Machine Learning for Prediction of Successful Extubation of Mechanical Ventilated Patients in an Intensive Care Unit: A Retrospective Observational Study
-
- Otaguro Takanobu
- Department of Emergency and Critical Care Medicine, Nippon Medical School
-
- Tanaka Hidenori
- Department of Industrial Administration, Tokyo University of Science
-
- Igarashi Yutaka
- Department of Emergency and Critical Care Medicine, Nippon Medical School
-
- Tagami Takashi
- Department of Emergency and Critical Care Medicine, Nippon Medical School
-
- Masuno Tomohiko
- Department of Emergency and Critical Care Medicine, Nippon Medical School
-
- Yokobori Shoji
- Department of Emergency and Critical Care Medicine, Nippon Medical School
-
- Matsumoto Hisashi
- Department of Emergency and Critical Care Medicine, Nippon Medical School
-
- Ohwada Hayato
- Department of Industrial Administration, Tokyo University of Science
-
- Yokota Hiroyuki
- Department of Emergency and Critical Care Medicine, Nippon Medical School
Search this article
Abstract
<p>Background: Ventilator weaning protocols are commonly implemented for patients receiving mechanical ventilation. However, despite such protocols, the rate of extubation failure remains high. This study analyzed the usefulness and accuracy of machine learning in predicting extubation success. Methods: We retrospectively evaluated data from patients who underwent intubation for respiratory failure and received mechanical ventilation in an intensive care unit (ICU). Information on 57 features, including patient demographics, vital signs, laboratory data, and ventilator data, were extracted. Extubation failure was defined as re-intubation within 72 hours of extubation. For supervised learning, data were labeled as intubation-required or not. We used three learning algorithms (Random Forest, XGBoost, and LightGBM) to predict successful extubation. We also analyzed important features and evaluated the area under curve (AUC) and prediction metrics. Results: Overall, 13 of the 117 included patients required re-intubation. LightGBM had the highest AUC (0.950), followed by XGBoost (0.946) and Random Forest (0.930). The accuracy, precision, and recall performance were 0.897, 0.910, and 0.909 for Random Forest; 0.910, 0.912, and 0.931 for XGBoost; and 0.927, 0.915, and 0.960 for LightGBM, respectively. The most important feature was duration of mechanical ventilation, followed by fraction of inspired oxygen, positive end-expiratory pressure, maximum and mean airway pressures, and Glasgow Coma Scale. Conclusions: Machine learning predicted successful extubation of ICU patients on mechanical ventilation. LightGBM had the best overall performance. Duration of mechanical ventilation was the most important feature in all models.</p>
Journal
-
- Journal of Nippon Medical School
-
Journal of Nippon Medical School 88 (5), 408-417, 2021-10-25
The Medical Association of Nippon Medical School
- Tweet
Details 詳細情報について
-
- CRID
- 1390290088581538944
-
- NII Article ID
- 130008117319
-
- NII Book ID
- AA11563215
-
- ISSN
- 13473409
- 13454676
-
- PubMed
- 33692291
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- IRDB
- Crossref
- PubMed
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed