A Deep Learning Approach to Detect Ventilatory Over-Assistance

Sylligardos, Emmanouil; Sigalas, Markos; Soundoulounaki, Stella; Vaporidi, Katerina; Trahanias, Panos

doi:10.1007/978-3-031-09282-4_42

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture of the employed 1D-CNN shown in Figure 2 A has been previously described in detail [ 17 ]; however, the model was restructured and retrained using the Pmus. More specifically, the model is composed of (i) a 2D input layer, fed with Flow and Paw segments, (ii) five 1D convolutional blocks with two identical layers each, to extract representative patterns used for classification, (iii) two dense layers, to increase model’s complexity and enhance its generalization capacity, and (iv) the output layer.…”

Section: Methodsmentioning

confidence: 99%

Neural Network-Enabled Identification of Weak Inspiratory Efforts during Pressure Support Ventilation Using Ventilator Waveforms

Soundoulounaki

Sylligardos

Akoumianaki

et al. 2023

JPM

View full text Add to dashboard Cite

During pressure support ventilation (PSV), excessive assist results in weak inspiratory efforts and promotes diaphragm atrophy and delayed weaning. The aim of this study was to develop a classifier using a neural network to identify weak inspiratory efforts during PSV, based on the ventilator waveforms. Recordings of flow, airway, esophageal and gastric pressures from critically ill patients were used to create an annotated dataset, using data from 37 patients at 2–5 different levels of support, computing the inspiratory time and effort for every breath. The complete dataset was randomly split, and data from 22 patients (45,650 breaths) were used to develop the model. Using a One-Dimensional Convolutional Neural Network, a predictive model was developed to characterize the inspiratory effort of each breath as weak or not, using a threshold of 50 cmH2O*s/min. The following results were produced by implementing the model on data from 15 different patients (31,343 breaths). The model predicted weak inspiratory efforts with a sensitivity of 88%, specificity of 72%, positive predictive value of 40%, and negative predictive value of 96%. These results provide a ‘proof-of-concept’ for the ability of such a neural-network based predictive model to facilitate the implementation of personalized assisted ventilation.

show abstract

Section: Methodsmentioning

confidence: 99%