Pan Qing, Zhang Lingwei, Jia Mengzhe, Pan Jie, Gong Qiang, Lu Yunfei, Zhang Zhongheng, Ge Huiqing, Fang Luping
College of Information Engineering, Zhejiang University of Technology, Liuhe Rd. 288, Hangzhou 310023, China.
Department of Emergency Medicine, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Qingchun East Rd. 3, Hangzhou 310016, China.
Comput Methods Programs Biomed. 2021 Jun;204:106057. doi: 10.1016/j.cmpb.2021.106057. Epub 2021 Mar 19.
Patient-ventilator asynchrony (PVA) is the result of a mismatch between the need of patients and the assistance provided by the ventilator during mechanical ventilation. Because the poor interaction between the patient and the ventilator is associated with inferior clinical outcomes, effort should be made to identify and correct their occurrence. Deep learning has shown promising ability in PVA detection; however, lack of network interpretability hampers its application in clinic.
We proposed an interpretable one-dimensional convolutional neural network (1DCNN) to detect four most manifestation types of PVA (double triggering, ineffective efforts during expiration, premature cycling and delayed cycling) under pressure control ventilation mode and pressure support ventilation mode. A global average pooling (GAP) layer was incorporated with the 1DCNN model to highlight the sections of the respiratory waveform the model focused on when making a classification. Dilation convolution and batch normalization were introduced to the 1DCNN model for compensating the reduction of performance caused by the GAP layer.
The proposed interpretable 1DCNN exhibited comparable performance with the state-of-the-art deep learning model in PVA detection. The F1 scores for the detection of four types of PVA under pressure control ventilation and pressure support ventilation modes were greater than 0.96. The critical sections of the waveform used to detect PVA were highlighted, and found to be well consistent with the understanding of the respective type of PVA by experts.
The findings suggest that the proposed 1DCNN can help detect PVA, and enhance the interpretability of the classification process to help clinicians better understand the results obtained from deep learning technology.
患者 - 呼吸机不同步（PVA）是机械通气过程中患者需求与呼吸机提供的辅助之间不匹配的结果。由于患者与呼吸机之间的不良相互作用与较差的临床结局相关，因此应努力识别并纠正其发生情况。深度学习在PVA检测方面已显示出有前景的能力；然而，缺乏网络可解释性阻碍了其在临床中的应用。
我们提出了一种可解释的一维卷积神经网络（1DCNN），用于在压力控制通气模式和压力支持通气模式下检测PVA的四种最常见表现类型（双重触发、呼气时无效努力、过早切换和延迟切换）。在1DCNN模型中加入全局平均池化（GAP）层，以突出模型在进行分类时所关注的呼吸波形部分。将扩张卷积和批量归一化引入1DCNN模型，以补偿由GAP层导致的性能下降。
所提出的可解释1DCNN在PVA检测方面表现出与最先进的深度学习模型相当的性能。在压力控制通气和压力支持通气模式下检测四种类型PVA的F1分数均大于0.96。突出显示了用于检测PVA的波形关键部分，发现与专家对各类型PVA的理解高度一致。
研究结果表明，所提出的1DCNN有助于检测PVA，并增强分类过程的可解释性，以帮助临床医生更好地理解深度学习技术获得的结果。
