Comparison of prognostic models for burn patients: A retrospective nationwide registry study

A comparative study of the predictive value of four models for death in patients with severe burns

OBJECTIVE

To assess the prognostic value of the Ryan score, Belgian Outcome of Burn Injury (BOBI) score,revised Baux (rBaux) score, and a new model (a Logit(P)-based scoring method created in 2020) for predicting mortality risk in patients with extremely severe burns and to conduct a comparative analysis.

METHODS

A retrospective analysis was conducted on 599 burn patients who met the inclusion criteria and were admitted to the burn unit of the First Affiliated Hospital of Nanchang University from 2017 to 2022. Relevant information was collected, and receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were plotted for each of the four models in assessing mortality in these burn patients using both age-stratified and unstratified forms. The ROC curve section was further compared with the area under the curve (AUC), optimal cutoff value, as well as its sensitivity and specificity. Additionally, the quality of the AUC was assessed using the Delong test.

RESULT

Among the patients who met the inclusion criteria, 532 were in the survival group and 67 in the death group. Irrespective of age stratification, the novel model exhibited superior performance with an AUC of 0.868 (95% CI: 0.838-0.894) among all four models predicting mortality risk in included patients, and also demonstrated better AUC quality than other models; the calibration curves showed that the accuracy of all four models was good; the DCA curves showed that the clinical utility of the novel model and rBuax score were better. In the comparison of four scoring models across different age groups, the new model demonstrated the largest AUC in both 0-19 years (0.954, 95% CI 0.914-0.979) and 20-59 years groups (0.838, 95% CI 0.793-0.877), while rBuax score exhibited the highest AUC in ≥ 60 years group (0.708, 95% CI of 0.602-0.800). The calibration curves showed that the four models exhibited greater accuracy within the age range of 20-59 years, while the DCA curves indicated that both the novel model and rBuax score scale displayed better prediction in both the 20-59 and ≥ 60 years groups.

CONCLUSIONS

All four models demonstrate accurate and effective prognostication for patients with severe burns. Both the novel model and rBaux score exhibit enhanced prediction utility. In terms of the model itself alone, the new model is not simpler than, for example, the rBaux score, and whether it can be applied clinicallyinvolves further study.

The Revised Baux Score as a Predictor of Burn Mortality: A Systematic Review and Meta-Analysis

Mortality following a severe burn is influenced by both patient- and injury-factors, and a number of predictive models have been developed or applied. As there is no consensus on the optimal formula to use, we aimed to investigate the predictive value of the revised Baux score in comparison to other models when determining mortality risk in patients with burn injuries. A systematic review was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. The review yielded 21 relevant studies. The Prediction model Risk Of Bias ASsessment Tool quality appraisal checklist was used with many studies classified as "high" quality. All studies assessed the utility of the revised Baux score in comparison to other scoring systems such as the original Baux, Belgian Outcome in Burn Injury, Abbreviated Burn Severity Index, Acute Physiology and Chronic Health Evaluation II, Sequential Organ Failure Assessment, Boston Group/Ryan scores, the Fatality by Longevity, APACHE II score, Measured Extent of burn, and Sex model, and the Prognostic Burn Index. There was a range of 48 to 15975 participants per study, with a mean age range of 16 to 52 years old. The area under the curve (AUC) values of the rBaux score ranged from 0.682 to 0.99, with a summary AUC of 0.93 for all included studies (CI 0.91-0.95). This summary value demonstrates that the rBaux equation is a reliable predictor for mortality risk in heterogeneous populations. However, this study also identified that the rBaux equation has a diminished ability to predict mortality risk when applied to patients at both extremes of age, highlighting an important area for future research. Overall, the rBaux equation offers a relatively easy means to quickly assess the mortality risk from burn injury in a broad range of patient populations.

[Burn surgery]

Burn injuries represent a special type of injury that requires special expertise. Both in adequate wound treatment and in intensive medical care, there are various special features that must be considered and due to which treatment by experienced medical personnel is necessary. In the clinical, but also in the preclinical course, the most important points in the treatment of the burn injury should be known to be able to guarantee adequate treatment. In this context, in addition to the knowledge of the different degrees of burns, the estimation of the burned body surface area (VKOF) is essential. Intensive medical treatment as well as surgical therapy of deep burn wounds should then be performed in a burn center. The article provides an overview of the classifications of burn injuries, the management of wound care, the various therapeutic options, both conservative and surgical, and the special features of burn disease.

Risk Models to Predict Mortality in Burn Patients: A Systematic Review and Meta-analysis

The predictive capability of various risk assessment models (RAMs) in evaluating the risk of mortality in burn patients is not well established. It is also unclear which RAM provides the highest discriminative ability and presents the highest clinical utility. We pooled all available studies to establish this validity and compare the predictive capability of the various RAMs.

Methods

We reviewed PubMed, MEDLINE, and Embase from their inception up until December 2021 for studies evaluating risk of mortality in burn patients as stratified by RAMs. Data were pooled using random-effect models and presented as area under the receiver operating characteristic (AUROC) curve.

Results

Thirty-four studies, comprising of a total of 98,610 patients, were included in our analysis. Most studies were found to have a low risk of bias and a good measure of applicability. Nine RAMs were evaluated. We discovered that the classic Baux; the revised Baux; and the Fatality by Longevity, APACHE II score, Measured Extent of burn, and Sex (FLAMES) scores presented with the highest discriminative power with there being no significant difference between the results presented by them [AUROCs (95% CI), 0.92 (0.90-0.95), 0.92 (0.90-0.93), 0.94 (0.91-0.97), respectively, with P < 0.00001 for all].

Conclusions

Many RAMs exist with no consensus on the optimal model to utilize and assess risk of mortality for burn patients. This study is the first systematic review and meta-analysis to compare the current RAMs' discriminative ability to predict mortality in patients with burn injuries. This meta-analysis demonstrated that RAMs designed for assessing mortality in individuals with burns have acceptable to great discriminative capacity, with the classic Baux, revised Baux, and FLAMES demonstrating superior discriminative performance in predicting death. FLAMES exhibited the highest discriminative ability among the RAMs studied.

Machine learning links different gene patterns of viral infection to immunosuppression and immune-related biomarkers in severe burns

Introduction

Viral infection, typically disregarded, has a significant role in burns. However, there is still a lack of biomarkers and immunotherapy targets related to viral infections in burns.

Methods

Virus-related genes (VRGs) that were extracted from Gene Oncology (GO) database were included as hallmarks. Through unsupervised consensus clustering, we divided patients into two VRGs molecular patterns (VRGMPs). Weighted gene co-expression network analysis (WGCNA) was performed to study the relationship between burns and VRGs. Random forest (RF), least absolute shrinkage and selection operator (LASSO) regression, and logistic regression were used to select key genes, which were utilized to construct prognostic signatures by multivariate logistic regression. The risk score of the nomogram defined high- and low-risk groups. We compared immune cells, immune checkpoint-related genes, and prognosis between the two groups. Finally, we used network analysis and molecular docking to predict drugs targeting CD69 and SATB1. Expression of CD69 and SATB1 was validated by qPCR and microarray with the blood sample from the burn patient.

Results

We established two VRGMPs, which differed in monocytes, neutrophils, dendritic cells, and T cells. In WGCNA, genes were divided into 14 modules, and the black module was correlated with VRGMPs. A total of 65 genes were selected by WGCNA, STRING, and differential expression analysis. The results of GO enrichment analysis were enriched in Th1 and Th2 cell differentiation, B cell receptor signaling pathway, alpha-beta T cell activation, and alpha-beta T cell differentiation. Then the 2-gene signature was constructed by RF, LASSO, and LOGISTIC regression. The signature was an independent prognostic factor and performed well in ROC, calibration, and decision curves. Further, the expression of immune cells and checkpoint genes differed between high- and low-risk groups. CD69 and SATB1 were differentially expressed in burns.

Discussion

This is the first VRG-based signature (including 2 key genes validated by qPCR) for predicting survival, and it could provide vital guidance to achieve optimized immunotherapy for immunosuppression in burns.

A proof-of-concept study on mortality prediction with machine learning algorithms using burn intensive care data

INTRODUCTION

Burn injuries are a common traumatic injury. Large burns have high mortality requiring intensive care and accurate mortality predictions. To assess if machine learning (ML) could improve predictions, ML algorithms were tested and compared with the original and revised Baux score.

METHODS

Admission data and mortality outcomes were collected from patients at Uppsala University Hospital Burn Centre from 2002 to 2019. Prognostic variables were selected, ML algorithms trained and predictions assessed by analysis of the area under the receiver operating characteristic curve (AUC). Comparison was made with Baux scores using DeLong test.

RESULTS

A total of 17 prognostic variables were selected from 92 patients. AUCs in leave-one-out cross-validation for a decision tree model, an extreme boosting model, a random forest model, a support-vector machine (SVM) model and a generalised linear regression model (GLM) were 0.83 (95% confidence interval [CI] = 0.72-0.94), 0.92 (95% CI = 0.84-1), 0.92 (95% CI = 0.84-1), 0.92 (95% CI = 0.84-1) and 0.84 (95% CI = 0.74-0.94), respectively. AUCs for the Baux score and revised Baux score were 0.85 (95% CI = 0.75-0.95) and 0.84 (95% CI = 0.74-0.94). No significant differences were observed when comparing ML algorithms with Baux score and revised Baux score. Secondary variable selection was made to analyse model performance.

CONCLUSION

This proof-of-concept study showed initial credibility in using ML algorithms to predict mortality in burn patients. The sample size was small and future studies are needed with larger sample sizes, further variable selections and prospective testing of the algorithms.

LAY SUMMARY

Burn injuries are one of the most common traumatic injuries especially in countries with limited prevention and healthcare resources. To treat a patient with large burns who has been admitted to an intensive care unit, it is often necessary to assess the risk of a fatal outcome. Physicians traditionally use simplified scores to calculate risks. One commonly used score, the Baux score, uses age of the patient and the size of the burn to predict the risk of death. Adding the factor of inhalation injury, the score is then called the revised Baux score. However, there are a number of additional causes that can influence the risk of fatal outcomes that Baux scores do not take into account. Machine learning is a method of data modelling where the system learns to predict outcomes based on previous cases and is a branch of artificial intelligence. In this study we evaluated several machine learning methods for outcome prediction in patients admitted for burn injury. We gathered data on 93 patients at admission to the intensive care unit and our experiments show that machine learning methods can reach an accuracy comparable with Baux scores in calculating the risk of fatal outcomes. This study represents a proof of principle and future studies on larger patient series are required to verify our results as well as to evaluate the methods on patients in real-life situations.

Low-soluble TREM-like transcript-1 levels early after severe burn reflect increased coagulation disorders and predict 30-day mortality

BACKGROUND

Patients with severe burns often show systemic coagulation changes in the early stage and even develop extensive coagulopathy. Previous studies have confirmed that soluble TREM-like transcript-1 (sTLT-1) mediates a novel mechanism of haemostasis and thrombosis in inflammatory vascular injury. At present, the role of sTLT-1 in patients with severe burns is not well known.

OBJECTIVE

To investigate the early association between sTLT-1 levels and markers of burn severity, coagulation disorders, endothelial permeability, shock and prognosis in patients with severe burns.

METHODS

A prospective, observational study was conducted with 60 severe burn patients (divided into a death group and a survival group according to 30-day prognosis) admitted to our hospital. Twenty-eight healthy volunteers were recruited as the control group. Blood components at 48 h after burn were analysed for sTLT-1 and biomarkers reflecting platelet activation, shock, endothelial glycocalyx damage, capillary leakage, haemostasis, fibrinolytic activity, natural anticoagulation and blood cells. We compared the three groups, analysed the correlation between sTLT-1 and biomarkers, and investigated the predictive value of sTLT-1 for 30-day prognosis.

RESULT

Compared with the surviving patients, the patients who died had a lower degree of platelet activation [lower sTLT-1, platelet factor 4 (PF-4) and platelet counts] and a higher degree of burn [higher abbreviated burn severity index score (ABSI score)], shock (higher lactate), endothelial glycocalyx damage [higher syndecan-1 and soluble thrombomodulin (sTM)] and capillary leakage [higher resuscitation fluid (0-48 h), lower albumin] as well as decreased haemostasis [higher activated partial prothrombin time (APTT), lower fibrinogen and thrombin-antithrombin III complex (TAT)], increased fibrinolytic activity [higher D-dimer and tissue-type plasminogen activator (tPA)] and decreased natural anticoagulation [lower protein C (PC) and protein S (PS)]. Higher D-dimer (P = 0.013) and lower PF-4 (P = 0.001) were significantly independently associated with lower sTLT-1. Low circulating sTLT-1 (a unit is 50 pg/mL) (odds ratio [OR] 2.08 [95% CI 1.11-3.92], P = 0.022) was an independent predictor of increased 30-day mortality.

CONCLUSION

Low sTLT-1 levels at 48 h after burn in patients with severe burns is associated with increased coagulation disorders. Low circulating sTLT-1 levels were an independent predictor of increased 30-day mortality.