1D-CNNs model for classification of sputum deposition degree in mechanical ventilated patients based on airflow signals

Abstract

Sputum deposition has always been a significant problem in patients with mechanical ventilation. If not handled in time, it can induce bacterial infection and even endanger the life safety of patients. Currently, the evaluation of sputum deposition heavily depends on the medical staff's clinical experience. This paper designs a sputum deposition monitoring system that realizes remote airway pressure and flow signals collection and management for mechanically ventilated patients. Forty-six patients in the intensive care unit were involved in this study. Meanwhile, a one-dimensional convolution neural networks model was proposed to classify four sputum deposition categories (no, slight, moderate, and severe). The experimental results showed that the overall classification accuracy could reach more than 78%. Moreover, the model has been optimized for practical application by setting thresholds for the output of the softmax layer. Finally, the classification accuracy of no sputum, slight, moderate, and severe deposition reaches 85.84%, 84.29%, 93.19%, and 93.38%, respectively. This study's proposed system and method could significantly increase the automation and intelligence of medical care.