Zhang Lingwei, Mao Kedong, Duan Kailiang, Fang Siqi, Lu Yunfei, Gong Qiang, Lu Fei, Jiang Ye, Jiang Liuqing, Fang Wenyao, Zhou Xiaolin, Wang Jimei, Fang Luping, Ge Huiqing, Pan Qing
College of Information Engineering, Zhejiang University of Technology, Liuhe Rd. 288, Hangzhou, 310023, China.
Department of Respiratory Care, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Qingchun East Rd. 3, Hangzhou, 310016, China.
Comput Biol Med. 2020 May;120:103721. doi: 10.1016/j.compbiomed.2020.103721. Epub 2020 Mar 26.
Mismatch between invasive mechanical ventilation and the requirements of patients results in patient-ventilator asynchrony (PVA), which is associated with a series of adverse clinical outcomes. Although the efficiency of the available approaches for automatically detecting various types of PVA from the ventilator waveforms is unsatisfactory, the feasibility of powerful deep learning approaches in addressing this problem has not been investigated.
We propose a 2-layer long short-term memory (LSTM) network to detect two most frequently encountered types of PVA, namely, double triggering (DT) and ineffective inspiratory effort during expiration (IEE), on two datasets. The performance of the networks is evaluated first using cross-validation on the combined dataset, and then using a cross testing scheme, in which the LSTM networks are established on one dataset and tested on the other.
Compared with the reported rule-based algorithms and the machine learning models, the proposed 2-layer LSTM network exhibits the best overall performance, with the F1 scores of 0.983 and 0.979 for DT and IEE detection, respectively, on the combined dataset. Furthermore, it outperforms the other approaches in cross testing.
The findings suggest that LSTM is an excellent technique for accurate recognition of PVA in clinics. Such a technique can help detect and correct PVA for a better patient ventilator interaction.
有创机械通气与患者需求不匹配会导致患者 - 呼吸机不同步（PVA），这与一系列不良临床结局相关。尽管从呼吸机波形中自动检测各种类型PVA的现有方法效率不尽人意，但强大的深度学习方法在解决这一问题上的可行性尚未得到研究。
我们提出了一个2层长短期记忆（LSTM）网络，用于在两个数据集上检测两种最常见的PVA类型，即双重触发（DT）和呼气时无效吸气努力（IEE）。首先在合并数据集上使用交叉验证评估网络性能，然后使用交叉测试方案，即在一个数据集上建立LSTM网络并在另一个数据集上进行测试。
与已报道的基于规则的算法和机器学习模型相比，所提出的2层LSTM网络表现出最佳的整体性能，在合并数据集上，DT和IEE检测的F1分数分别为0.983和0.979。此外，在交叉测试中它优于其他方法。
研究结果表明，LSTM是一种在临床上准确识别PVA的优秀技术。这种技术有助于检测和纠正PVA，以实现更好的患者 - 呼吸机交互。
