Efficacy prediction of noninvasive ventilation failure based on the stacking ensemble algorithm and autoencoder

BMC Medical Informatics and Decision Making

Yu Wang¹  Na Liang²  Chengliang Wang²  Xin Xie²  Jun Duan³ 

[1] Chongqing Health Statistics Information Center, 401120, Chongqing, People’s Republic of China;College of Computer Science, Chongqing University, 400000, Chongqing, People’s Republic of China;Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Chongqing Medical University, 400016, Chongqing, People’s Republic of China;

关键词: Noninvasive ventilation;    SMSN model;    Autoencoder;    Efficacy prediction;   

DOI  :  10.1186/s12911-022-01767-z

来源: Springer

【 摘 要 】

BackgroundEarly prediction of noninvasive ventilation failure is of great significance for critically ill ICU patients to escalate or change treatment. Because clinically collected data are highly time-series correlated and have imbalanced classes, it is difficult to accurately predict the efficacy of noninvasive ventilation for severe patients. This paper aims to precisely predict the failure probability of noninvasive ventilation before or in the early stage (1–2 h) of using it on patients and to explain the correlation of the predicted results.MethodsIn this paper, we proposed a SMSN model (stacking and modified SMOTE algorithm of prediction of noninvasive ventilation failure). In the feature generation stage, we used an autoencoder algorithm based on long short-term memory (LSTM) to automatically extract time series features. In the modelling stage, we adopted a modified SMOTE algorithm to address imbalanced classes, and three classifiers (logistic regression, random forests, and Catboost) were combined with the stacking ensemble algorithm to achieve high prediction accuracy.ResultsData from 2495 patients were used to train the SMSN model. Among them, 80% of 2495 patients (1996 patients) were randomly selected as the training set, and 20% of these patients (499 patients) were chosen as the testing set. The F1 of the proposed SMSN model was 79.4%, and the accuracy was 88.2%. Compared with the traditional logistic regression algorithm, the F1 and accuracy were improved by 4.7% and 1.3%, respectively.ConclusionsThrough SHAP analysis, oxygenation index, pH and H1FIO2 collected after 1 h of noninvasive ventilation were the most relevant features affecting the prediction.

【 授权许可】

CC BY