Health Innovation Bigdata Center, Asan Institute for Life Sciences, Asan Medical Center, 88, Olympic-ro 43 gil, Songpa-gu, Seoul, 05505, South Korea.
Department of Financial Engineering, School of Business, Ajou University, Worldcupro 206, Yeongtong-gu, Suwon, 16499, South Korea.
Comput Biol Med. 2017 Oct 1;89:248-255. doi: 10.1016/j.compbiomed.2017.08.015. Epub 2017 Aug 19.
Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens.
This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction.
Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared.
With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model.
The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns.
脓毒症是重症监护病房患者死亡的主要原因之一。早期发现脓毒症至关重要，因为随着脓毒症阶段的恶化，死亡率会增加。
本研究旨在使用深度学习方法开发脓毒症早期检测模型，并比较新的深度学习方法与具有传统时间特征提取的回归方法的可行性和性能。
研究组选择符合 InSight 模型。比较了基于深度学习的模型和 InSight 模型的结果。
使用深度前馈网络，模型的 ROC 曲线下面积（AUC）分别为 InSight 和新特征集的 0.887 和 0.915。对于组合特征集的模型，AUC 与基本特征集相同（0.915）。对于长短期记忆模型，仅应用基本特征集，AUC 提高到 0.929，与现有 InSight 模型的 0.887 相比有所提高。
本文的贡献可以总结为三点：（i）无需使用领域知识进行特征提取即可提高性能，（ii）通过与参考特征进行比较验证深度神经网络的特征提取能力，以及（iii）使用可以学习序列模式的神经网络架构长短期记忆的前馈神经网络来提高性能。
