Interpretable recurrent neural network models for dynamic prediction of the extubation failure risk in patients with invasive mechanical ventilation in the intensive care unit.

Background: Clinical decision of extubation is a challenge in the treatment of patient with invasive mechanical ventilation (IMV), since existing extubation protocols are not capable of precisely predicting extubation failure (EF). This study aims to develop and validate interpretable recurrent neural network (RNN) models for dynamically predicting EF risk.

Methods: A retrospective cohort study was conducted on IMV patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database.

[Effect of Environment Adjustment Layers on Nitrogen Transformation in Anaerobic Bioreactor Landfills].

To investigate the perennial effect of environment adjustment layers on the interior environment and nitrogen transformation in anaerobic bioreactor landfills, three sets of simulated anaerobic bioreactor landfills and two kinds of environment adjustment layers of mineralized refuse with heavy calcium carbonate (R2) and mineralized refuse with natural zeolites (R3) were designed and established. The degradation and transformation of nitrogen in waste and leachate had been monitored for 390 days. The results showed that, the value orders of pH, alkalinity, oxidation reduction potential and moisture content (MS) were pH(R2) > pH(R3) > pH(R1), alkalinity (R2) > alkalinity (R3) > alkalinity (R1), Eh(R2) < Eh(R3) < Eh(R1) and MS(R3) > MS(R2) > MS(R1).