ABSTRACT
INTRODUCTION: Intensivists have faced difficult decisions about when to intubate patients during the Covid 19 pandemic. Initial studies had suggested that early intubation may be beneficial, as patients would avoid self induced lung injury, whereas later studies indicated that delaying intubation could be advantageous in some patients by avoiding the inherent risks of mechanical ventilation. This study aims to assess if NIPPV and HiFlow NC are safe methods of oxygenation in patients with Covid 19 ARDS and can prevent intubation. METHOD(S): A retrospective chart review of 693 patients was conducted. These patients tested positive for Covid 19 during hospitalization AND required supplemental oxygen via either HiFlow or NIPPV (including CPAP and BiPAP). Demographic and clinical characteristics were compared between intubated and nonintubated patients. Associations between days on NIPPV/HiFlow and hospital outcomes were assessed by univariable linear regression for continuous outcomes and by univariable logistic regression for dichotomous outcomes. Subgroup analysis was conducted on patients who were intubated, those who were in the ICU, and those who died. All analyses were conducted using R v. 4.0.3. RESULT(S): Among all patients, each additional day on NIPPV/HiFlow was associated with a 0.14 day decrease in overall hospital length of stay and reduced odds of intubation. Furthermore, each additional day on NIPPV/HiFlow was NOT associated with increased odds of complications such as VTE, PE, cerebral thrombosis, pneumothorax, GI bleeding or ICU admission. This held true in the subgroups as well. We also found that when compared against nonintubated patients, intubated patients had a significantly shorter median length of time on NIPPV/HiFlow (5 days vs 7) and a longer total median hospital length of stay (23 days vs 11), along with a significantly higher rate of VTE (15% vs 4.9%), pneumothorax (8.1% vs 1.5%), cerebral thrombosis (4.5% vs 1.5%), and PE (4.5% vs 1.1%). CONCLUSION(S): Our results suggest that NIPPV/ HiFlow does not worsen patient outcomes in patients with Covid 19 and may save some patients from intubation. Nonetheless, intubation should not be withheld in patients who decompensate on NIPPV/HiFlow as these patients have more Covid related complications and require additional support.
ABSTRACT
Although, recently convolutional neural networks (CNNs) based prognostic models have been developed for COVID-19 severity prediction, most of these studies have analyzed characteristics of lung infiltrates (ground-glass opacities and consolidations) on chest radiographs or CT. However, none of the studies have explored the possible lung deformations due to the disease. Our hypothesis is that more severe disease results in more pronounced deformation. The key contributions of this work are three-fold: (1) A new lung deformation based biomarker analyzing regions of differential distensions between COVID-19 patients with mild and severe disease. (2) Integrating 3D-CNN characterization of lung deformation regions and lung infiltrates on lung CT into a novel framework (LuMiRa) for prognosticating COVID-19 severity. (3) Validating LuMiRa on one of the largest multi-institutional cohort till date (N = 948 patients). We found that majority of the shape deformations were observed in the mediastinal surface of both the lungs and in left interior lobe. On a testing cohort based on two institutions, Av (N = 419) and Bv (N = 113), LuMiRa yielded an area under the receiver operating characteristic curve (AUC) of 0.89 and 0.77 respectively showing significant improvement over a 3D-CNN trained over just lung infiltrates (AUC = 0.85 (p < 0.001), AUC = 0.75 (p = 0.01)). Additionally, LuMiRa performed significantly better than machine learning models trained on clinical and radiomic features (0.82, 0.78 and 0.72, 0.72 on Av and Bv respectively). © 2021, Springer Nature Switzerland AG.