XGBoost), postoperative sore throat (POST)

Abstract

Postoperative sore throat (POST) is a prevalent complication after general anesthesia and targeting high-risk patients helps in its prevention. This study developed and validated a machine learning model to predict POST. A total number of 834 patients who underwent general anesthesia with endotracheal intubation were included in this study. Data from a cohort of 685 patients was used for model development and validation, while a cohort of 149 patients served for external validation. The prediction performance of random forest (RF), neural network (NN), and extreme gradient boosting (XGBoost) models was compared using comprehensive performance metrics. The Local Interpretable Model-Agnostic Explanations (LIME) methods elucidated the best-performing model. POST incidences across training, validation, and testing cohorts were 41.7%, 38.4%, and 36.2%, respectively. Five predictors were age, sex, endotracheal tube cuff pressure, endotracheal tube insertion depth, and the time interval between extubation and the first drinking of water after extubation. After incorporating these variables, the NN model demonstrated superior generalization capabilities in predicting POST when compared to the XGBoost and RF models in external validation, achieving an area under the receiver operating characteristic curve (AUROC) of 0.81 (95% CI 0.74–0.89) and a precision–recall curve (AUPRC) of 0.77 (95% CI 0.66–0.86). The model also showed good calibration and clinical usage values. The NN model outperforms the XGBoost and RF models in predicting POST, with potential applications in the healthcare industry for reducing the incidence of this common postoperative complication.

Downloads

Download data is not yet available.
Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study

Downloads

Published

02-05-2024

Issue

Section

Translational and Clinical Research

Categories

How to Cite

1.
Leveraging artificial intelligence to identify high-risk patients for postoperative sore throat: An observational study. Biomol Biomed [Internet]. 2024 May 2 [cited 2024 May 19];24(3):593–605. Available from: https://www.bjbms.org/ojs/index.php/bjbms/article/view/9519