Extracorporeal Membrane Oxygenation for Acute Respiratory Failure Due to COVID-19: A Multicenter Matched Cohort Study.

Mechanical ventilation for respiratory failure due to COVID-19 is associated with significant morbidity and mortality. Veno-venous extracorporeal membrane oxygenation (ECMO) is an attractive management option. This study sought to determine the effect of ECMO on hospital mortality and discharge condition in this population. We conducted a retrospective multicenter study to emulate a pragmatic targeted trial comparing ECMO to mechanical ventilation without ECMO for severe COVID-19. Data were gathered from a large hospital network database in the US. Adults admitted with COVID-19 were included if they were managed with ECMO or mechanical ventilation for severe hypoxemia and excluded if they had significant comorbidities or lacked functional independence on admission. The groups underwent coarsened exact matching on multiple clinical variables. The primary outcome was adjusted in-hospital mortality; secondary outcomes included ventilator days, intensive care days, and discharge destination. A total of 278 ECMO patients were matched to 2,054 comparison patients. Adjusted in-hospital mortality was significantly less in the ECMO group (38.8% vs. 60.1%, p < 0.001). Extracorporeal membrane oxygenation was associated with higher rates of liberation from mechanical ventilation, intensive care discharge, and favorable discharge destination. These findings support the use of ECMO for well-selected patients with severe acute respiratory failure due to COVID-19.

A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts.

Despite continuous improvements, precipitation forecasts are still not as accurate and reliable as those of other meteorological variables. A major contributing factor to this is that several key processes affecting precipitation distribution and intensity occur below the resolved scale of global weather models. Generative adversarial networks (GANs) have been demonstrated by the computer vision community to be successful at super-resolution problems, that is, learning to add fine-scale structure to coarse images. Leinonen et al. (2020, https://doi.org/10.1109/TGRS.2020.3032790) previously applied a GAN to produce ensembles of reconstructed high-resolution atmospheric fields, given coarsened input data. In this paper, we demonstrate this approach can be extended to the more challenging problem of increasing the accuracy and resolution of comparatively low-resolution input from a weather forecasting model, using high-resolution radar measurements as a "ground truth." The neural network must learn to add resolution and structure whilst accounting for non-negligible forecast error. We show that GANs and VAE-GANs can match the statistical properties of state-of-the-art pointwise post-processing methods whilst creating high-resolution, spatially coherent precipitation maps. Our model compares favorably to the best existing downscaling methods in both pixel-wise and pooled CRPS scores, power spectrum information and rank histograms (used to assess calibration). We test our models and show that they perform in a range of scenarios, including heavy rainfall.

Brain natriuretic peptide levels do not correlate with acute cellular rejection in De Novo orthotopic heart transplant recipients.

BACKGROUND: The changes in brain natriuretic peptide (BNP) levels after orthotopic heart transplantation have not been previously described. The use of brain natriuretic peptide levels as a surrogate marker for cellular rejection remains controversial, with conflicting data. METHODS: We prospectively evaluated the potential utility of BNP levels in the first 6 months after transplantation and sought correlation with histologic grade of rejection and hemodynamic status. RESULTS: Thirty-five patients and 265 biopsy samples were included in the study. BNP levels did not correlate with histologic grade of rejection. They showed good correlation with central venous pressure and pulmonary capillary wedge pressure. BNP levels were elevated after transplant and showed a steep time-dependent decline. BNP levels correlated with echocardiographically derived indices of diastolic dysfunction. CONCLUSIONS: BNP levels are not a surrogate marker for rejection in the first 2 months after orthotopic heart transplantation and do not obviate the necessity for endomyocardial biopsy. Whether BNP levels have long-term prognostic significance is unclear and remains the subject of ongoing prospective study.