RESUMEN
BackgroundAcute kidney injury (AKI) is a recently recognized complication of coronavirus disease-2019 (COVID-19). This study aims to evaluate the incidence, risk factors and case-fatality rate of AKI in patients with documented COVID-19. MethodsWe reviewed the health medical records of 307 consecutive patients hospitalized for symptoms of COVID-19 at the University Hospital of Modena, Italy. ResultsAKI was diagnosed in 69 out of 307 (22.4%) patients. The stages of AKI were stage 1 in 57.9%, stage 2 in 24.6% and stage 3 in 17.3%. Hemodialysis was performed in 7.2% of the subjects. AKI patients had a mean age of 74.7{+/-}9.9 years and higher serum levels of the main marker of inflammation and organ involvement (lung, liver, hearth and liver) than non-AKI patients. AKI events were more frequent in subjects with severe lung comprise. Two peaks of AKI events coincided with in-hospital admission and death of the patients. Kidney injury was associate with a higher rate of urinary abnormalities including proteinuria (0.448{+/-}0.85 vs 0.18{+/-}0.29; P=<0.0001) and hematuria (P=0.032) compared to non-AKI patients. At the end of follow-up, 65.2% of the patients did not recover their renal function after AKI. Risk factors for kidney injury were age, male sex, CKD and non-renal SOFA. Adjusted Cox regression analysis revealed that AKI was independently associated with in-hospital death (hazard ratio [HR]=3.74; CI 95%, 1.34-10.46) compared to non-AKI patients. Groups of patients with AKI stage 2-3 and failure to recover kidney function were associated with the highest risk of in-hospital mortality. Lastly, long-hospitalization was positively associated with a decrease of serum creatinine, likely due to muscle depletion occurred with prolonged bed rest. ConclusionsAKI was a dire consequence of patients with COVID-19. Identification of patients at high-risk for AKI and prevention of kidney injury by avoiding dehydration and nephrotoxic agents is imperative in this vulnerable cohort of patients.
RESUMEN
AimsThe aim of this study was to estimate a 48 hour prediction of moderate to severe respiratory failure, requiring mechanical ventilation, in hospitalized patients with COVID-19 pneumonia. MethodsThis was an observational study that comprised consecutive patients with COVID-19 pneumonia admitted to hospital from 21 February to 6 April 2020. The patients medical history, demographic, epidemiologic and clinical data were collected in an electronic patient chart. The dataset was used to train predictive models using an established machine learning framework leveraging a hybrid approach where clinical expertise is applied alongside a data-driven analysis. The study outcome was the onset of moderate to severe respiratory failure defined as PaO2/FiO2 ratio <150 mmHg in at least one of two consecutive arterial blood gas analyses in the following 48 hours. Shapley Additive exPlanations values were used to quantify the positive or negative impact of each variable included in each model on the predicted outcome. ResultsA total of 198 patients contributed to generate 1068 usable observations which allowed to build 3 predictive models based respectively on 31-variables signs and symptoms, 39-variables laboratory biomarkers and 91-variables as a composition of the two. A fourth "boosted mixed model" included 20 variables was selected from the model 3, achieved the best predictive performance (AUC=0.84) without worsening the FN rate. Its clinical performance was applied in a narrative case report as an example. ConclusionThis study developed a machine model with 84% prediction accuracy, which is able to assist clinicians in decision making process and contribute to develop new analytics to improve care at high technology readiness levels.