Single-modal and multi-modal false arrhythmia alarm reduction using attention-based convolutional and recurrent neural networks
Single-modal and multi-modal false arrhythmia alarm reduction using attention-based convolutional and recurrent neural networks
复制标题
DOI：
10.1371/journal.pone.0226990
复制
发表时间：
2020-01-10
期刊：
影响因子：
3.7
通讯作者：
Afghah, Fatemeh
中科院分区：
文献类型：
--
作者：
Mousavi, Sajad;Fotoohinasab, Atiyeh;Afghah, Fatemeh
本研究提出了一种深度学习模型，该模型可以有效地抑制重症监护病房（icu）的假警报，而不会忽略使用单模态和多模态生物信号的真警报。目前文献中的大多数工作要么是基于规则的方法，需要心律失常分析的先验知识来构建规则，要么是经典的机器学习方法，取决于手工设计的特征。在这项工作中，我们应用卷积神经网络来自动提取时不变特征，注意机制来更加强调分割输入信号中更有可能导致报警的重要区域，长短期记忆单元来捕获信号片段中呈现的时间信息。我们使用两步训练算法（即预训练和微调所提出的网络）在2015年心脏病学挑战赛PhysioNet计算提供的数据集上有效地训练了我们的方法。评估结果表明，与现有算法相比，本文提出的方法在降低icu虚警任务方面取得了更好的效果。在考虑三种不同信号的情况下，该方法的报警分类灵敏度为93.88%，特异度为92.05%。此外，我们对5种不同报警类型的实验得出了显著的结果，其中我们只考虑单导联心电图（例如，室性心动过速心律失常报警类型的灵敏度为90.71%，特异性为88.30%，AUC为89.51）。
This study proposes a deep learning model that effectively suppresses the false alarms in the intensive care units (ICUs) without ignoring the true alarms using single- and multimodal biosignals. Most of the current work in the literature are either rule-based methods, requiring prior knowledge of arrhythmia analysis to build rules, or classical machine learning approaches, depending on hand-engineered features. In this work, we apply convolutional neural networks to automatically extract time-invariant features, an attention mechanism to put more emphasis on the important regions of the segmented input signal(s) that are more likely to contribute to an alarm, and long short-term memory units to capture the temporal information presented in the signal segments. We trained our method efficiently using a two-step training algorithm (i.e., pre-training and fine-tuning the proposed network) on the dataset provided by the PhysioNet computing in cardiology challenge 2015. The evaluation results demonstrate that the proposed method obtains better results compared to other existing algorithms for the false alarm reduction task in ICUs. The proposed method achieves a sensitivity of 93.88% and a specificity of 92.05% for the alarm classification, considering three different signals. In addition, our experiments for 5 separate alarm types leads significant results, where we just consider a single-lead ECG (e.g., a sensitivity of 90.71%, a specificity of 88.30%, an AUC of 89.51 for alarm type of Ventricular Tachycardia arrhythmia).