An adversarial learning approach to generate pressure support ventilation waveforms for asynchrony detection.

BACKGROUND AND OBJECTIVE: 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. METHODS: 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. RESULTS: 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). CONCLUSIONS: 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.

Testing the effects of checklists on team behaviour during emergencies on general wards: An observational study using high-fidelity simulation.

INTRODUCTION: Clinical teams struggle on general wards with acute management of deteriorating patients. We hypothesized that the Crisis Checklist App, a mobile application containing checklists tailored to crisis-management, can improve teamwork and acute care management. METHODS: A before-and-after study was undertaken in high-fidelity simulation centres in the Netherlands, Denmark and United Kingdom. Clinical teams completed three scenarios with a deteriorating patient without checklists followed by three scenarios using the Crisis Checklist App. Teamwork performance as the primary outcome was assessed by the Mayo High Performance Teamwork scale. The secondary outcomes were the time required to complete all predefined safety-critical steps, percentage of omitted safety-critical steps, effects on other non-technical skills, and users' self-assessments. Linear mixed models and a non-parametric survival test were conducted to assess these outcomes. RESULTS: 32 teams completed 188 scenarios. The Mayo High Performance Teamwork scale mean scores improved to 23.4 out of 32 (95% CI: 22.4-24.3) with the Crisis Checklist App compared to 21.4 (20.4-22.3) with local standard of care. The mean difference was 1.97 (1.34-2.6; p < 0.001). Teams that used the checklists were able to complete all safety-critical steps of a scenario in more simulations (40/95 vs 21/93 scenarios) and these steps were completed faster (stratified log-rank test χ2 = 8.0; p = 0.005). The self-assessments of the observers and users showed favourable effects after checklist usage for other non-technical skills including situational awareness, decision making, task management and communication. CONCLUSIONS: Implementation of a novel mobile crisis checklist application among clinical teams was associated in a simulated general ward setting with improved teamwork performance, and a higher and faster completion rate of predetermined safety-critical steps.

Current practice of closed-loop mechanical ventilation modes on intensive care units - a nationwide survey in the Netherlands.

BACKGROUND: The most recent modes for mechanical ventilation are closed-loop modes, which are able to automatically adjust certain respiratory settings. Although closed-loop modes have been investigated in various clinical trials, it is unclear to what extent these modes are actually used in clinical practice. The aim of this study was to determine closed-loop ventilation practice on intensive care units (ICUs) in the Netherlands, and to explore reasons for not applying closed-loop ventilation. Our hypothesis was that closed-loop ventilation is increasingly used. METHODS: A short survey was conducted among all non-paediatric ICUs in the Netherlands. Use of closed-loop modes was classified as frequently, occasionally or never, if respondents stated they had used these modes in the last week, in the last month/year, or never, respectively. RESULTS: The response rate of the survey was 82% (72 of 88). Respondents had access to a closed-loop ventilation mode in 58% of the ICUs (42 of 72). Of these ICUs, 43% (18 of 42) frequently applied a closed-loop ventilation mode, while 57% (24 of 42) never or occasionally used it. Reasons for not using these modes were lack of knowledge (40%), insufficient evidence reporting a beneficial effect (35%) and lack of confidence (25%). CONCLUSION: This study does not support our hypothesis that closed-loop ventilation is increasingly used in the Dutch ICU setting. While industry continues to develop new closed-loop modes, implementation of these modes in clinical practice seems to encounter difficulties. Various barriers could play a role, and these all need attention in future investigations.