Predictors of shorter- and longer-term mortality after COVID-19 presentation among dialysis patients: parallel use of machine learning models in Latin and North American countries.

BACKGROUND: We developed machine learning models to understand the predictors of shorter-, intermediate-, and longer-term mortality among hemodialysis (HD) patients affected by COVID-19 in four countries in the Americas. METHODS: We used data from adult HD patients treated at regional institutions of a global provider in Latin America (LatAm) and North America who contracted COVID-19 in 2020 before SARS-CoV-2 vaccines were available. Using 93 commonly captured variables, we developed machine learning models that predicted the likelihood of death overall, as well as during 0-14, 15-30, > 30 days after COVID-19 presentation and identified the importance of predictors. XGBoost models were built in parallel using the same programming with a 60%:20%:20% random split for training, validation, & testing data for the datasets from LatAm (Argentina, Columbia, Ecuador) and North America (United States) countries. RESULTS: Among HD patients with COVID-19, 28.8% (1,001/3,473) died in LatAm and 20.5% (4,426/21,624) died in North America. Mortality occurred earlier in LatAm versus North America; 15.0% and 7.3% of patients died within 0-14 days, 7.9% and 4.6% of patients died within 15-30 days, and 5.9% and 8.6% of patients died > 30 days after COVID-19 presentation, respectively. Area under curve ranged from 0.73 to 0.83 across prediction models in both regions. Top predictors of death after COVID-19 consistently included older age, longer vintage, markers of poor nutrition and more inflammation in both regions at all timepoints. Unique patient attributes (higher BMI, male sex) were top predictors of mortality during 0-14 and 15-30 days after COVID-19, yet not mortality > 30 days after presentation. CONCLUSIONS: Findings showed distinct profiles of mortality in COVID-19 in LatAm and North America throughout 2020. Mortality rate was higher within 0-14 and 15-30 days after COVID-19 in LatAm, while mortality rate was higher in North America > 30 days after presentation. Nonetheless, a remarkable proportion of HD patients died > 30 days after COVID-19 presentation in both regions. We were able to develop a series of suitable prognostic prediction models and establish the top predictors of death in COVID-19 during shorter-, intermediate-, and longer-term follow up periods.

Randomised, controlled, open label, multicentre clinical trial to explore safety and efficacy of hyperbaric oxygen for preventing ICU admission, morbidity and mortality in adult patients with COVID-19.

INTRODUCTION: COVID-19 may cause severe pneumonitis and trigger a massive inflammatory response that requires ventilatory support. The intensive care unit (ICU)-mortality has been reported to be as high as 62%. Dexamethasone is the only of all anti-inflammatory drugs that have been tested to date that has shown a positive effect on mortality. We aim to explore if treatment with hyperbaric oxygen (HBO) is safe and effective for patients with severe COVID-19. Our hypothesis is that HBO can prevent ICU admission, morbidity and mortality by attenuating the inflammatory response. The primary objective is to evaluate if HBO reduces the number of ICU admissions compared with best practice treatment for COVID-19, main secondary objectives are to evaluate if HBO reduces the load on ICU resources, morbidity and mortality and to evaluate if HBO mitigates the inflammatory reaction in COVID-19. METHODS AND ANALYSIS: A randomised, controlled, phase II, open label, multicentre trial. 200 subjects with severe COVID-19 and at least two risk factors for mortality will be included. Baseline clinical data and blood samples will be collected before randomisation and repeated daily for 7 days, at days 14 and 30. Subjects will be randomised with a computer-based system to HBO, maximum five times during the first 7 days plus best practice treatment or only best practice treatment. The primary endpoint, ICU admission, is defined by criteria for selection for ICU. We will evaluate if HBO mitigates the inflammatory reaction in COVID-19 using molecular analyses. All parameters are recorded in an electronic case report form. An independent Data Safety Monitoring Board will review the safety parameters. ETHICS AND DISSEMINATION: The trial is approved by The National Institutional Review Board in Sweden (2020-01705) and the Swedish Medical Product Agency (5.1-2020-36673). Positive, negative and any inconclusive results will be published in peer-reviewed scientific journals with open access. TRIAL REGISTRATION: NCT04327505. EudraCT number: 2020-001349-37.