Introduction: In intensive care units (ICU), the most significant life support technology for patients with acute respiratory failure is mechanical ventilation. A mismatch between ventilatory support and patient demand is referred to as patient-ventilator asynchrony (PVA), and it is associated with a series of adverse clinical outcomes. Although the use of a reference signal for patient effort is critical in recognition of PVA, existing detection algorithms are frequently solely based on the ventilator’s airway pressure (Paw) and flow-time signals. The aim of this study was to develop an automated detection algorithm for PVA using the ventilator’s Paw, flow-time and esophageal pressure (Pes) signals.

Methods: We proposed a two-dimensional convolutional neural network (2DCNN) to detect two types of PVA (reverse triggering (RT) and premature cycling) using a dataset of respiratory cycles recorded from 11 patients. Mechanical ventilation experts with access to the Pes signal annotated 12.337 respiratory cycles to create a gold standard dataset. Several techniques for a potential class imbalance problem, as well as several changes to the initial model architecture, were investigated. A leave-one-patient-out cross-validation technique was used to evaluate model performance. The proposed Pes-based 2DCNN (Pes_2DCNN) was compared to a similar model based solely on the ventilator Paw and flow-time signals (PF_2DCNN).

Results: The proposed Pes_2DCNN exhibited superior performance in detecting RT as compared to PF_2DCNN in terms of area under the receiver operating characteristic (AUROC) (0.80 ± 0.07 vs. 0.75 ± 0.13, respectively; p < 0.01). Furthermore, the results indicate that the class imbalance solutions did not improve the performance for detection of RT. For detection of premature cycling, Pes_2DCNN also outperformed PF_2DCNN in terms of AUROC (0.88 ± 0.09 vs. 0.71 ± 0.24, respectively; p < 0.01).

Conclusion: The findings of this study suggest the added value of the Pes signal in detection of RT and premature cycling. However, because this is a preliminary study, more research is required to further investigate the importance of the Pes signal in PVA detection.

Background: The prevention of ventilator-induced lung injury (VILI) is an important topic in criticalcare. Lung overdistention is a great attributor to VILI. Regional evaluation of the pulmonary mechanicsis a relatively new method and is currently being studied using electrical impedance tomography (EIT)and computed tomography (CT). However, ultrasonography may be an effective alternative tomeasure lung overdistention by quantifying lung sliding.
Objective: The primary aim of this study was to explore if lung sliding can be quantified using in-housemade speckle tracking algorithms. Second, the usability of lung sliding quantification to detect lungoverdistention was investigated.
Methods: Two speckle tracking algorithms were built and validated to quantify lung sliding. Adultpatients admitted to the ICU were prospectively examined using ultrasound. Ultrasound images wereanalyzed offline using the in-house developed Fourier-Based Speckle Tracking algorithm (FBST) andthe Intensity-Based Speckle Tracking algorithm (IBST). The performance of the best algorithm wasvalidated against the manual evaluation of lung sliding by experts and validated against lungcompliance. Besides, the performance of the best algorithm was investigated by reproducibilitytesting. Finally, we tested the algorithm for its ability to detect lung overdistention.
Results: The FBST algorithm could not reliably quantify lung sliding and was not further evaluated.However, the IBST algorithm showed an overall success rate of 88%. Moreover, the IBST algorithmdifferentiated normal and moderate lung sliding with a mean IBST score of 12.1 and 29, respectively(p<0.001). A positive correlation was measured between IBST score and lung compliance (β 0.15, SE0.025, 95% CI 0.101-0.208, p <0.001). The reproducibility test calculated a relative standard error of2.7. Finally, a difference was found in IBST scores between patients with a PEEP value <12 and ≥12with a mean ± SD of 20.9 ± 7 and 12.6 ± 6, p < 0.05, respectively.
Conclusion: The IBST algorithm enables a robust lung sliding quantification. The IBST scores correlatewell with expert opinion and lung compliance, but the reliability needs improvement. Our results showthat detection of lung overdistention using ultrasound is feasible. Further clinical studies should assessif ultrasonography can measure lung overdistention.