Harbin Institute of Technology Shenzhen, Shenzhen, China.
Harbin Institute of Technology Shenzhen, Shenzhen, China; Peng Cheng Lab, Shenzhen, China.
Int J Med Inform. 2024 Jun;186:105425. doi: 10.1016/j.ijmedinf.2024.105425. Epub 2024 Mar 26.
For patients in the Intensive Care Unit (ICU), the timing of intubation has a significant association with patients' outcomes. However, accurate prediction of the timing of intubation remains an unsolved challenge due to the noisy, sparse, heterogeneous, and unbalanced nature of ICU data. In this study, our objective is to develop a workflow for pre-processing ICU data and to develop a customized deep learning model to predict the need for intubation.
To improve the prediction accuracy, we transform the intubation prediction task into a time series classification task. We carefully design a sequence of data pre-processing steps to handle the multimodal noisy data. Firstly, we discretize the sequential data and address missing data using interpolation. Next, we employ a sampling strategy to address data imbalance and standardize the data to facilitate faster model convergence. Furthermore, we employ the feature selection technique and propose an ensemble model to combine features learned by different deep learning models.
The performance is evaluated on Medical Information Mart for Intensive Care (MIMIC)-III, an ICU dataset. Our proposed Deep Feature Fusion method achieves an area under the curve (AUC) of the receiver operating curve (ROC) of 0.8953, surpassing the performance of other deep learning and traditional machine learning models.
Our proposed Deep Feature Fusion method proves to be a viable approach for predicting intubation and outperforms other deep learning and classical machine learning models. The study confirms that high-frequency time-varying indicators, particularly Mean Blood Pressure (MeanBP) and peripheral oxygen saturation (SpO2), are significant risk factors for predicting intubation.
对于重症监护病房（ICU）中的患者，插管时机与患者的预后有显著关联。然而，由于 ICU 数据的噪声、稀疏、异质和不平衡性质，准确预测插管时机仍然是一个未解决的挑战。在本研究中，我们的目标是开发一种 ICU 数据预处理工作流程，并开发一种定制的深度学习模型来预测插管需求。
为了提高预测准确性，我们将插管预测任务转化为时间序列分类任务。我们精心设计了一系列数据预处理步骤来处理多模态噪声数据。首先，我们对序列数据进行离散化，并使用插值处理缺失数据。接下来，我们采用采样策略来解决数据不平衡问题，并对数据进行标准化，以促进模型更快地收敛。此外，我们还采用特征选择技术，并提出了一种集成模型，将不同深度学习模型学习到的特征进行组合。
在重症监护医学信息集市（MIMIC）-III 这一 ICU 数据集上评估了性能。我们提出的深度特征融合方法在接收者操作曲线（ROC）的曲线下面积（AUC）方面达到了 0.8953，优于其他深度学习和传统机器学习模型的性能。
我们提出的深度特征融合方法被证明是一种可行的插管预测方法，优于其他深度学习和经典机器学习模型。研究证实，高频时变指标，特别是平均血压（MeanBP）和外周血氧饱和度（SpO2），是预测插管的重要风险因素。
