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...
Early EUS-CPN reduces pain and may moderate morphine consumption in patients with painful, inoperable pancreatic adenocarcinoma. EUS-CPN can be considered in all such patients at the time of diagnostic and staging EUS.
Substantial differences in perceptions and practices of brain death exist worldwide. The identification of discrepancies, improvement of gaps in medical education, and formalization of protocols in lower-income countries provide first pragmatic steps to reconciling these variations. Whether a harmonized, uniform standard for brain death worldwide can be achieved remains questionable.
Objective Transplant recipients are at risk of developing progressive multifocal leukoencephalopathy (PML), a rare demyelinating disorder caused by oligodendrocyte destruction by JC virus. Methods Reports of PML following transplantation were found using PubMed Entrez (1958–July 2010). A multicenter, retrospective cohort study also identified all cases of PML among transplant recipients diagnosed at Mayo Clinic, Johns Hopkins University, Washington University, and Amsterdam Academic Medical Center. At 1 institution, the incidence of posttransplantation PML was calculated. Results A total of 69 cases (44 solid organ, 25 bone marrow) of posttransplantation PML were found including 15 from the 4 medical centers and another 54 from the literature. The median time to development of first symptoms of PML following transplantation was longer in solid organ vs bone marrow recipients (27 vs 11 months, p = 0.0005, range of <1 to >240). Median survival following symptom onset was 6.4 months in solid organ vs 19.5 months in bone marrow recipients (p = 0.068). Case fatality was 84% (95% confidence interval [CI], 70.3–92.4%) and survival beyond 1 year was 55.7% (95% CI, 41.2–67.2%). The incidence of PML among heart and/or lung transplant recipients at 1 institution was 1.24 per 1,000 posttransplantation person-years (95% CI, 0.25–3.61). No clear association was found with any 1 immunosuppressant agent. No treatment provided demonstrable therapeutic benefit. Interpretation The risk of PML exists throughout the posttransplantation period. Bone marrow recipients survive longer than solid organ recipients but may have a lower median time to first symptoms of PML. Posttransplantation PML has a higher case fatality and may have a higher incidence than reported in human immunodeficiency virus (HIV) patients on highly-active antiretroviral therapy (HAART) or multiple sclerosis patients treated with natalizumab.
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.