Clinical characteristics and outcomes in COVID-19 in kidney transplant recipients: a propensity score matched cohort study.

Patients with chronic kidney disease (CKD), especially those on dialysis or who have received a kidney transplant (KT), are considered more vulnerable to severe COVID-19. This susceptibility is attributed to advanced age, a higher frequency of comorbidities, and the chronic immunosuppressed state, which may exacerbate their susceptibility to severe outcomes. Therefore, our study aimed to compare the clinical characteristics and outcomes of COVID-19 in KT patients with those on chronic dialysis and non-CKD patients in a propensity score-matched cohort study. This multicentric retrospective cohort included adult COVID-19 laboratory-confirmed patients admitted from March/2020 to July/2022, from 43 Brazilian hospitals. The primary outcome was in-hospital mortality. Propensity score analysis matched KT recipients with controls - patients on chronic dialysis and those without CKD (within 0.25 standard deviations of the logit of the propensity score) - according to age, sex, number of comorbidities, and admission year. This study included 555 patients: 163 KT, 146 on chronic dialysis, and 249 non-CKD patients (median age 57 years, 55.2% women). With regards to clinical outcomes, chronic dialysis patients had a higher prevalence of acute heart failure, compared to KT recipients, furthermore, both groups presented high in-hospital mortality, 34.0 and 28.1%, for KT and chronic dialysis patients, respectively. When comparing KT and non-CKD patients, the first group had a higher incidence of in-hospital dialysis (26.4% vs. 8.8%, p < 0.001), septic shock (24.1% vs. 12.0%, p = 0.002), and mortality (32.5% vs. 23.3%, p = 0.039), in addition to longer time spent in the intensive care unit (ICU). In this study, chronic dialysis patients presented a higher prevalence of acute heart failure, compared to KT recipients, whereas KT patients had a higher frequency of complications than those without CKD, including septic shock, dialysis during hospitalization, and in-hospital mortality as well as longer time spent in the ICU.

Potential and limitations of machine meta-learning (ensemble) methods for predicting COVID-19 mortality in a large inhospital Brazilian dataset.

The majority of early prediction scores and methods to predict COVID-19 mortality are bound by methodological flaws and technological limitations (e.g., the use of a single prediction model). Our aim is to provide a thorough comparative study that tackles those methodological issues, considering multiple techniques to build mortality prediction models, including modern machine learning (neural) algorithms and traditional statistical techniques, as well as meta-learning (ensemble) approaches. This study used a dataset from a multicenter cohort of 10,897 adult Brazilian COVID-19 patients, admitted from March/2020 to November/2021, including patients [median age 60 (interquartile range 48-71), 46% women]. We also proposed new original population-based meta-features that have not been devised in the literature. Stacking has shown to achieve the best results reported in the literature for the death prediction task, improving over previous state-of-the-art by more than 46% in Recall for predicting death, with AUROC 0.826 and MacroF1 of 65.4%. The newly proposed meta-features were highly discriminative of death, but fell short in producing large improvements in final prediction performance, demonstrating that we are possibly on the limits of the prediction capabilities that can be achieved with the current set of ML techniques and (meta-)features. Finally, we investigated how the trained models perform on different hospitals, showing that there are indeed large differences in classifier performance between different hospitals, further making the case that errors are produced by factors that cannot be modeled with the current predictors.

Predictors of venous thromboembolism in COVID-19 patients: results of the COVID-19 Brazilian Registry.

Previous studies that assessed risk factors for venous thromboembolism (VTE) in COVID-19 patients have shown inconsistent results. Our aim was to investigate VTE predictors by both logistic regression (LR) and machine learning (ML) approaches, due to their potential complementarity. This cohort study of a large Brazilian COVID-19 Registry included 4120 COVID-19 adult patients from 16 hospitals. Symptomatic VTE was confirmed by objective imaging. LR analysis, tree-based boosting, and bagging were used to investigate the association of variables upon hospital presentation with VTE. Among 4,120 patients (55.5% men, 39.3% critical patients), VTE was confirmed in 6.7%. In multivariate LR analysis, obesity (OR 1.50, 95% CI 1.11-2.02); being an ex-smoker (OR 1.44, 95% CI 1.03-2.01); surgery ≤ 90 days (OR 2.20, 95% CI 1.14-4.23); axillary temperature (OR 1.41, 95% CI 1.22-1.63); D-dimer ≥ 4 times above the upper limit of reference value (OR 2.16, 95% CI 1.26-3.67), lactate (OR 1.10, 95% CI 1.02-1.19), C-reactive protein levels (CRP, OR 1.09, 95% CI 1.01-1.18); and neutrophil count (OR 1.04, 95% CI 1.005-1.075) were independent predictors of VTE. Atrial fibrillation, peripheral oxygen saturation/inspired oxygen fraction (SF) ratio and prophylactic use of anticoagulants were protective. Temperature at admission, SF ratio, neutrophil count, D-dimer, CRP and lactate levels were also identified as predictors by ML methods. By using ML and LR analyses, we showed that D-dimer, axillary temperature, neutrophil count, CRP and lactate levels are risk factors for VTE in COVID-19 patients.