Dataset Information

The analysis and accuracy of mortality prediction scores in burn patients admitted to the intensive care burn unit (ICBU).

ABSTRACT:

Background

To date, multiple scoring systems have been utilised in predicting outcomes in burn patients. The aim of this study is to determine the accuracy of three established scoring systems used for burn patients admitted to the intensive care unit and to determine the risk factors associated with poor outcomes.

Methods

A total of 211 patients who were admitted to the ICBU in a tertiary care centre in Kuwait from January 2017 to December 2019 were analysed retrospectively. Data were collected using patient medical records. The FLAMES, BOBI and revised Baux scores were calculated, and the survivor and non-survivor scores of patients were analysed to determine the sensitivity, specificity and Area Under the Receiver Operating Characteristics (AUROC) of the different scoring modalities.

Results

The majority of the analysed population were male patients (165/211) and the most common mechanism of burns was flame burns (166/211). Most of the patients admitted to the ICBU survived (188/211). Female gender was associated with a higher mortality rate, whilst inhalational injury and co-morbidities were not associated with a higher mortality rate. The revised Baux score had a sensitivity value of 96% and 90% specificity. The BOBI score had a sensitivity of 91% and 76% specificity. The FLAMES score had a sensitivity of 96% and the highest specificity of 99%. All 3 scores had AUC values exceeding 90%.

Conclusion

Statistically, FLAMES score had the highest accuracy of predicting outcomes in burn patients, however all three scores demonstrated acceptable predictive rates when it comes to practical application, permitting the use of either one of the studied scores with satisfactory prognostic outcomes.

SUBMITTER: Hassan Z

PROVIDER: S-EPMC8065182 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

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:BackgroundsThe in-hospital mortality in lung cancer patients admitted to intensive care unit (ICU) is extremely high. This study intended to adopt machine learning algorithm models to predict in-hospital mortality of critically ill lung cancer for providing relative information in clinical decision-making.MethodsData were extracted from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) for a training cohort and data extracted from the Medical Information Mart for eICU Collaborative Research Database (eICU-CRD) database for a validation cohort. Logistic regression, random forest, decision tree, light gradient boosting machine (LightGBM), eXtreme gradient boosting (XGBoost), and an ensemble (random forest+LightGBM+XGBoost) model were used for prediction of in-hospital mortality and important feature extraction. The AUC (area under receiver operating curve), accuracy, F1 score and recall were used to evaluate the predictive performance of each model. Shapley Additive exPlanations (SHAP) values were calculated to evaluate feature importance of each feature.ResultsOverall, there were 653 (24.8%) in-hospital mortality in the training cohort, and 523 (21.7%) in-hospital mortality in the validation cohort. Among the six machine learning models, the ensemble model achieved the best performance. The top 5 most influential features were the sequential organ failure assessment (SOFA) score, albumin, the oxford acute severity of illness score (OASIS) score, anion gap and bilirubin in random forest and XGBoost model. The SHAP summary plot was used to illustrate the positive or negative effects of the top 15 features attributed to the XGBoost model.ConclusionThe ensemble model performed best and might be applied to forecast in-hospital mortality of critically ill lung cancer patients, and the SOFA score was the most important feature in all models. These results might offer valuable and significant reference for ICU clinicians' decision-making in advance.

Project description:BACKGROUND:Acute kidney injury (AKI) is a common complication in burn patients admitted to the intensive care unit (ICU) associated with increased morbidity and mortality. Our primary aim was to review incidence, risk factors, and outcomes of AKI in burn patients admitted to the ICU. Secondary aims were to review the use of renal replacement therapy (RRT) and impact on health care costs. METHODS:We conducted a systematic search in PubMed, UpToDate, and NICE through 3 December 2018. All reviews in Cochrane Database of Systematic Reviews except protocols were added to the PubMed search. We searched for studies on AKI according to Risk, Injury, Failure, Loss of kidney function, and End-stage kidney disease (RIFLE); Acute Kidney Injury Network (AKIN); and/or Kidney Disease: Improving Global Outcomes (KDIGO) criteria in burn patients admitted to the ICU. We collected data on AKI incidence, risk factors, use of RRT, renal recovery, length of stay (LOS), mortality, and health care costs. RESULTS:We included 33 observational studies comprising 8200 patients. Overall study quality, scored according to the Newcastle-Ottawa scale, was moderate. Random effect model meta-analysis revealed that the incidence of AKI among burn patients in the ICU was 38 (30-46) %. Patients with AKI were almost evenly distributed in the mild, moderate, and severe AKI subgroups. RRT was used in 12 (8-16) % of all patients. Risk factors for AKI were high age, chronic hypertension, diabetes mellitus, high Total Body Surface Area percent burnt, high Abbreviated Burn Severity Index score, inhalation injury, rhabdomyolysis, surgery, high Acute Physiology and Chronic Health Evaluation II score, high Sequential Organ Failure Assessment score, sepsis, and mechanical ventilation. AKI patients had 8.6 (4.0-13.2) days longer ICU LOS and higher mortality than non-AKI patients, OR 11.3 (7.3-17.4). Few studies reported renal recovery, and no study reported health care costs. CONCLUSIONS:AKI occurred in 38% of burn patients admitted to the ICU, and 12% of all patients received RRT. Presence of AKI was associated with increased LOS and mortality. TRIAL REGISTRATION:PROSPERO (CRD42017060420).