Monitoring of total positive end-expiratory pressure during mechanical ventilation by artificial neural networks

PET Imaging of Neutrophil Elastase with 11C-GW457427 in Acute Respiratory Distress Syndrome in Pigs

Today, there is a lack of clinically available imaging techniques to detect and quantify specific immune cell populations. Neutrophils are one of the first immune cells at the site of inflammation, and they secrete the serine protease neutrophil elastase (NE), which is crucial in the fight against pathogens. However, the prolonged lifespan of neutrophils increases the risk that patients will develop severe complications, such as acute respiratory distress syndrome (ARDS). Here, we evaluated the novel radiolabeled NE inhibitor 11C-GW457427 in a pig model of ARDS, for detection and quantification of neutrophil activity in the lungs. Methods: ARDS was induced by intravenous administration of oleic acid to 5 farm pigs, and 4 were considered healthy controls. The severity of ARDS was monitored by clinical parameters of lung function and plasma biomarkers. Each pig was studied with 11C-GW457427 and PET/CT, before and after pretreatment with the NE inhibitor GW311616 to determine in vivo binding specificity. PET image data were analyzed as SUVs and correlated with immunohistochemical staining for NE in biopsies. Results: The binding of 11C-GW457427 was increased in pig lungs with induced ARDS (median SUVmean, 1.91; interquartile range [IQR], 1.67-2.55) compared with healthy control pigs (P < 0.05 and P = 0.03, respectively; median SUVmean, 1.04; IQR, 0.66-1.47). The binding was especially strong in lung regions with high levels of NE and ongoing inflammation, as verified by immunohistochemistry. The binding was successfully blocked by pretreatment of an NE inhibitor drug, which demonstrated the in vivo specificity of 11C-GW457427 (P < 0.05 and P = 0.04, respectively; median SUVmean, 0.60; IQR, 0.58-0.77). The binding in neutrophil-rich tissues such as bone marrow (P < 0.05 and P = 0.04, respectively; baseline median SUVmean, 5.01; IQR, 4.48-5.49; block median SUVmean, 1.57; IQR, 0.95-1.85) and spleen (median SUVmean, 2.14; IQR, 1.19-2.36) was also high in all pigs. Conclusion: 11C-GW457427 binds to NE in a porcine model of oleic acid-induced lung inflammation in vivo, with a specific increase in regional lung, bone marrow, and spleen SUV. 11C-GW457427 is a promising tool for localizing, tracking, and quantifying neutrophil-facilitated inflammation in clinical diagnostics and drug development.

Psychological Stress Identification and Evaluation Method Based on Mobile Human-Computer Interaction Equipment

Since the 1980s, the research of artificial neural networks in the field of artificial intelligence has become more and more common. It accepts nonlinear parallel processing, has strong learning and flexibility, and can be used for influencing factor analysis. The ideal power values and triggers are obtained in the Hopfield network model using genetic algorithm, which best avoids the drawbacks of the Hopfield network model instillation learning method. Through the BP of mobile human-computer interaction equipment, hereditary, genetic algorithms, and Hi-PLS regression method in the artificial neural network, the psychological pressure of college students is identified, evaluated, and predicted from three dimensions such as learning, life, and personal events. This makes it possible to understand the current physical and mental conditions of the students in a timely manner, guide to relieve anxiety and fear, and reach a safe psychological level. The three test results are less than 1%, which has high research significance and value.

Induction of dynamic hyperinflation by expiratory resistance breathing in healthy subjects - an efficacy and safety study

New Findings

What is the central question of this study?

The study aimed to establish a novel model to study the chronic obstructive pulmonary disease (COPD)‐related cardiopulmonary effects of dynamic hyperinflation in healthy subjects.

What is the main finding and its importance?

A model of expiratory resistance breathing (ERB) was established in which dynamic hyperinflation was induced in healthy subjects, expressed both by lung volumes and intrathoracic pressures. ERB outperformed existing methods and represents an efficacious model to study cardiopulmonary mechanics of dynamic hyperinflation without potentially confounding factors as present in COPD.

Abstract

Dynamic hyperinflation (DH) determines symptoms and prognosis of chronic obstructive pulmonary disease (COPD). The induction of DH is used to study cardiopulmonary mechanics in healthy subjects without COPD‐related confounders like inflammation, hypoxic vasoconstriction and rarefication of pulmonary vasculature. Metronome‐paced tachypnoea (MPT) has proven effective in inducing DH in healthy subjects, but does not account for airflow limitation. We aimed to establish a novel model incorporating airflow limitation by combining tachypnoea with an expiratory airway stenosis. We investigated this expiratory resistance breathing (ERB) model in 14 healthy subjects using different stenosis diameters to assess a dose–response relationship. Via cross‐over design, we compared ERB to MPT in a random sequence. DH was quantified by inspiratory capacity (IC, litres) and intrinsic positive end‐expiratory pressure (PEEPi, cmH₂O). ERB induced a stepwise decreasing IC (means (95% CI): tidal breathing: 3.66 (3.45–3.88), ERB 3 mm: 3.33 (1.75–4.91), 2 mm: 2.05 (0.76–3.34), 1.5 mm: 0.73 (0.12–1.58) litres) and increasing PEEPi (tidal breathing: 0.70 (0.50–0.80), ERB 3 mm: 11.1 (7.0–15.2), 2 mm: 22.3 (17.1–27.6), 1.5 mm: 33.4 (3.40–63) cmH₂O). All three MPT patterns increased PEEPi, but to a far lesser extent than ERB. No adverse events during ERB were noted. In conclusion, ERB was proven to be a safe and efficacious model for the induction of DH and might be used for the investigation of cardiopulmonary interaction in healthy subjects.

Analytics with artificial intelligence to advance the treatment of acute respiratory distress syndrome

Artificial intelligence (AI) has found its way into clinical studies in the era of big data. Acute respiratory distress syndrome (ARDS) or acute lung injury (ALI) is a clinical syndrome that encompasses a heterogeneous population. Management of such heterogeneous patient population is a big challenge for clinicians. With accumulating ALI datasets being publicly available, more knowledge could be discovered with sophisticated analytics. We reviewed literatures with big data analytics to understand the role of AI for improving the caring of patients with ALI/ARDS. Many studies have utilized the electronic medical records (EMR) data for the identification and prognostication of ARDS patients. As increasing number of ARDS clinical trials data is open to public, secondary analysis on these combined datasets provide a powerful way of finding solution to clinical questions with a new perspective. AI techniques such as Classification and Regression Tree (CART) and artificial neural networks (ANN) have also been successfully used in the investigation of ARDS problems. Individualized treatment of ARDS could be implemented with a support from AI as we are now able to classify ARDS into many subphenotypes by unsupervised machine learning algorithms. Interestingly, these subphenotypes show different responses to a certain intervention. However, current analytics involving ARDS have not fully incorporated information from omics such as transcriptome, proteomics, daily activities and environmental conditions. AI technology is assisting us to interpret complex data of ARDS patients and enable us to further improve the management of ARDS patients in future with individual treatment plans.

Artificial Intelligence and Machine Learning in Anesthesiology

Commercial applications of artificial intelligence and machine learning have made remarkable progress recently, particularly in areas such as image recognition, natural speech processing, language translation, textual analysis, and self-learning. Progress had historically languished in these areas, such that these skills had come to seem ineffably bound to intelligence. However, these commercial advances have performed best at single-task applications in which imperfect outputs and occasional frank errors can be tolerated.The practice of anesthesiology is different. It embodies a requirement for high reliability, and a pressured cycle of interpretation, physical action, and response rather than any single cognitive act. This review covers the basics of what is meant by artificial intelligence and machine learning for the practicing anesthesiologist, describing how decision-making behaviors can emerge from simple equations. Relevant clinical questions are introduced to illustrate how machine learning might help solve them-perhaps bringing anesthesiology into an era of machine-assisted discovery.

Journal of Clinical Monitoring and Computing 2017 end of year summary: respiration

This paper reviews 32 papers or commentaries published in Journal of Clinical Monitoring and Computing in 2016, within the field of respiration. Papers were published covering airway management, ventilation and respiratory rate monitoring, lung mechanics and gas exchange monitoring, in vitro monitoring of lung mechanics, CO₂ monitoring, and respiratory and metabolic monitoring techniques.

Robustness of two different methods of monitoring respiratory system compliance during mechanical ventilation

Robustness measures the performance of estimation methods when they work under non-ideal conditions. We compared the robustness of artificial neural networks (ANNs) and multilinear fitting (MLF) methods in estimating respiratory system compliance (C_RS) during mechanical ventilation (MV). Twenty-four anaesthetized pigs underwent MV. Airway pressure, flow and volume were recorded at fixed intervals after the induction of acute lung injury. After consecutive mechanical breaths, an inspiratory pause (BIP) was applied in order to calculate C_RS using the interrupter technique. From the breath preceding the BIP, ANN and MLF had to compute C_RS in the presence of two types of perturbations: transient sensor disconnection (TD) and random noise (RN). Performance of the two methods was assessed according to Bland and Altman. The ANN presented a higher bias and scatter than MLF during the application of RN, except when RN was lower than 2% of peak airway pressure. During TD, MLF algorithm showed a higher bias and scatter than ANN. After the application of RN, ANN and MLF maintain a stable performance, although MLF shows better results. ANNs have a more stable performance and yield a more robust estimation of C_RS than MLF in conditions of transient sensor disconnection.