Flow starvation during square-flow assisted ventilation detected by supervised deep learning techniques.

BACKGROUND: Flow starvation is a type of patient-ventilator asynchrony that occurs when gas delivery does not fully meet the patients' ventilatory demand due to an insufficient airflow and/or a high inspiratory effort, and it is usually identified by visual inspection of airway pressure waveform. Clinical diagnosis is cumbersome and prone to underdiagnosis, being an opportunity for artificial intelligence. Our objective is to develop a supervised artificial intelligence algorithm for identifying airway pressure deformation during square-flow assisted ventilation and patient-triggered breaths. METHODS: Multicenter, observational study. Adult critically ill patients under mechanical ventilation > 24 h on square-flow assisted ventilation were included. As the reference, 5 intensive care experts classified airway pressure deformation severity. Convolutional neural network and recurrent neural network models were trained and evaluated using accuracy, precision, recall and F1 score. In a subgroup of patients with esophageal pressure measurement (ΔPes), we analyzed the association between the intensity of the inspiratory effort and the airway pressure deformation. RESULTS: 6428 breaths from 28 patients were analyzed, 42% were classified as having normal-mild, 23% moderate, and 34% severe airway pressure deformation. The accuracy of recurrent neural network algorithm and convolutional neural network were 87.9% [87.6-88.3], and 86.8% [86.6-87.4], respectively. Double triggering appeared in 8.8% of breaths, always in the presence of severe airway pressure deformation. The subgroup analysis demonstrated that 74.4% of breaths classified as severe airway pressure deformation had a ΔPes > 10 cmH2O and 37.2% a ΔPes > 15 cmH2O. CONCLUSIONS: Recurrent neural network model appears excellent to identify airway pressure deformation due to flow starvation. It could be used as a real-time, 24-h bedside monitoring tool to minimize unrecognized periods of inappropriate patient-ventilator interaction.

Non-Invasive Monitoring of Microvascular Oxygenation and Reactive Hyperemia using Hybrid, Near-Infrared Diffuse Optical Spectroscopy for Critical Care.

The detection of levels of impairment in microvascular oxygen consumption and reactive hyperemia is vital in critical care. However, there are no practical means for a robust and quantitative evaluation. This paper describes a protocol to evaluate these impairments using a hybrid near-infrared diffuse optical device. The device contains modules for near-infrared time-resolved and diffuse correlation spectroscopies and pulse-oximetry. These modules allow the non-invasive, continuous, and real-time measurement of the absolute, microvascular blood/tissue oxygen saturation (StO2) and the blood flow index (BFI) along with the peripheral arterial oxygen saturation (SpO2). This device uses an integrated, computer-controlled tourniquet system to execute a standardized protocol with optical data acquisition from the brachioradialis muscle. The standardized vascular occlusion test (VOT) takes care of the variations in the occlusion duration and pressure reported in the literature, while the automation minimizes inter-operator differences. The protocol we describe focuses on a 3-min occlusion period but the details described in this paper can readily be adapted to other durations and cuff pressures, as well as other muscles. The inclusion of an extended baseline and post-occlusion recovery period measurement allows the quantification of the baseline values for all the parameters and the blood/tissue deoxygenation rate that corresponds to the metabolic rate of oxygen consumption. Once the cuff is released, we characterize the tissue reoxygenation rate, magnitude, and duration of the hyperemic response in BFI and StO2. These latter parameters correspond to the quantification of the reactive hyperemia, which provides information about the endothelial function. Furthermore, the above-mentioned measurements of the absolute concentration of oxygenated and deoxygenated hemoglobin, BFI, the derived metabolic rate of oxygen consumption, StO2, and SpO2 provide a yet-to-be-explored rich data set that can exhibit disease severity, personalized therapeutics, and management interventions.

[Haemodynamic monitoring in sepsis and septic shock]. / Monitorización hemodinámica en la sepsis y el shock séptico.

Cardiovascular disturbances associated with sepsis cause hypoperfusion situations, which will negatively impact these patients' prognosis. The aim of haemodynamic monitoring is to guide the detection and correction of this hypoperfusion, and assist in decision making in optimising oxygen transport to tissues, primarily by manipulating cardiac output. This review seeks to summarise the different parameters of haemodynamic monitoring, the objectives of resuscitation, the physiological parameters, and the tools available to us for appropriate cardiac output manipulation.