A Simple Weaning Model Based on Interpretable Machine Learning Algorithm for Patients With Sepsis: A Research of MIMIC-IV and eICU Databases

Wanjun Liu; Gan Tao; Yijun Zhang; Wenyan Xiao; Jin Zhang; Yu Liu; Zongqing Lu; Tianfeng Hua; Min Yang

doi:10.3389/fmed.2021.814566

A Simple Weaning Model Based on Interpretable Machine Learning Algorithm for Patients With Sepsis: A Research of MIMIC-IV and eICU Databases

Front Med (Lausanne). 2022 Jan 18:8:814566. doi: 10.3389/fmed.2021.814566. eCollection 2021.

Authors

Wanjun Liu^{1

2}, Gan Tao¹, Yijun Zhang^{1

2}, Wenyan Xiao^{1

2}, Jin Zhang^{1

2}, Yu Liu³, Zongqing Lu^{1

2}, Tianfeng Hua^{1

2}, Min Yang^{1

2}

Affiliations

¹ The 2nd Department of Intensive Care Unit, The Second Affiliated Hospital of Anhui Medical University, Hefei, China.
² The Laboratory of Cardiopulmonary Resuscitation and Critical Care Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, China.
³ Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei, China.

Abstract

Background: Invasive mechanical ventilation plays an important role in the prognosis of patients with sepsis. However, there are, currently, no tools specifically designed to assess weaning from invasive mechanical ventilation in patients with sepsis. The aim of our study was to develop a practical model to predict weaning in patients with sepsis.

Methods: We extracted patient information from the Medical Information Mart for Intensive Care Database-IV (MIMIC-IV) and the eICU Collaborative Research Database (eICU-CRD). Kaplan-Meier curves were plotted to compare the 28-day mortality between patients who successfully weaned and those who failed to wean. Subsequently, MIMIC-IV was divided into a training set and an internal verification set, and the eICU-CRD was designated as the external verification set. We selected the best model to simplify the internal and external validation sets based on the performance of the model.

Results: A total of 5020 and 7081 sepsis patients with invasive mechanical ventilation in MIMIC-IV and eICU-CRD were included, respectively. After matching, weaning was independently associated with 28-day mortality and length of ICU stay (p < 0.001 and p = 0.002, respectively). After comparison, 35 clinical variables were extracted to build weaning models. XGBoost performed the best discrimination among the models in the internal and external validation sets (AUROC: 0.80 and 0.86, respectively). Finally, a simplified model was developed based on XGBoost, which included only four variables. The simplified model also had good predictive performance (AUROC:0.75 and 0.78 in internal and external validation sets, respectively) and was developed into a web-based tool for further review.

Conclusions: Weaning success is independently related to short-term mortality in patients with sepsis. The simplified model based on the XGBoost algorithm provides good predictive performance and great clinical applicablity for weaning, and a web-based tool was developed for better clinical application.

Keywords: XGBoost; invasive mechanical ventilation; sepsis; simple prediction model; weaning.