Prediction and simulation of PEEP setting effects with machine learning models / Predicción y simulación de los efectos de la configuración de la PEEP con modelos de aprendizaje automático

Objective To establish a new machine learning-based method to adjust positive end-expiratory pressure (PEEP) using only already routinely measured data. Design Retrospective observational study. Setting Intensive care unit (ICU). Patients or participants 51811 mechanically ventilated patients in multiple ICUs in the USA (data from MIMIC-III and eICU databases). Interventions No interventions. Main variables of interest Success parameters of ventilation (arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance). Results The multi-tasking neural network model performed significantly best for all target tasks in the primary test set. The model predicts arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance about 45 min into the future with mean absolute percentage errors of about 21.7%, 10.0% and 15.8%, respectively. The proposed use of the model was demonstrated in case scenarios, where we simulated possible effects of PEEP adjustments for individual cases. Conclusions Our study implies that machine learning approach to PEEP titration is a promising new method which comes with no extra cost once the infrastructure is in place. Availability of databases with most recent ICU patient data is crucial for the refinement of prediction performance. (AU)

Objetivo Establecer un nuevo método basado en el aprendizaje automático para ajustar la presión positiva al final de la espiración (PEEP según sus siglas en inglés) utilizando únicamente datos ya obtenidos de forma rutinaria. Diseño Estudio retrospectivo de observación. Ámbito Unidad de cuidados intesivos (UCI) Pacientes o participantes 51811 pacientes ventilados mecánicamente en múltiples UCIs de EE.UU. (tomados de las bases de datos MIMIC-III y eICU). Intervenciones Sin intervenciones. Variables de interés principales Parametros de éxito de la ventilación (presiones parciales arteriales de oxígeno y dióxido de carbono y distensibilidad del sistema respiratorio). Resultados El modelo de red neuronal multitarea obtuvo los mejores resultados en todos los objetivos del conjunto de pruebas primario. El modelo predice las presiones parciales arteriales de oxígeno y dióxido de carbono así como la distensibilidad del sistema respiratorio con aproximadamente 45 minutos de anticipación, mostrando errores porcentuales absolutos medios de aproximadamente 21.7%, 10.0% y 15.8%, respectivamente. El uso propuesto del modelo se demostró en situaciones hipotéticas en las que se simularon los posibles efectos de los ajustes de PEEP para casos individuales. Conclusiones Nuestro estudio implica que el enfoque de aprendizaje automático para el ajuste de la PEEP es un método nuevo y prometedor que no supone ningún coste adicional una vez que se dispone de la infraestructura necesaria. La disponibilidad de bases de datos con información de pacientes de UCI más recientes es crucial para perfeccionar el rendimiento de la predicción. (AU)

Pulmonary function testing in preoperative high-risk patients.

BACKGROUND: Postoperative respiratory failure is the most frequent complication in postsurgical patients. The purpose of this study is to assess whether pulmonary function testing in high-risk patients during preoperative assessment detects previously unknown respiratory impairments which may influence patient outcomes. METHODS: A targeted patient screening by spirometry and the measurement of the diffusing capacity of the lung for carbon monoxide (DLCO) was implemented in the anesthesia department of a tertiary university hospital. Patients of all surgical disciplines who were at least 75 years old or exhibited reduced exercise tolerance with the metabolic equivalent of task less than four (MET < 4) were examined. Clinical characteristics, history of lung diseases, and smoking status were also recorded. The statistical analysis entailed t-tests, one-way ANOVA, and multiple linear regression with backward elimination for group comparisons. RESULTS: Among 256 included patients, 230 fulfilled the test quality criteria. Eighty-one (35.2%) patients presented obstructive ventilatory disorders, out of which 65 were previously unknown. 38 of the newly diagnosed obstructive disorders were mild, 18 moderate, and 9 severe. One hundred forty-five DLCO measurements revealed 40 (27.6%) previously unknown gas exchange impairments; 21 were mild, 17 moderate, and 2 severe. The pulmonary function parameters of forced vital capacity (FVC), forced expiratory volume in 1 s (FEV1), and DLCO were significantly lower than the international reference values of a healthy population. Patients with a lower ASA class and no history of smoking exhibited higher FVC, FEV1, and DLCO values. Reduced exercise tolerance with MET < 4 was strongly associated with lower spirometry values. CONCLUSIONS: Our screening program detected a relevant number of patients with previously unknown obstructive ventilatory disorders and impaired pulmonary gas exchange. This newly discovered sickness is associated with low metabolic equivalents and may influence perioperative outcomes. Whether optimized management of patients with previously unknown impaired lung function leads to a better outcome should be evaluated in multicenter studies. TRIAL REGISTRATION: German Registry of Clinical Studies (DRKS00029337), registered on: June 22nd, 2022.

Pressure- and time-dependent alveolar recruitment/derecruitment in a spatially resolved patient-specific computational model for injured human lungs.

We present a novel computational model for the dynamics of alveolar recruitment/derecruitment (RD), which reproduces the underlying characteristics typically observed in injured lungs. The basic idea is a pressure- and time-dependent variation of the stress-free reference volume in reduced dimensional viscoelastic elements representing the acinar tissue. We choose a variable reference volume triggered by critical opening and closing pressures in a time-dependent manner from a straightforward mechanical point of view. In the case of (partially and progressively) collapsing alveolar structures, the volume available for expansion during breathing reduces and vice versa, eventually enabling consideration of alveolar collapse and reopening in our model. We further introduce a method for patient-specific determination of the underlying critical parameters of the new alveolar RD dynamics when integrated into the tissue elements, referred to as terminal units, of a spatially resolved physics-based lung model that simulates the human respiratory system in an anatomically correct manner. Relevant patient-specific parameters of the terminal units are herein determined based on medical image data and the macromechanical behavior of the lung during artificial ventilation. We test the whole modeling approach for a real-life scenario by applying it to the clinical data of a mechanically ventilated patient. The generated lung model is capable of reproducing clinical measurements such as tidal volume and pleural pressure during various ventilation maneuvers. We conclude that this new model is an important step toward personalized treatment of ARDS patients by considering potentially harmful mechanisms-such as cyclic RD and overdistension-and might help in the development of relevant protective ventilation strategies to reduce ventilator-induced lung injury (VILI).

Prediction and simulation of PEEP setting effects with machine learning models.

OBJECTIVE: To establish a new machine learning-based method to adjust positive end-expiratory pressure (PEEP) using only already routinely measured data. DESIGN: Retrospective observational study. SETTING: Intensive care unit (ICU). PATIENTS OR PARTICIPANTS: 51811 mechanically ventilated patients in multiple ICUs in the USA (data from MIMIC-III and eICU databases). INTERVENTIONS: No interventions. MAIN VARIABLES OF INTEREST: Success parameters of ventilation (arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance) RESULTS: The multi-tasking neural network model performed significantly best for all target tasks in the primary test set. The model predicts arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance about 45 min into the future with mean absolute percentage errors of about 21.7%, 10.0% and 15.8%, respectively. The proposed use of the model was demonstrated in case scenarios, where we simulated possible effects of PEEP adjustments for individual cases. CONCLUSIONS: Our study implies that machine learning approach to PEEP titration is a promising new method which comes with no extra cost once the infrastructure is in place. Availability of databases with most recent ICU patient data is crucial for the refinement of prediction performance.

[Ultrasound diagnostics in prehospital emergency care-do we need a standardized educational approach?] / Ultraschalldiagnostik in der prähospitalen Notfallmedizin ­ brauchen wir eine standardisierte Ausbildung?

BACKGROUND: Limited diagnostic capabilities represent an ongoing obstacle in out-of-hospital emergency settings. Prehospital deployment of ultrasound might reduce this particular diagnostic gap. So far, little is known about the availability and usage of ultrasound in emergency medical services (EMS) or about the level of education of EMS physicians regarding prehospital ultrasound (point-of-care ultrasound, POCUS). METHODS: A nationwide survey was conducted among emergency physicians in Germany focusing on POCUS education and experience. RESULTS: Between 02/2022 and 05/2022, 1079 responses were registered, of which 853 complete responses were analyzed. Of the emergency physicians, 71.9% consider POCUS beneficial for out-of-hospital diagnostics and 43.8% had participated in a certified POCUS training prior to the survey. The self-evaluation of POCUS skills among emergency physicians depended significantly on their participation in a certified training (p < 0.001) and frequent ultrasound routine (p < 0.001). CONCLUSION: The majority of participating emergency physicians in Germany consider POCUS to improve out-of-hospital diagnostic capabilities. Participation in a certified POCUS training and frequent use of ultrasound facilitated higher self-confidence in POCUS skills.

An approach to study recruitment/derecruitment dynamics in a patient-specific computational model of an injured human lung.

We present a new approach for physics-based computational modeling of diseased human lungs. Our main object is the development of a model that takes the novel step of incorporating the dynamics of airway recruitment/derecruitment into an anatomically accurate, spatially resolved model of respiratory system mechanics, and the relation of these dynamics to airway dimensions and the biophysical properties of the lining fluid. The importance of our approach is that it potentially allows for more accurate predictions of where mechanical stress foci arise in the lungs, since it is at these locations that injury is thought to arise and propagate from. We match the model to data from a patient with acute respiratory distress syndrome (ARDS) to demonstrate the potential of the model for revealing the underlying derangements in ARDS in a patient-specific manner. To achieve this, the specific geometry of the lung and its heterogeneous pattern of injury are extracted from medical CT images. The mechanical behavior of the model is tailored to the patient's respiratory mechanics using measured ventilation data. In retrospective simulations of various clinically performed, pressure-driven ventilation profiles, the model adequately reproduces clinical quantities measured in the patient such as tidal volume and change in pleural pressure. The model also exhibits physiologically reasonable lung recruitment dynamics and has the spatial resolution to allow the study of local mechanical quantities such as alveolar strains. This modeling approach advances our ability to perform patient-specific studies in silico, opening the way to personalized therapies that will optimize patient outcomes.

The role of PEEP for cannulation of the subclavian vein: A prospective observational study.

PURPOSE: The role of positive endexpiratory pressure (PEEP) for successful cannulation of the subclavian vein (SCV) remains inconclusive. The aim of our study was to assess the effect of different levels of PEEP on distance from SCV to parietal pleura (DVP) and on the cross-sectional area (CSA) of the SCV. METHODS: Invasive mechanically ventilated adult patients with a clinical indication for a stepwise PEEP-trial (0, 5, 10, and 15 cm H2O) were included in this prospective observational single-center study. Ultrasound examinations of SCV were performed with a linear ultrasound probe using the infraclavicular view. DVP and CSA were measured on the right and left bodyside. Examinations were repeated at each PEEP step. RESULTS: 27 patients were enrolled (12 female; 60±21 years; BMI 24.6±4.9 kg/m2; 20 patients on controlled, 7 on assisted ventilation). A statistically significant increase of DVP in the in-plane view was found on the left side which was not clinically relevant. No significant differences of DVP were observed in all other views. PEEP induced changes in CSAs were statistically significant but clinically not relevant on both sides. The largest change in CSA (2mm2) was observed when comparing PEEP 10 with PEEP 0 cm H2O. CONCLUSION: A stepwise PEEP increase was not associated with clinically relevant changes of the DVP and CSA. Thus, a PEEP-optimization for the cannulation of the subclavian vein is not indicated.

(1 → 3)-ß-D-Glucan-guided antifungal therapy in adults with sepsis: the CandiSep randomized clinical trial.

PURPOSE: To investigate whether (1 → 3)-ß-d-Glucan (BDG)-guidance shortens time to antifungal therapy and thereby reduces mortality of sepsis patients with high risk of invasive Candida infection (ICI). METHODS: Multicenter, randomized, controlled trial carried out between September 2016 and September 2019 in 18 intensive care units enrolling adult sepsis patients at high risk for ICI. Patients in the control group received targeted antifungal therapy driven by culture results. In addition to targeted therapy, patients in the BDG group received antifungals if at least one of two consecutive BDG samples taken during the first two study days was ≥ 80 pg/mL. Empirical antifungal therapy was discouraged in both groups. The primary endpoint was 28-day-mortality. RESULTS: 339 patients were enrolled. ICI was diagnosed in 48 patients (14.2%) within the first 96 h after enrollment. In the BDG-group, 48.8% (84/172) patients received antifungals during the first 96 h after enrollment and 6% (10/167) patients in the control group. Death until day 28 occurred in 58 of 172 patients (33.7%) in the BDG group and 51 of 167 patients (30.5%) in the control group (relative risk 1.10; 95% confidence interval, 0.80-1.51; p = 0.53). Median time to antifungal therapy was 1.1 [interquartile range (IQR) 1.0-2.2] days in the BDG group and 4.4 (IQR 2.0-9.1, p < 0.01) days in the control group. CONCLUSIONS: Serum BDG guided antifungal treatment did not improve 28-day mortality among sepsis patients with risk factors for but unexpected low rate of IC. This study cannot comment on the potential benefit of BDG-guidance in a more selected at-risk population.

Mobilization in the evening to prevent delirium: A pilot randomized trial.

BACKGROUND: Delirium is a common complication in patients in Intensive Care Units (ICU). Interventions such as mobilization are effective in the prevention and treatment of delirium, although this is usually completed during the daytime. AIM: The aim of this study was to assess the feasibility of mobilization in the evening to prevent and treat ICU patients from delirium by an additional mobility team over 2 weeks. METHODS: The design was a pilot, multi-centre, randomized, controlled trial in four mixed ICUs over a period of 2 weeks. The mobility team consisted of trained nurses and physiotherapists. Patients in the intervention group were mobilized onto the edge of the bed or more between 21.00 and 23.00. Patients in the control group received usual care. The primary outcome parameter was the feasibility of the study, measured as recruitment rate, delivery rate, and safety. Secondary outcomes were duration and incidence of delirium, mortality, duration of mechanical ventilation (MV), and hospital length of stay for 28 days follow-up, and power calculation for a full trial. RESULTS: Out of 185 patients present in the ICUs, 28.6% (n = 53) were eligible and could be recruited, of which 24.9% (n = 46, Intervention = 26, Control = 20) were included in the final analysis. In the intervention group, mobilization could be delivered in 75% (n = 54) of 72 possible occasions; mobilization-related safety events appeared in 16.7% (n = 9) without serious consequences. Secondary parameters were similar, with less delirium in the intervention group albeit not significant. With an association of Cramer's V = 0.237, a complete study reaching statistical significance would require at least 140 patients, last 6 weeks, and cost >30 000 €. CONCLUSIONS: In a mixed ICU population, mobilization in the evening was feasible in one-quarter of patients with a low rate of safety events. Future trials seem to be feasible and worth conducting.

Spatial Ventilation Inhomogeneity Determined by Electrical Impedance Tomography in Patients With Chronic Obstructive Lung Disease.

The aim of this study was to examine whether electrical impedance tomography (EIT) could determine the presence of ventilation inhomogeneity in patients with chronic obstructive lung disease (COPD) from measurements carried out not only during conventional forced full expiration maneuvers but also from forced inspiration maneuvers and quiet tidal breathing and whether the inhomogeneity levels were comparable among the phases and higher than in healthy subjects. EIT data were acquired in 52 patients with exacerbated COPD (11 women, 41 men, 68 ± 11 years) and 14 healthy subjects (6 women, 8 men, 38 ± 8 years). Regional lung function parameters of forced vital capacity (FVC), forced expiratory volume in 1 s (FEV1), forced inspiratory vital capacity (FIVC), forced inspiratory volume in 1 s (FIV1), and tidal volume (V T ) were determined in 912 image pixels. The spatial inhomogeneity of the pixel parameters was characterized by the coefficients of variation (CV) and the global inhomogeneity (GI) index. CV and GI values of pixel FVC, FEV1, FIVC, FIV1, and VT were significantly higher in patients than in healthy subjects (p ≤ 0.0001). The ventilation distribution was affected by the analyzed lung function parameter in patients (CV: p = 0.0024, GI: p = 0.006) but not in healthy subjects. Receiver operating characteristic curves showed that CV and GI discriminated patients from healthy subjects with an area under the curve (AUC) of 0.835 and 0.852 (FVC), 0.845 and 0.867 (FEV1), 0.903 and 0.903 (FIVC), 0.891 and 0.882 (FIV1), and 0.821 and 0.843 (VT), respectively. These findings confirm the ability of EIT to identify increased ventilation inhomogeneity in patients with COPD.

Efficacy and Safety of Vilobelimab (IFX-1), a Novel Monoclonal Anti-C5a Antibody, in Patients With Early Severe Sepsis or Septic Shock-A Randomized, Placebo-Controlled, Double-Blind, Multicenter, Phase IIa Trial (SCIENS Study).

Anaphylatoxin C5a, a proinflammatory complement split product, plays a central role in mediating organ dysfunction. OBJECTIVES: This phase II clinical trial was conducted to study safety, tolerability, pharmacokinetics, and pharmacodynamics of vilobelimab, a recombinant monoclonal antibody against C5a, in patients with severe sepsis or septic shock. DESIGN: Multicenter, randomized, and placebo-controlled study. SETTING AND PARTICIPANTS: Eleven multidisciplinary ICUs across Germany. Adult patients with severe sepsis or septic shock and with early onset of infection-associated organ dysfunction. MAIN OUTCOMES AND MEASURES: Patients were randomly assigned in a ratio of 2:1 to three subsequent dosing cohorts for IV vilobelimab or placebo receiving either 2 × 2 mg/kg (0 and 12 hr), 2 × 4 mg/kg (0 and 24 hr), and 3 × 4 mg/kg (0, 24, and 72 hr). Co-primary endpoints were pharmacodynamics (assessed by C5a concentrations), pharmacokinetics (assessed by vilobelimab concentrations), and safety of vilobelimab. Preliminary efficacy was evaluated by secondary objectives. RESULTS: Seventy-two patients were randomized (16 patients for each vilobelimab dosing cohort and eight patients for each placebo dosing cohort). Vilobelimab application was associated with dosing dependent decrease in C5a compared with baseline (p < 0.001). Duration of C5a decrease increased with more frequent dosing. Membrane attack complex lysis capacity measured by 50% hemolytic complement was not affected. Vilobelimab was well tolerated with similar safety findings in all dose cohorts. No vilobelimab-specific adverse events emerged. For vilobelimab-treated patients, investigators attributed less treatment-emergent adverse events as related compared with placebo. Dosing cohorts 2 and 3 had the highest ICU-free and ventilator-free days. There was no difference in mortality, vasopressor-free days, or renal replacement therapy-free days between the groups. CONCLUSIONS AND RELEVANCE: Administration of vilobelimab in patients with severe sepsis and septic shock selectively neutralizes C5a in a dose-dependent manner without blocking formation of the membrane attack complex and without resulting in detected safety issues. The data warrant further investigation of C5a inhibition in sepsis.

The Effect of Physical Therapy on Regional Lung Function in Critically Ill Patients.

Early mobilization has become an important aspect of treatment in intensive care medicine, especially in patients with acute pulmonary dysfunction. As its effects on regional lung physiology have not been fully explored, we conceived a prospective observational study (Registration number: DRKS00023076) investigating regional lung function during a 15-min session of early mobilization physiotherapy with a 30-min follow-up period. The study was conducted on 20 spontaneously breathing adult patients with impaired pulmonary gas exchange receiving routine physical therapy during their intensive care unit stay. Electrical impedance tomography (EIT) was applied to continuously monitor ventilation distribution and changes in lung aeration during mobilization and physical therapy. Baseline data was recorded in the supine position, the subjects were then transferred into the seated and partly standing position for physical therapy. Afterward, patients were transferred back into the initial position and followed up with EIT for 30 min. EIT data were analyzed to assess changes in dorsal fraction of ventilation (%dorsal), end-expiratory lung impedance normalized to tidal variation (ΔEELI), center of ventilation (CoV) and global inhomogeneity index (GI index).Follow-up was completed in 19 patients. During exercise, patients exhibited a significant change in ventilation distribution in favor of dorsal lung regions, which did not persist during follow-up. An identical effect was shown by CoV. ΔEELI increased significantly during follow-up. In conclusion, mobilization led to more dorsal ventilation distribution, but this effect subsided after returning to initial position. End-expiratory lung impedance increased during follow-up indicating a slow increase in end-expiratory lung volume following physical therapy.

Effects of different ischemic preconditioning strategies on physiological and cellular mechanisms of intestinal ischemia/reperfusion injury: Implication from an isolated perfused rat small intestine model.

BACKGROUND: Intestinal ischemia/reperfusion (I/R)-injury often results in sepsis and organ failure and is of major importance in the clinic. A potential strategy to reduce I/R-injury is the application of ischemic preconditioning (IPC) during which repeated, brief episodes of I/R are applied. The aim of this study was to evaluate physiological and cellular effects of intestinal I/R-injury and to compare the influence of in-vivo IPC (iIPC) with ex-vivo IPC (eIPC), in which blood derived factors and nerval regulations are excluded. METHODS: Using an established perfused rat intestine model, effects of iIPC and eIPC on physiological as well as cellular mechanisms of I/R-injury (60 min hypoxia, 30 min reperfusion) were investigated. iIPC was applied by three reversible occlusions of the mesenteric artery in-vivo for 5 min followed by 5 min of reperfusion before isolating the small intestine, eIPC was induced by stopping the vascular perfusion ex-vivo 3 times for 5 min followed by 5 min of reperfusion after isolation of the intestine. Study groups (each N = 8-9 animals) were: iIPC, eIPC, I/R (iIPC group), I/R (eIPC group), iIPC+I/R, eIPC+I/R, no intervention/control (iIPC group), no intervention/control (eIPC group). Tissue morphology/damage, metabolic functions, fluid shifts and barrier permeability were evaluated. Cellular mechanisms were investigated using signaling arrays. RESULTS: I/R-injury decreased intestinal galactose uptake (iIPC group: p<0.001), increased vascular perfusion pressure (iIPC group: p<0.001; eIPC group: p<0.01) and attenuated venous flow (iIPC group: p<0.05) while lactate-to-pyruvate ratio (iIPC group, eIPC group: p<0.001), luminal flow (iIPC group: p<0.001; eIPC group: p<0.05), goblet cell ratio (iIPC group, eIPC group: p<0.001) and apoptosis (iIPC group, eIPC group: p<0.05) were all increased. Application of iIPC prior to I/R increased vascular galactose uptake (P<0.05) while eIPC had no significant impact on parameters of I/R-injury. On cellular level, I/R-injury resulted in a reduction of the phosphorylation of several MAPK signaling molecules. Application of iIPC prior to I/R increased phosphorylation of JNK2 and p38δ while eIPC enhanced CREB and GSK-3α/ß phosphorylation. CONCLUSION: Intestinal I/R-injury is associated with major physiological and cellular changes. However, the overall influence of the two different IPC strategies on the acute phase of intestinal I/R-injury is rather limited.

Individualization of PEEP and tidal volume in ARDS patients with electrical impedance tomography: a pilot feasibility study.

BACKGROUND: In mechanically ventilated patients with acute respiratory distress syndrome (ARDS), electrical impedance tomography (EIT) provides information on alveolar cycling and overdistension as well as assessment of recruitability at the bedside. We developed a protocol for individualization of positive end-expiratory pressure (PEEP) and tidal volume (VT) utilizing EIT-derived information on recruitability, overdistension and alveolar cycling. The aim of this study was to assess whether the EIT-based protocol allows individualization of ventilator settings without causing lung overdistension, and to evaluate its effects on respiratory system compliance, oxygenation and alveolar cycling. METHODS: 20 patients with ARDS were included. Initially, patients were ventilated according to the recommendations of the ARDS Network with a VT of 6 ml per kg predicted body weight and PEEP adjusted according to the lower PEEP/FiO2 table. Subsequently, ventilator settings were adjusted according to the EIT-based protocol once every 30 min for a duration of 4 h. To assess global overdistension, we determined whether lung stress and strain remained below 27 mbar and 2.0, respectively. RESULTS: Prospective optimization of mechanical ventilation with EIT led to higher PEEP levels (16.5 [14-18] mbar vs. 10 [8-10] mbar before optimization; p = 0.0001) and similar VT (5.7 ± 0.92 ml/kg vs. 5.8 ± 0.47 ml/kg before optimization; p = 0.96). Global lung stress remained below 27 mbar in all patients and global strain below 2.0 in 19 out of 20 patients. Compliance remained similar, while oxygenation was significantly improved and alveolar cycling was reduced after EIT-based optimization. CONCLUSIONS: Adjustment of PEEP and VT using the EIT-based protocol led to individualization of ventilator settings with improved oxygenation and reduced alveolar cycling without promoting global overdistension. Trial registrationThis study was registered at clinicaltrials.gov (NCT02703012) on March 9, 2016 before including the first patient.

Inferring Respiratory and Circulatory Parameters from Electrical Impedance Tomography With Deep Recurrent Models.

Electrical impedance tomography (EIT) is a noninvasive imaging modality that allows a continuous assessment of changes in regional bioimpedance of different organs. One of its most common biomedical applications is monitoring regional ventilation distribution in critically ill patients treated in intensive care units. In this work, we put forward a proof-of-principle study that demonstrates how one can reconstruct synchronously measured respiratory or circulatory parameters from the EIT image sequence using a deep learning model trained in an end-to-end fashion. For this purpose, we devise an architecture with a convolutional feature extractor whose output is processed by a recurrent neural network. We demonstrate that one can accurately infer absolute volume, absolute flow, normalized airway pressure and within certain limitations even the normalized arterial blood pressure from the EIT signal alone, in a way that generalizes to unseen patients without prior calibration. As an outlook with direct clinical relevance, we furthermore demonstrate the feasibility of reconstructing the absolute transpulmonary pressure from a combination of EIT and absolute airway pressure, as a way to potentially replace the invasive measurement of esophageal pressure. With these results, we hope to stimulate further studies building on the framework put forward in this work.

Regional Lung Perfusion Analysis in Experimental ARDS by Electrical Impedance and Computed Tomography.

Electrical impedance tomography is clinically used to trace ventilation related changes in electrical conductivity of lung tissue. Estimating regional pulmonary perfusion using electrical impedance tomography is still a matter of research. To support clinical decision making, reliable bedside information of pulmonary perfusion is needed. We introduce a method to robustly detect pulmonary perfusion based on indicator-enhanced electrical impedance tomography and validate it by dynamic multidetector computed tomography in two experimental models of acute respiratory distress syndrome. The acute injury was induced in a sublobar segment of the right lung by saline lavage or endotoxin instillation in eight anesthetized mechanically ventilated pigs. For electrical impedance tomography measurements, a conductive bolus (10% saline solution) was injected into the right ventricle during breath hold. Electrical impedance tomography perfusion images were reconstructed by linear and normalized Gauss-Newton reconstruction on a finite element mesh with subsequent element-wise signal and feature analysis. An iodinated contrast agent was used to compute pulmonary blood flow via dynamic multidetector computed tomography. Spatial perfusion was estimated based on first-pass indicator dilution for both electrical impedance and multidetector computed tomography and compared by Pearson correlation and Bland-Altman analysis. Strong correlation was found in dorsoventral (r = 0.92) and in right-to-left directions (r = 0.85) with good limits of agreement of 8.74% in eight lung segments. With a robust electrical impedance tomography perfusion estimation method, we found strong agreement between multidetector computed and electrical impedance tomography perfusion in healthy and regionally injured lungs and demonstrated feasibility of electrical impedance tomography perfusion imaging.

Video-based, student tutor- versus faculty staff-led ultrasound course for medical students - a prospective randomized study.

BACKGROUND: Ultrasound education is propagated already during medical school due to its diagnostic importance. Courses are usually supervised by experienced faculty staff (FS) with patient bedside examinations or students among each other but often overbooked due to limited FS availability. To overcome this barrier, use of teaching videos may be advantageous. Likewise, peer teaching concepts solely with trained student tutors have shown to be feasible and effective. The aim was to evaluate 1) objective learning outcomes of a combined video-based, student-tutor (ViST) as compared to a FS-led course without media support, 2) acceptance and subjective learning success of the videos. METHODS: Two ultrasound teaching videos for basic and advanced abdominal ultrasound (AU) and transthoracic echocardiography (TTE) were produced and six students trained as tutors. Fourth-year medical students (N = 96) were randomized to either the ViST- or FS course (6 students per tutor). Learning objectives were defined equally for both courses. Acquired practical basic and advanced ultrasound skills were tested in an objective structured clinical examination (OSCE) using modified validated scoring sheets with a maximum total score of 40 points. Acceptance and subjective learning success of both videos were evaluated by questionnaires based on Kirkpatrick's evaluation model with scale-rated closed and open questions. RESULTS: 79 of 96 medical students completed the OSCE and 77 could be finally analyzed. There was no significant difference in the mean total point score of 31.3 in the ViST (N = 42) and 32.7 in the FS course (N = 35, P = 0.31) or in any of the examined basic or advanced ultrasound skill subtasks. Of the 42 ViST participants, 29 completed the AU and 27 the TTE video questionnaire. Acceptance and subjective learning success of both videos was rated positively in 14-52% and 48-88% of the rated responses to each category, respectively. Attendance of either the student or faculty tutor was deemed necessary in addition to the videos. CONCLUSIONS: A ViST versus FS teaching concept was able to effectively teach undergraduate students in AU and TTE, albeit acceptance of the teaching videos alone was limited. However, the ViST concept has the potential to increase course availability and FS resource allocation.

Randomized controlled multicentre study of albumin replacement therapy in septic shock (ARISS): protocol for a randomized controlled trial.

BACKGROUND: Albumin is a key regulator of fluid distribution within the extracellular space and has several properties beyond its oncotic activity. The accumulating evidence suggests that supplementation of albumin may provide survival advantages only when the insult is severe as in patients with septic shock. METHODS/DESIGN: The randomized controlled multicentre study of albumin replacement therapy in septic shock (ARISS) investigates whether the replacement with albumin and the maintenance of its serum levels of at least 30 g/l for 28 days improve survival in patients with septic shock compared to resuscitation and volume maintenance without albumin. Adult patients (≥ 18 years) with septic shock are randomly assigned within a maximum of 24 h after the onset of septic shock after obtaining informed consents to treatment or control groups. Patients assigned to the treatment group receive a 60-g loading dose of human albumin 20% over 2-3 h. Serum albumin levels are maintained at least at 30 g/l in the ICU for a maximum of 28 days following randomization using 40-80 g human albumin 20% infusion. The control group is treated according to the usual practice with crystalloids as the first choice for the resuscitation and maintenance phase of septic shock. The primary endpoint is 90 days mortality and secondary endpoints include 28-day, 60-day, ICU, and in-hospital mortality, organ dysfunction/failure, total amount of fluid administration and total fluid balance in the ICU, and lengths of ICU and hospital stay. In total, 1412 patients need to be analysed, 706 per group. For the sample size estimation, a 15% reduction in 90-day mortality is assumed, i.e. an absolute reduction of 7.5% points to 42.5% (relative risk 1.18). Assuming a dropout rate of 15%, a total of 1662 patients need to be allocated. DISCUSSION: The results of the clinical trial may influence the treatment of patients with septic shock. The expected improvement in patient survival may result in a reduction in the resources currently used in the treatment of these patients and in the socioeconomic burden of this disease. TRIAL REGISTRATION: ClinicalTrials.gov NCT03869385 . Registration on 18 July 2019. Protocol version: Final 3.0.

Multimodal remote chest monitoring system with wearable sensors: a validation study in healthy subjects.

OBJECTIVE: Development of wearable medical technology for remote monitoring of patients suffering from chronic lung diseases may improve the care, therapy and outcome of these patients. APPROACH: A multimodal system using wearable sensors for the acquisition of multiple biosignals (electrical bioimpedance of the chest for electrical impedance tomography and respiratory rate assessment, peripheral oxygen saturation, chest sounds, electrocardiography for heart rate measurement, body activity, and posture) was developed and validated in a prospective, monocentric study on 50 healthy subjects. The subjects were studied under different types of ventilation (tidal and deep breathing, forced full expiration maneuver) and during increased body activity and posture changes. The major goals were to assess the functionality by determining the presence and plausibility of the signals, comfort of wearing and safety of the vest. MAIN RESULTS: All intended signals were recorded. Streaming of selected signals and wireless download of complete data sets were functional. Electrical impedance tomography recordings revealed good to excellent quality of detection of ventilation-related impedance changes in 34 out of 50 participants. Respiratory and heart rates were reliably detected and generally in physiological ranges. Peripheral oxygen saturation values were unphysiologically low. The chest sound recordings did not show waveforms allowing meaningful analysis of lung sounds. Body activity and posture were correctly identified. The comfort of wearing and the vest properties were positively rated. No adverse events occurred. SIGNIFICANCE: Albeit the full functionality of the current vest design was not established, the study confirmed the feasibility of remote functional chest monitoring with a marked increase in clinically relevant information compared to existing systems.

Noninvasive measurement of stroke volume changes in critically ill patients by means of electrical impedance tomography.

Previous animal experiments have suggested that electrical impedance tomography (EIT) has the ability to noninvasively track changes in cardiac stroke volume (SV). The present study intended to reproduce these findings in patients during a fluid challenge. In a prospective observational study including critically ill patients on mechanical ventilation, SV was estimated via ECG-gated EIT before and after a fluid challenge and compared to transpulmonary thermodilution reference measurements. Relative changes in EIT-derived cardiosynchronous impedance changes in the heart ([Formula: see text]) and lung region ([Formula: see text]) were compared to changes in reference SV by assessing the concordance rate (CR) and Pearson's correlation coefficient (R). We compared 39 measurements of 20 patients. [Formula: see text] did not show to be a reliable estimate for tracking changes of SV (CR = 52.6% and R = 0.13 with P = 0.44). In contrast, [Formula: see text] showed an acceptable trending performance (CR = 94.4% and R = 0.72 with P < 0.0001). Our results indicate that ECG-gated EIT measurements of [Formula: see text] are able to noninvasively monitor changes in SV during a fluid challenge in critically ill patients. However, this was not possible using [Formula: see text]. The present approach is limited by the influences induced by ventilation, posture or changes in electrode-skin contact and requires further validation.