Background A high body mass index (BMI) has been associated with decreased mortality in critically ill patients. This association may, in part, relate to the impact of BMI on glycemia. We aimed to study the relationship between BMI, glycemia and hospital mortality. Methods We included all patients with a recorded BMI from four large international clinical databases (n = 259,177). We investigated the unadjusted association of BMI with average glucose levels, mortality and hypoglycemia rate. We applied multivariate analysis to investigate the impact of BMI on hypoglycemia rate, after adjusting for glycemia-relevant treatments (insulin, dextrose, corticosteroids, enteral and parenteral nutrition) and key physiological parameters (previous blood glucose level, blood lactate, shock state, SOFA score). Results We analyzed 5,544,366 glucose measurements. On unadjusted analysis, increasing BMI was associated with increasing glucose levels (average increase of 5 and 10 mg/dL for the 25–30, 30–35 kg/m2 BMI groups compared to normal BMI (18.5–25 kg/m2) patients). Despite greater hyperglycemia, increasing BMI was associated with lower hospital mortality (average decrease of 2% and 3.25% for the 25–30, 30–35 kg/m2 groups compared to normal BMI patients) and lower hypoglycemia rate (average decrease of 2.5% and 3.5% for the 25–30, 30–35 kg/m2 groups compared to normal BMI patients). Increasing BMI was significantly independently associated with reduced hypoglycemia rate, with odds ratio (OR) 0.72 and 0.65, respectively (95% CIs 0.67–0.77 and 0.60–0.71, both p < 0.001) when compared with normal BMI. Low BMI patients showed greater hypoglycemia rate, with OR 1.6 (CI 1.43–1.79, p < 0.001). The association of high BMI and decreased mortality did not apply to diabetic patients. Although diabetic patients had higher rates of hypoglycemia overall and higher glucose variability (p < 0.001), they also had a reduced risk of hypoglycemia with higher BMI levels (p < 0.001). Conclusions Increasing BMI is independently associated with decreased risk of hypoglycemia. It is also associated with increasing hyperglycemia and yet with lower mortality. Lower risk of hypoglycemia might contribute to decreased mortality and might partly explain the obesity paradox. These associations, however, were markedly modified by the presence of diabetes. Graphical Abstract

No abstract

Background The prediction of in‐hospital mortality for ICU patients with COVID‐19 is fundamental to treatment and resource allocation. The main purpose was to develop an easily implemented score for such prediction. Methods This was an observational, multicenter, development, and validation study on a national critical care dataset of COVID‐19 patients. A systematic literature review was performed to determine variables possibly important for COVID‐19 mortality prediction. Using a logistic multivariable model with a LASSO penalty, we developed the Rapid Evaluation of Coronavirus Illness Severity (RECOILS) score and compared its performance against published scores. Results Our development (validation) cohort consisted of 1480 (937) adult patients from 14 (11) Dutch ICUs admitted between March 2020 and April 2021. Median age was 65 (65) years, 31% (26%) died in hospital, 74% (72%) were males, average length of ICU stay was 7.83 (10.25) days and average length of hospital stay was 15.90 (19.92) days. Age, platelets, PaO2/FiO2 ratio, pH, blood urea nitrogen, temperature, PaCO2, Glasgow Coma Scale (GCS) score measured within +/−24 h of ICU admission were used to develop the score. The AUROC of RECOILS score was 0.75 (CI 0.71–0.78) which was higher than that of any previously reported predictive scores (0.68 [CI 0.64–0.71], 0.61 [CI 0.58–0.66], 0.67 [CI 0.63–0.70], 0.70 [CI 0.67–0.74] for ISARIC 4C Mortality Score, SOFA, SAPS‐III, and age, respectively). Conclusions Using a large dataset from multiple Dutch ICUs, we developed a predictive score for mortality of COVID‐19 patients admitted to ICU, which outperformed other predictive scores reported so far.

Objective To develop a unified framework for analyzing data from 5 large publicly available intensive care unit (ICU) datasets. Findings Using 3 American (Medical Information Mart for Intensive Care III, Medical Information Mart for Intensive Care IV, electronic ICU) and 2 European (Amsterdam University Medical Center Database, High Time Resolution ICU Dataset) databases, we constructed a mapping for each database to a set of clinically relevant concepts, which are grounded in the Observational Medical Outcomes Partnership Vocabulary wherever possible. Furthermore, we performed synchronization in the units of measurement and data type representation. On top of this, we built functionality, which allows the user to download, set up, and load data from all of the 5 databases, through a unified Application Programming Interface. The resulting ricu R-package represents the computational infrastructure for handling publicly available ICU datasets, and its latest release allows the user to load 119 existing clinical concepts from the 5 data sources. Conclusion The ricu R-package (available on GitHub and CRAN) is the first tool that enables users to analyze publicly available ICU datasets simultaneously (datasets are available upon request from respective owners). Such an interface saves researchers time when analyzing ICU data and helps reproducibility. We hope that ricu can become a community-wide effort, so that data harmonization is not repeated by each research group separately. One current limitation is that concepts were added on a case-to-case basis, and therefore the resulting dictionary of concepts is not comprehensive. Further work is needed to make the dictionary comprehensive.

Machine learning algorithms are useful for various predictions tasks, but they can also learn how to discriminate, based on gender, race or other sensitive attributes. This realization gave rise to the field of fair machine learning, which aims to measure and mitigate such algorithmic bias. This manuscript describes the R-package fairadapt, which implements a causal inference pre-processing method. By making use of a causal graphical model and the observed data, the method can be used to address hypothetical questions of the form "What would my salary have been, had I been of a different gender/race?". Such individual level counterfactual reasoning can help eliminate discrimination and help justify fair decisions. We also discuss appropriate relaxations which assume certain causal pathways from the sensitive attribute to the outcome are not discriminatory.