OBJECTIVES: Critically ill patients with coronavirus disease 2019 have variable mortality. Risk scores could improve care and be used for prognostic enrichment in trials. We aimed to compare machine learning algorithms and develop a simple tool for predicting 28-day mortality in ICU patients with coronavirus disease 2019. DESIGN: This was an observational study of adult patients with coronavirus disease 2019. The primary outcome was 28-day inhospital mortality. Machine learning models and a simple tool were derived using variables from the first 48 hours of ICU admission and validated externally in independent sites and temporally with more recent admissions. Models were compared with a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 using the area under the receiver operating characteristic curve and calibration. SETTING: Sixty-eight U.S. ICUs. PATIENTS: Adults with coronavirus disease 2019 admitted to 68 ICUs in the United States between March 4, 2020, and June 29, 2020. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The study included 5,075 patients, 1,846 (36.4%) of whom died by day 28. eXtreme Gradient Boosting had the highest area under the receiver operating characteristic curve in external validation (0.81) and was well-calibrated, while k-nearest neighbors were the lowest performing machine learning algorithm (area under the receiver operating characteristic curve 0.69). Findings were similar with temporal validation. The simple tool, which was created using the most important features from the eXtreme Gradient Boosting model, had a significantly higher area under the receiver operating characteristic curve in external validation (0.78) than the Sequential Organ Failure Assessment score (0.69), National Early Warning Score (0.60), and CURB-65 (0.65; p < 0.05 for all comparisons). Age, number of ICU beds, creatinine, lactate, arterial pH, and Pao2/Fio2 ratio were the most important predictors in the eXtreme Gradient Boosting model. CONCLUSIONS: eXtreme Gradient Boosting had the highest discrimination overall, and our simple tool had higher discrimination than a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 on external validation. These models could be used to improve triage decisions and clinical trial enrichment.

PURPOSE: Limited data are available on venovenous extracorporeal membrane oxygenation (ECMO) in patients with severe hypoxemic respiratory failure from coronavirus disease 2019 (COVID-19). METHODS: We examined the clinical features and outcomes of 190 patients treated with ECMO within 14 days of ICU admission, using data from a multicenter cohort study of 5122 critically ill adults with COVID-19 admitted to 68 hospitals across the United States. To estimate the effect of ECMO on mortality, we emulated a target trial of ECMO receipt versus no ECMO receipt within 7 days of ICU admission among mechanically ventilated patients with severe hypoxemia (PaO2/FiO2 < 100). Patients were followed until hospital discharge, death, or a minimum of 60 days. We adjusted for confounding using a multivariable Cox model. RESULTS: Among the 190 patients treated with ECMO, the median age was 49 years (IQR 41-58), 137 (72.1%) were men, and the median PaO2/FiO2 prior to ECMO initiation was 72 (IQR 61-90). At 60 days, 63 patients (33.2%) had died, 94 (49.5%) were discharged, and 33 (17.4%) remained hospitalized. Among the 1297 patients eligible for the target trial emulation, 45 of the 130 (34.6%) who received ECMO died, and 553 of the 1167 (47.4%) who did not receive ECMO died. In the primary analysis, patients who received ECMO had lower mortality than those who did not (HR 0.55; 95% CI 0.41-0.74). Results were similar in a secondary analysis limited to patients with PaO2/FiO2 < 80 (HR 0.55; 95% CI 0.40-0.77). CONCLUSION: In select patients with severe respiratory failure from COVID-19, ECMO may reduce mortality.

BACKGROUND: Intravenous fluids and vasopressor agents are commonly used in early resuscitation of patients with sepsis, but comparative data for prioritizing their delivery are limited. METHODS: In an unblinded superiority trial conducted at 60 U.S. centers, we randomly assigned patients to either a restrictive fluid strategy (prioritizing vasopressors and lower intravenous fluid volumes) or a liberal fluid strategy (prioritizing higher volumes of intravenous fluids before vasopressor use) for a 24-hour period. Randomization occurred within 4 hours after a patient met the criteria for sepsis-induced hypotension refractory to initial treatment with 1 to 3 liters of intravenous fluid. We hypothesized that all-cause mortality before discharge home by day 90 (primary outcome) would be lower with a restrictive fluid strategy than with a liberal fluid strategy. Safety was also assessed. RESULTS: A total of 1563 patients were enrolled, with 782 assigned to the restrictive fluid group and 781 to the liberal fluid group. Resuscitation therapies that were administered during the 24-hour protocol period differed between the two groups; less intravenous fluid was administered in the restrictive fluid group than in the liberal fluid group (difference of medians, -2134 ml; 95% confidence interval [CI], -2318 to -1949), whereas the restrictive fluid group had earlier, more prevalent, and longer duration of vasopressor use. Death from any cause before discharge home by day 90 occurred in 109 patients (14.0%) in the restrictive fluid group and in 116 patients (14.9%) in the liberal fluid group (estimated difference, -0.9 percentage points; 95% CI, -4.4 to 2.6; P = 0.61); 5 patients in the restrictive fluid group and 4 patients in the liberal fluid group had their data censored (lost to follow-up). The number of reported serious adverse events was similar in the two groups. CONCLUSIONS: Among patients with sepsis-induced hypotension, the restrictive fluid strategy that was used in this trial did not result in significantly lower (or higher) mortality before discharge home by day 90 than the liberal fluid strategy. (Funded by the National Heart, Lung, and Blood Institute; CLOVERS ClinicalTrials.gov number, NCT03434028.).

Prompt intravenous fluid therapy is a fundamental treatment for patients with septic shock. However, the optimal approach for administering intravenous fluid in septic shock resuscitation is unknown. Two competing strategies are emerging: a liberal fluids approach, consisting of a larger volume of initial fluid (50 to 75 mL/kg [4 to 6 L in an 80-kg adult] during the first 6 hours) and later use of vasopressors, versus a restrictive fluids approach, consisting of a smaller volume of initial fluid (≤30 mL/kg [≤2 to 3 L]), with earlier reliance on vasopressor infusions to maintain blood pressure and perfusion. Early fluid therapy may enhance or maintain tissue perfusion by increasing venous return and cardiac output. However, fluid administration may also have deleterious effects by causing edema within vital organs, leading to organ dysfunction and impairment of oxygen delivery. Conversely, a restrictive fluids approach primarily relies on vasopressors to reverse hypotension and maintain perfusion while limiting the administration of fluid. Both strategies have some evidence to support their use but lack robust data to confirm the benefit of one strategy over the other, creating clinical and scientific equipoise. As part of the National Heart, Lung, and Blood Institute Prevention and Early Treatment of Acute Lung Injury Network, we designed a randomized clinical trial to compare the liberal and restrictive fluids strategies, the Crystalloid Liberal or Vasopressor Early Resuscitation in Sepsis trial. The purpose of this article is to review the current literature on approaches to early fluid resuscitation in adults with septic shock and outline the rationale for the upcoming trial.

Rationale & objective

Underlying kidney disease is an emerging risk factor for more severe coronavirus disease 2019 (COVID-19) illness. We examined the clinical courses of critically ill COVID-19 patients with and without pre-existing chronic kidney disease (CKD) and investigated the association between the degree of underlying kidney disease and in-hospital outcomes.

Study design

Retrospective cohort study.

Settings & participants

4,264 critically ill patients with COVID-19 (143 patients with pre-existing kidney failure receiving maintenance dialysis; 521 patients with pre-existing non-dialysis-dependent CKD; and 3,600 patients without pre-existing CKD) admitted to intensive care units (ICUs) at 68 hospitals across the United States.

Predictor(s)

Presence (vs absence) of pre-existing kidney disease.

Outcome(s)

In-hospital mortality (primary); respiratory failure, shock, ventricular arrhythmia/cardiac arrest, thromboembolic events, major bleeds, and acute liver injury (secondary).

Analytical approach

We used standardized differences to compare patient characteristics (values>0.10 indicate a meaningful difference between groups) and multivariable-adjusted Fine and Gray survival models to examine outcome associations.

Results

Dialysis patients had a shorter time from symptom onset to ICU admission compared to other groups (median of 4 [IQR, 2-9] days for maintenance dialysis patients; 7 [IQR, 3-10] days for non-dialysis-dependent CKD patients; and 7 [IQR, 4-10] days for patients without pre-existing CKD). More dialysis patients (25%) reported altered mental status than those with non-dialysis-dependent CKD (20%; standardized difference=0.12) and those without pre-existing CKD (12%; standardized difference=0.36). Half of dialysis and non-dialysis-dependent CKD patients died within 28 days of ICU admission versus 35% of patients without pre-existing CKD. Compared to patients without pre-existing CKD, dialysis patients had higher risk for 28-day in-hospital death (adjusted HR, 1.41 [95% CI, 1.09-1.81]), while patients with non-dialysis-dependent CKD had an intermediate risk (adjusted HR, 1.25 [95% CI, 1.08-1.44]).

Limitations

Potential residual confounding.

Conclusions

Findings highlight the high mortality of individuals with underlying kidney disease and severe COVID-19, underscoring the importance of identifying safe and effective COVID-19 therapies in this vulnerable population.