Background Improved mortality prediction for patients in intensive care units (ICU) remains an important challenge. Many severity scores have been proposed but validation studies have concluded that they are not adequately calibrated. Many flexible algorithms are available, yet none of these individually outperform all others regardless of context. In contrast, the Super Learner (SL), an ensemble machine learning technique that leverages on multiple learning algorithms to obtain better prediction performance, has been shown to perform at least as well as the optimal member of its library. It might provide an ideal opportunity to construct a novel severity score with an improved performance profile. The aim of the present study was to provide a new mortality prediction algorithm for ICU patients using an implementation of the Super Learner, and to assess its performance relative to prediction based on the SAPS II, APACHE II and SOFA scores. Methods We used the Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database (v26) including all patients admitted to an ICU at Boston’s Beth Israel Deaconess Medical Center from 2001 to 2008. The calibration, discrimination and risk classification of predicted hospital mortality based on SAPS II, on APACHE II, on SOFA and on our Super Learned-based proposal were evaluated. Performance measures were calculated using cross-validation to avoid making biased assessments. Our proposed score was then externally validated on a dataset of 200 randomly selected patients admitted at the ICU of Hôpital Européen Georges-Pompidou in Paris, France between September 2013 and June 2014. The primary outcome was hospital mortality. The explanatory variables were the same as those included in the SAPS II score. Results 24,508 patients were included, with median SAPS II 38 (IQR: 27–51), median SOFA 5 (IQR: 2–8). A total of 3,002/24,508(12.2%) patients died in the hospital. The two versions of our Super Learner-based proposal yielded average predicted probabilities of death of 0.12 (IQR: 0.02–0.16) and 0.13 (IQR: 0.01–0.19), whereas the corresponding values for the SOFA and SAPS II scores were, respectively, 0.12 (IQR: 0.05–0.15) and 0.30 (IQR: 0.08–0.48). The cross-validated area under the receiver operating characteristics curve (AUROC) for SAPS II and SOFA were 0.78(95%CI: 0.77–0.78) and 0.71 (95%CI: 0.71–0.72), respectively. Our proposal reached an AUROC of 0.85 (95%CI: 0.84–0.85) when the explanatory variables were categorized as in SAPS II, and of 0.88 (95%CI: 0.87–0.89) when the same explanatory variables were included without any transformation. In addition, it exhibited better calibration properties than previous score systems. On the external validation dataset, the AUROC was 0.94 (95%CI: 0.90–0.98) and calibration properties were good. Interpretation As compared to conventional severity scores, our Super Learner-based proposal offers improved performance for predicting hospital mortality in ICU patients. A user-friendly implementation is available online an...
For a given severity, mHLA-DR proved not to a predictive marker of outcome, but a weak trend of mHLA-DR recovery was associated with an increased risk of secondary infection. Monitoring immune functions through mHLA-DR in intensive care unit patients therefore could be useful to identify a high risk of secondary infection.
BackgroundPropensity score (PS) methods are increasingly used, even when sample sizes are small or treatments are seldom used. However, the relative performance of the two mainly recommended PS methods, namely PS-matching or inverse probability of treatment weighting (IPTW), have not been studied in the context of small sample sizes.MethodsWe conducted a series of Monte Carlo simulations to evaluate the influence of sample size, prevalence of treatment exposure, and strength of the association between the variables and the outcome and/or the treatment exposure, on the performance of these two methods.ResultsDecreasing the sample size from 1,000 to 40 subjects did not substantially alter the Type I error rate, and led to relative biases below 10%. The IPTW method performed better than the PS-matching down to 60 subjects. When N was set at 40, the PS matching estimators were either similarly or even less biased than the IPTW estimators. Including variables unrelated to the exposure but related to the outcome in the PS model decreased the bias and the variance as compared to models omitting such variables. Excluding the true confounder from the PS model resulted, whatever the method used, in a significantly biased estimation of treatment effect. These results were illustrated in a real dataset.ConclusionEven in case of small study samples or low prevalence of treatment, PS-matching and IPTW can yield correct estimations of treatment effect unless the true confounders and the variables related only to the outcome are not included in the PS model.
Despite the fact that elderly patients have more intensive care unit rejections than younger patients and have a higher mortality when admitted, the mortality benefit appears greater for the elderly. Physicians should consider changing their intensive care unit triage practices for the elderly.
When compared to usual medical care, immediate application of CPAP alone in out-of-hospital treatment of ACPO is significantly better improving physiological variables and symptoms and significantly reduces tracheal intubation incidence and in-hospital mortality.
EudraCT Number: 2012-000232-25; clinicaltrials.gov Identifier: NCT02184819.
Aims Out-of-hospital cardiac arrest (OHCA) without return of spontaneous circulation (ROSC) despite conventional resuscitation is common and has poor outcomes. Adding extracorporeal membrane oxygenation (ECMO) to cardiopulmonary resuscitation (extracorporeal-CPR) is increasingly used in an attempt to improve outcomes. Methods and results We analysed a prospective registry of 13 191 OHCAs in the Paris region from May 2011 to January 2018. We compared survival at hospital discharge with and without extracorporeal-CPR and identified factors associated with survival in patients given extracorporeal-CPR. Survival was 8% in 525 patients given extracorporeal-CPR and 9% in 12 666 patients given conventional-CPR (P = 0.91). By adjusted multivariate analysis, extracorporeal-CPR was not associated with hospital survival [odds ratio (OR), 1.3; 95% confidence interval (95% CI), 0.8–2.1; P = 0.24]. By conditional logistic regression with matching on a propensity score (including age, sex, occurrence at home, bystander CPR, initial rhythm, collapse-to-CPR time, duration of resuscitation, and ROSC), similar results were found (OR, 0.8; 95% CI, 0.5–1.3; P = 0.41). In the extracorporeal-CPR group, factors associated with hospital survival were initial shockable rhythm (OR, 3.9; 95% CI, 1.5–10.3; P = 0.005), transient ROSC before ECMO (OR, 2.3; 95% CI, 1.1–4.7; P = 0.03), and prehospital ECMO implantation (OR, 2.9; 95% CI, 1.5–5.9; P = 0.002). Conclusions In a population-based registry, 4% of OHCAs were treated with extracorporeal-CPR, which was not associated with increased hospital survival. Early ECMO implantation may improve outcomes. The initial rhythm and ROSC may help select patients for extracorporeal-CPR.
The consistency of propensity score (PS) estimators relies on correct specification of the PS model. The PS is frequently estimated using main-effects logistic regression. However, the underlying model assumptions may not hold. Machine learning methods provide an alternative nonparametric approach to PS estimation. In this simulation study, we evaluated the benefit of using Super Learner (SL) for PS estimation. We created 1,000 simulated data sets (n = 500) under 4 different scenarios characterized by various degrees of deviance from the usual main-term logistic regression model for the true PS. We estimated the average treatment effect using PS matching and inverse probability of treatment weighting. The estimators' performance was evaluated in terms of PS prediction accuracy, covariate balance achieved, bias, standard error, coverage, and mean squared error. All methods exhibited adequate overall balancing properties, but in the case of model misspecification, SL performed better for highly unbalanced variables. The SL-based estimators were associated with the smallest bias in cases of severe model misspecification. Our results suggest that use of SL to estimate the PS can improve covariate balance and reduce bias in a meaningful manner in cases of serious model misspecification for treatment assignment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.