Open Access

Introduction: Acute lung injury (ALI) is an inflammatory disorder of pulmonary or extrapulmonary origin. We have previously demonstrated that netrin-1 dampens murine ALI, and in an attempt to advance this finding into future clinical practice we evaluated whether netrin-1 would reduce alveolar inflammation during porcine ALI. Methods: This was a controlled in vivo experimental study in pigs. We induced ALI through lipoploysaccharide (LPS) infusion (50 micro g/kg) for 2 hours. Following this, we exposed animals to either vehicle, intravenous netrin-1 (netrin-1 i.v.) or inhaled netrin-1 (netrin-1 inh.). Serum samples and bronchoalveolar lavage (BAL) were obtained to determine levels of tumor necrosis factor-alpha (TNF-alpha), interleukin (IL)-1beta, interleukin-6 and interleukin-8 at baseline and 6 hours following treatment. Myeloperoxidase activity (MPO) and protein levels were determined in the BAL, and tissue samples were obtained for histological evaluation. Finally, animals were scanned with spiral CT. Results: Following LPS infusion, animals developed acute pulmonary injury. Serum levels of TNF-alpha and IL-6 were significantly reduced in the netrin-1 i.v. group. BAL demonstrated significantly reduced cytokine levels 6 hours post-netrin-1 treatment (TNF-alpha: vehicle 633 ± 172 pg/ml, netrin-1 i.v. 84 ± 5 pg/ml, netrin-1 inh. 168 ± 74 pg/ml; both P < 0.05). MPO activity and protein content were significantly reduced in BAL samples from netrin-1-treated animals. Histological sections confirmed reduced inflammatory changes in the netrin-1-treated animals. Computed tomography corroborated reduced pulmonary damage in both netrin-1-treated groups. Conclusions: We conclude that treatment with the endogenous anti-inflammatory protein netrin-1 reduces pulmonary inflammation during the initial stages of ALI and should be pursued as a future therapeutic option.

Background: Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes. Methods: A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported. Results: 1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy. Conclusions: Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models. Trial registration “ClinicalTrials” (clinicaltrials.gov) under NCT04455451.