Mechanical ventilation is a lifesaving treatment for critically ill patients in an Intensive Care Unit (ICU) or during surgery. However, one potential harm of mechanical ventilation is related to patient-ventilator asynchrony (PVA). PVA can cause discomfort to the patient, damage to the lungs, and an increase in the length of stay in the ICU and on the ventilator. Therefore, automated detection algorithms are being developed to detect and classify PVAs, with the goal of optimizing mechanical ventilation. However, the development of these algorithms often requires large labeled datasets; these are generally difficult to obtain, as their collection and labeling is a time-consuming and labor-intensive task, which needs to be performed by clinical experts. In this work, we aimed to develop a computer algorithm for the automatic detection and classification of PVA. The algorithm employs a neural network for the detection of the breath of the patient. The development of the algorithm was aided by simulations from a recently published model of the patient-ventilator interaction. The proposed method was effective, providing an algorithm with reliable detection and classification results of over 90% accuracy. Besides presenting a detection and classification algorithm for a variety of PVAs, here we show that using simulated data in combination with clinical data increases the variability in the training dataset, leading to a gain in performance and generalizability. In the future, these algorithms can be utilized to gain a better understanding of the clinical impact of PVAs and help clinicians to better monitor their ventilation strategies.

Non-invasive blood pressure (BP) measurements still rely on empirical interpretation of arterial oscillations recorded via cuff-based oscillometric methods. Extensive effort has dedicated to establishing a theoretical basis for oscillometry, aiming at more accurate BP estimations and measurement of additional hemodynamic parameters. However, oscillometry is still a heuristic method for BP inference. Goal: This study is focused on improving our understanding of the expression of arm volume pulsations in oscillometric signals. The aim is to identify main factors that determine the transfer function of arm volume to cuff pressure oscillations for existing cuff devices - this being an essential step in establishing a theoretical basis for oscillometry. Methods: The effects of air compression within the cuff and the influence of viscoelastic cuff material properties on the transfer function are studied by an experimental setup. Mechanical numerical modelling is used to interpret the results. Results: Air compression is found to be of adiabatic nature in the frequency range of interest. The cuff material exhibits viscous characteristics which is the cause of cuff response dependence on: inflation speed, tightness of wrapping, time passed since previous measurement, heart rate. Conclusion: It was found that typical cuffs used in clinical practice exhibit complex behavior. Cuff hardware needs to be improved to enable practical translation of pressure to arm volume oscillations. The presented characterisation method contributes to standardized development of new cuff prototypes and to identification of designs, techniques and materials with improved properties for enabling BP measurement accuracy and extraction of additional hemodynamic information.

Hemodynamic monitoring technologies are evolving continuously—a large number of bedside monitoring options are becoming available in the clinic. Methods such as echocardiography, electrical bioimpedance, and calibrated/uncalibrated analysis of pulse contours are becoming increasingly common. This is leading to a decline in the use of highly invasive monitoring and allowing for safer, more accurate, and continuous measurements. The new devices mainly aim to monitor the well-known hemodynamic variables (e.g., novel pulse contour, bioreactance methods are aimed at measuring widely-used variables such as blood pressure, cardiac output). Even though hemodynamic monitoring is now safer and more accurate, a number of issues remain due to the limited amount of information available for diagnosis and treatment. Extensive work is being carried out in order to allow for more hemodynamic parameters to be measured in the clinic. In this review, we identify and discuss the main sensing strategies aimed at obtaining a more complete picture of the hemodynamic status of a patient, namely: (i) measurement of the circulatory system response to a defined stimulus; (ii) measurement of the microcirculation; (iii) technologies for assessing dynamic vascular mechanisms; and (iv) machine learning methods. By analyzing these four main research strategies, we aim to convey the key aspects, challenges, and clinical value of measuring novel hemodynamic parameters in critical care.

In standard critical care practice, cuff sphygmomanometry is widely used for intermittent blood pressure (BP) measurements. However, cuff devices offer ample possibility of modulating blood flow and pulse propagation along the artery. We explore underutilized arrangements of sensors involving cuff devices which could be of use in critical care to reveal additional information on compensatory mechanisms. In our previous work, we analyzed the response of the vasculature to occlusion perturbations by means of observations obtained non-invasively. In this study, our aim is to (1) acquire additional insights by means of invasive measurements and (2) based on these insights, further develop cuff-based measurement strategies. Invasive BP experimental data is collected downstream from the cuff in two patients monitored in the OR. It is found that highly dynamic processes occur in the distal arm during cuff inflation. Mean arterial pressure increases in the distal artery by 20 mmHg, leading to a decrease in pulse transit time by 20 ms. Previous characterizations neglected such distal vasculature effects. A model is developed to reproduce the observed behaviors and to provide a possible explanation of the factors that influence the distal arm mechanisms. We apply the new findings to further develop measurement strategies aimed at acquiring information on pulse arrival time vs. BP calibration, artery compliance, peripheral resistance, artery-vein interaction.

Mechanical ventilation is a life-saving treatment for critically-ill patients. During treatment, patient-ventilator asynchrony (PVA) can occur, which can lead to pulmonary damage, complications, and higher mortality. While traditional detection methods for PVAs rely on visual inspection by clinicians, in recent years, machine learning models are being developed to detect PVAs automatically. However, training these models requires large labeled datasets, which are difficult to obtain, as labeling is a labour-intensive and time-consuming task, requiring clinical expertise. Simulating the lung-ventilator interactions has been proposed to obtain large labeled datasets to train machine learning classifiers. However, the obtained data lacks the influence of different hardware, of servo-controlled algorithms, and different sources of noise. Here, we propose VentGAN, an adversarial learning approach to improve simulated data by learning the ventilator fingerprints from unlabeled clinical data. In VentGAN, the loss functions are designed to add characteristics of clinical waveforms to the generated results, while preserving the labels of the simulated waveforms. To validate VentGAN, we compare the performance for detection and classification of PVAs when training a previously developed machine learning algorithm with the original simulated data and with the data generated by VentGAN. Testing is performed on independent clinical data labeled by experts. The McNemar test is applied to evaluate statistical differences in the obtained classification accuracy. VentGAN significantly improves the classification accuracy for late cycling, early cycling and normal breaths (p< 0.01); no significant difference in accuracy was observed for delayed inspirations (p = 0.2), while the accuracy decreased for ineffective efforts (p< 0.01). Generation of realistic synthetic data with labels by the proposed framework is feasible and represents a promising avenue for improving training of machine learning models.