Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters

Kuo-Yang Huang; Ying-Lin Hsu; Huang-Chi Chen; Ming-Hwarng Horng; Che-Liang Chung; Ching-Hsiung Lin; Jia-Lang Xu; Ming-Hon Hou

doi:10.3389/fmed.2023.1167445

Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters

Front Med (Lausanne). 2023 May 9:10:1167445. doi: 10.3389/fmed.2023.1167445. eCollection 2023.

Authors

Kuo-Yang Huang^{1

2

3

4}, Ying-Lin Hsu⁵, Huang-Chi Chen⁶, Ming-Hwarng Horng⁶, Che-Liang Chung⁶, Ching-Hsiung Lin^{1

3

7}, Jia-Lang Xu², Ming-Hon Hou^{1

3

4

8

9}

Affiliations

¹ Division of Chest Medicine, Department of Internal Medicine, Changhua Christian Hospital, Changhua, Taiwan.
² Artificial Intelligence Development Center, Changhua Christian Hospital, Changhua, Taiwan.
³ Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung, Taiwan.
⁴ Ph.D. Program in Medical Biotechnology, National Chung Hsing University, Taichung, Taiwan.
⁵ Department of Applied Mathematics, Institute of Statistics, National Chung Hsing University, Taichung, Taiwan.
⁶ Division of Chest Medicine, Department of Internal Medicine, Yuanlin Christian Hospital, Changhua, Taiwan.
⁷ Department of Recreation and Holistic Wellness, MingDao University, Changhua, Taiwan.
⁸ Graduate Institute of Biotechnology, National Chung Hsing University, Taichung, Taiwan.
⁹ Department of Life Sciences, National Chung Hsing University, Taichung, Taiwan.

Abstract

Background: Successful weaning from mechanical ventilation is important for patients admitted to intensive care units. However, models for predicting real-time weaning outcomes remain inadequate. Therefore, this study aimed to develop a machine-learning model for predicting successful extubation only using time-series ventilator-derived parameters with good accuracy.

Methods: Patients with mechanical ventilation admitted to the Yuanlin Christian Hospital in Taiwan between August 2015 and November 2020 were retrospectively included. A dataset with ventilator-derived parameters was obtained before extubation. Recursive feature elimination was applied to select the most important features. Machine-learning models of logistic regression, random forest (RF), and support vector machine were adopted to predict extubation outcomes. In addition, the synthetic minority oversampling technique (SMOTE) was employed to address the data imbalance problem. The area under the receiver operating characteristic (AUC), F1 score, and accuracy, along with the 10-fold cross-validation, were used to evaluate prediction performance.

Results: In this study, 233 patients were included, of whom 28 (12.0%) failed extubation. The six ventilatory variables per 180 s dataset had optimal feature importance. RF exhibited better performance than the others, with an AUC value of 0.976 (95% confidence interval [CI], 0.975-0.976), accuracy of 94.0% (95% CI, 93.8-94.3%), and an F1 score of 95.8% (95% CI, 95.7-96.0%). The difference in performance between the RF and the original and SMOTE datasets was small.

Conclusion: The RF model demonstrated a good performance in predicting successful extubation in mechanically ventilated patients. This algorithm made a precise real-time extubation outcome prediction for patients at different time points.

Keywords: extubation; intensive care unit; machine learning; mechanical ventilation; prediction model.