ABSTRACT
Background: Acute Kidney Injury (AKI) is a very frequent condition, occurring in about one in three patients admitted to an intensive care unit (ICU). AKI is a syndrome defined as a sudden decrease in glomerular filtration rate. However, this unified definition does not reflect the various mechanisms involved in AKI pathophysiology, each with its own characteristics and sensitivity to therapy. In this study, we aimed at developing an innovative machine learning based method able to subphenotype AKI according to its pattern of risk factors. Methods: We adopted a three-step pipeline of analyses. Firstly, we looked for factors associated with AKI using a generalized additive model. Secondly, we calculated the importance of each identified AKI related factor in the estimated AKI risk to find the main risk factor for AKI, at the single patient level. Lastly, we clusterized AKI patients according to their profile of risk factors and compared the clinical characteristics and outcome of every cluster. We applied this method to a cohort of severe Covid19 patients hospitalized in the ICU of Geneva University Hospitals. Results: Among the 250 patients analyzed, we found ten factors associated with AKI development. Using the individual expression of these factors, we identified three groups of AKI patients, based on the use of Lopinavir/Ritonavir, a prior history of diabetes mellitus and baseline eGFR and ventilation. The three clusters expressed distinct characteristic in terms of AKI severity and recovery, metabolic patterns and ICU mortality. Conclusion: We propose here a new method to phenotype AKI patients according to their most important individual risk factors for AKI development. When applied to an ICU cohort of Covid19 patients, we were able to differentiate three groups of patients. Each expressed specific AKI characteristics and outcomes, which probably reflects a distinct pathophysiology.
Subject(s)
Diabetes Mellitus , Kidney Diseases , Acute Kidney Injury , COVID-19ABSTRACT
Background: Delaying time to prone positioning (PP) may be associated with higher mortality in acute respiratory distress syndrome (ARDS) due to coronavirus disease 2019 (COVID-19). We evaluated the use and the impact of early PP on clinical outcomes in intubated patients hospitalized in intensive care units (ICUs) for COVID-19. Methods: All intubated patients with ARDS due to COVID-19 were involved in a secondary analysis from a prospective multicenter cohort study of COVID-ICU network including 149 ICUs across France, Belgian and Switzerland. Patients were followed-up until Day-90. The primary outcome was survival at Day-60. Analysis used a Cox proportional hazard model including a propensity score. Results: Among 2137 intubated patients, 1504 (70.4%) were placed in PP during their ICU stay, and 491 (23%) during the first 24 hrs following ICU admission. One hundred and eighty-one patients (36.9%) of the early PP group had a PaO 2 /FiO 2 ratio > 150 mmHg when prone positioning was initiated. Among non-early PP group patients, 1013 (47.4%) patients had finally been placed in PP within a median delay of 3 days after ICU admission. Day-60 mortality in non-early PP group was 34.2% vs. 39.3% in the early PP group ( p = 0.038). Day-28 and Day-90 mortality as well as the need for adjunctive therapies were more important in patients with early PP. After propensity score adjustment, no significant difference in survival at Day-60 was found between the two-study groups (HR 1.34 [0.96-1.68], p =0.09 and HR 1.19 [0.998-1.412], p =0.053 in complete case analysis or in multiple imputation analysis, respectively). Conclusions: In a large multicentric international cohort of intubated ICU patients with ARDS due to COVID-19, PP has been used frequently as a main treatment. In this study, early PP started within 24 hrs after ICU admission was not associated with a survival benefit compared to PP after day 1.