Dataset Information

Rapid Evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality.

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.

SUBMITTER: Plecko D

PROVIDER: S-EPMC8652966 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Rapid Evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality.

Plečko Drago D Bennett Nicolas N Mårtensson Johan J Dam Tariq A TA Entjes Robert R Rettig Thijs C D TCD Dongelmans Dave A DA Boelens Age D AD Rigter Sander S Hendriks Stefaan H A SHA de Jong Remko R Kamps Marlijn J A MJA Peters Marco M Karakus Attila A Gommers Diederik D Ramnarain Dharmanand D Wils Evert-Jan EJ Achterberg Sefanja S Nowitzky Ralph R van den Tempel Walter W de Jager Cornelis P C CPC Nooteboom Fleur G C A FGCA Oostdijk Evelien E Koetsier Peter P Cornet Alexander D AD Reidinga Auke C AC de Ruijter Wouter W Bosman Rob J RJ Frenzel Tim T Urlings-Strop Louise C LC de Jong Paul P Smit Ellen G M EGM Cremer Olaf L OL Mehagnoul-Schipper D Jannet DJ Faber Harald J HJ Lens Judith J Brunnekreef Gert B GB Festen-Spanjer Barbara B Dormans Tom T de Bruin Daan P DP Lalisang Robbert C A RCA Vonk Sebastiaan J J SJJ Haan Martin E ME Fleuren Lucas M LM Thoral Patrick J PJ Elbers Paul W G PWG Bellomo Rinaldo R

Acta anaesthesiologica Scandinavica 20211015 1

<h4>Background</h4>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.<h4>Methods</h4>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 ...[more]

PMID: 34622441

Similar Datasets

Project description:ObjectivesTo explain and demonstrate a new approach for rapidly developing a decision-support tool for prioritizing patients with coronovirus 2019 disease for admission to ICUs.DesignAn expert group used multi-criteria decision analysis methods to specify criteria and weights, representing their relative importance, for prioritizing patients with coronovirus 2019 disease with respect to likely clinical benefit. Specialized multi-criteria decision analysis software, implementing the "Potentially All Pairwise RanKings of all possible Alternatives" method to determine the weights, was used. Social equity considerations for prioritizing patients were also identified as important.SettingThe prioritization tool was developed in New Zealand.SubjectsAn expert group comprising specialists from intensive care medicine and nursing, Māori (New Zealand's indigenous population) health, infectious diseases, and neonatology was formed. The group's work was supported by health economists and decision analysts and overseen by an ethicist and a senior representative from the New Zealand Ministry of Health.InterventionsMulti-criteria decision analysis to create a prioritization tool.Measurements and main resultsThe prioritization tool comprised eight criteria with respect to likely clinical benefit. In decreasing order of importance (weights in parentheses): Sequential Organ Failure Assessment score (15.7%), preexisting cardiovascular conditions (15.7%), functional capacity (15.7%), age (12.4%), preexisting respiratory conditions (11.1%), immunocompromised (11.1%), body mass index (9.2%), and other relevant medical conditions (9.2%). Two social equity considerations were also included in the overarching decision framework to be used alongside the clinical criteria: prioritizing Māori and Pacific people (and, potentially, other at-risk groups), and healthcare and other frontline workers.ConclusionsThe criteria and weights in the prioritization tool can be easily revised as new evidence emerges. The approach for developing the tool could be used in other countries whose ICUs are at risk of being overwhelmed by the coronavirus disease 2019 pandemic to rapidly develop their own prioritization tools. In the event that future crises threaten to overload ICUs, other prioritization tools could also be rapidly developed.

Project description:BACKGROUND:Majority burn mortality prognostic scores were developed and validated in western populations. The primary objective of this study was to evaluate and identify possible risk factors which may be used to predict burns mortality in a local Malaysian burns intensive care unit. The secondary objective was to validate the five well known burn prognostic scores (Baux score, Abbreviated Burn Severity Index (ABSI) score, Ryan score, Belgium Outcome Burn Injury (BOBI) score and revised Baux score) to predict burn mortality prediction. METHODS:Patients that were treated at the Hospital Sultan Ismail's Burns Intensive Care (BICU) unit for acute burn injuries between 1 January 2010 to 31 December 2017 were included. Risk factors to predict in-patient burn mortality were gender, age, mechanism of injury, total body surface area burn (TBSA), inhalational injury, mechanical ventilation, presence of tracheotomy, time from of burn injury to BICU admission and initial centre of first emergency treatment was administered. These variables were analysed using univariate and multivariate analysis for the outcomes of death. All patients were scored retrospectively using the five-burn mortality prognostic scores. Predictive ability for burn mortality was analysed using the area under receiver operating curve (AUROC). RESULTS:A total of 525 patients (372 males and 153 females) with mean age of 34.5 ± 14.6 years were included. There were 463 survivors and 62 deaths (11.8% mortality rate). The outcome of the primary objective showed that amongst the burn mortality risk factors that remained after multivariate analysis were older age (p = 0.004), wider TBSA burn (p < 0.001) and presence of mechanical ventilation (p < 0.001). Outcome of secondary objective showed good AUROC value for the prediction of burn death for all five burn prediction scores (Baux score; AUROC:0.9, ABSI score; AUROC:0.92, Ryan score; AUROC:0.87, BOBI score; AUROC:0.91 and revised Baux score; AUROC:0.94). The revised Baux score had the best AUROC value of 0.94 to predict burns mortality. CONCLUSION:Current study evaluated and identified older age, total body surface area burns, and mechanical ventilation as significant predictors of burn mortality. In addition, the revised Baux score was the most accurate burn mortality risk score to predict mortality in a Malaysian burn's population.

Project description:ObjectiveRisk stratification of patients with congestive heart failure (HF) is vital in clinical practice. The aim of this study was to construct a machine learning model to predict the in-hospital all-cause mortality for intensive care unit (ICU) patients with HF.MethodseXtreme Gradient Boosting algorithm (XGBoost) was used to construct a new prediction model (XGBoost model) from the Medical Information Mart for Intensive Care IV database (MIMIC-IV) (training set). The eICU Collaborative Research Database dataset (eICU-CRD) was used for the external validation (test set). The XGBoost model performance was compared with a logistic regression model and an existing model (Get with the guideline-Heart Failure model) for mortality in the test set. Area under the receiver operating characteristic cure and Brier score were employed to evaluate the discrimination and the calibration of the three models. The SHapley Additive exPlanations (SHAP) value was applied to explain XGBoost model and calculate the importance of its features.ResultsThe total of 11,156 and 9,837 patients with congestive HF from the training set and test set, respectively, were included in the study. In-hospital all-cause mortality occurred in 13.3% (1,484/11,156) and 13.4% (1,319/9,837) of patients, respectively. In the training set, of 17 features with the highest predictive value were selected into the models with LASSO regression. Acute Physiology Score III (APS III), age and Sequential Organ Failure Assessment (SOFA) were strongest predictors in SHAP. In the external validation, the XGBoost model performance was superior to that of conventional risk predictive methods, with an area under the curve of 0.771 (95% confidence interval, 0.757-0.784) and a Brier score of 0.100. In the evaluation of clinical effectiveness, the machine learning model brought a positive net benefit in the threshold probability of 0%-90%, prompting evident competitiveness compare to the other two models. This model has been translated into an online calculator which is accessible freely to the public (https://nkuwangkai-app-for-mortality-prediction-app-a8mhkf.streamlit.app).ConclusionThis study developed a valuable machine learning risk stratification tool to accurately assess and stratify the risk of in-hospital all-cause mortality in ICU patients with congestive HF. This model was translated into a web-based calculator which access freely.

Project description:Study objectiveThe goal of this study is to create a predictive, interpretable model of early hospital respiratory failure among emergency department (ED) patients admitted with coronavirus disease 2019 (COVID-19).MethodsThis was an observational, retrospective, cohort study from a 9-ED health system of admitted adult patients with severe acute respiratory syndrome coronavirus 2 (COVID-19) and an oxygen requirement less than or equal to 6 L/min. We sought to predict respiratory failure within 24 hours of admission as defined by oxygen requirement of greater than 10 L/min by low-flow device, high-flow device, noninvasive or invasive ventilation, or death. Predictive models were compared with the Elixhauser Comorbidity Index, quick Sequential [Sepsis-related] Organ Failure Assessment, and the CURB-65 pneumonia severity score.ResultsDuring the study period, from March 1 to April 27, 2020, 1,792 patients were admitted with COVID-19, 620 (35%) of whom had respiratory failure in the ED. Of the remaining 1,172 admitted patients, 144 (12.3%) met the composite endpoint within the first 24 hours of hospitalization. On the independent test cohort, both a novel bedside scoring system, the quick COVID-19 Severity Index (area under receiver operating characteristic curve mean 0.81 [95% confidence interval {CI} 0.73 to 0.89]), and a machine-learning model, the COVID-19 Severity Index (mean 0.76 [95% CI 0.65 to 0.86]), outperformed the Elixhauser mortality index (mean 0.61 [95% CI 0.51 to 0.70]), CURB-65 (0.50 [95% CI 0.40 to 0.60]), and quick Sequential [Sepsis-related] Organ Failure Assessment (0.59 [95% CI 0.50 to 0.68]). A low quick COVID-19 Severity Index score was associated with a less than 5% risk of respiratory decompensation in the validation cohort.ConclusionA significant proportion of admitted COVID-19 patients progress to respiratory failure within 24 hours of admission. These events are accurately predicted with bedside respiratory examination findings within a simple scoring system.

Dataset Information

Rapid Evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality.

Background

Methods

Results

Conclusions

Publications

Rapid Evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets