Severe burn injury: Body Mass Index and the Baux score

Implementing AI Models for Prognostic Predictions in High-Risk Burn Patients

BACKGROUND AND OBJECTIVES

Burn injuries range from minor medical issues to severe, life-threatening conditions. The severity and location of the burn dictate its treatment; while minor burns might be treatable at home, severe burns necessitate medical intervention, sometimes in specialized burn centers with extended follow-up care. This study aims to leverage artificial intelligence (AI)/machine learning (ML) to forecast potential adverse effects in burn patients.

METHODS

This retrospective analysis considered burn patients admitted to Chi Mei Medical Center from 2010 to 2019. The study employed 14 features, comprising supplementary information like prior comorbidities and laboratory results, for building models for predicting graft surgery, a prolonged hospital stay, and overall adverse effects. Overall, 70% of the data set trained the AI models, with the remaining 30% reserved for testing. Three ML algorithms of random forest, LightGBM, and logistic regression were employed with evaluation metrics of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).

RESULTS

In this research, out of 224 patients assessed, the random forest model yielded the highest AUC for predictions related to prolonged hospital stays (>14 days) at 81.1%, followed by the XGBoost (79.9%) and LightGBM (79.5%) models. Besides, the random forest model of the need for a skin graft showed the highest AUC (78.8%), while the random forest model and XGBoost model of the occurrence of adverse complications both demonstrated the highest AUC (87.2%) as well. Based on the best models with the highest AUC values, an AI prediction system is designed and integrated into hospital information systems to assist physicians in the decision-making process.

CONCLUSIONS

AI techniques showcased exceptional capabilities for predicting a prolonged hospital stay, the need for a skin graft, and the occurrence of overall adverse complications for burn patients. The insights from our study fuel optimism for the inception of a novel predictive model that can seamlessly meld with hospital information systems, enhancing clinical decisions and bolstering physician-patient dialogues.

Aberrant inflammatory responses in intoxicated burn-injured patients parallel impaired cognitive function

Burn-injured patients with alcohol use disorder (AUD) have increased morbidity and mortality compared to alcohol-abstaining individuals with similar injuries. It is hypothesized that this is due, in part, to alcohol-induced dysregulation of the systemic inflammatory response, leading to worsened clinical outcomes, including increased susceptibility to infection, and heightened cognitive impairment. To examine the effects of alcohol on inflammatory markers after burn injury, we used multiplex assays to measure a panel of 48 cytokines, chemokines, and growth factors in the plasma of burn patents within 24 h of admission to the University of Colorado Burn Center. Thirty patients were enrolled between July 2018 to February 2020 and were stratified based on presence of AUD and total body surface area (TBSA) burn of ≥20% into four groups: [AUD-, TBSA <20%, N = 12], [AUD+, TBSA <20%, N = 3], [AUD-, TBSA ≥20%, N = 8], [AUD+, TBSA ≥20%, N = 7]. In addition, Confusion Assessment Method (CAM) scores were collected to evaluate patient delirium during the course of hospitalization. Multivariate statistical analysis demonstrated a number of cytokines and other factors that were significantly different between the groups. For example, the anti-inflammatory cytokine interleukin 1 receptor antagonist (IL-1ra) was dampened in the AUD+, TBSA ≥20% cohort with a 75.2% decrease compared to AUD-, TBSA ≥20%, and an 83.9% decrease compared to AUD-, TBSA <20% (p = 0.008). Additionally, plasma levels of the pro-inflammatory mediator CXCL12 (C-X-C motif chemokine ligand 12, also known as stromal cell-derived factor 1, SDF-1) was higher in the AUD + groups (p = 0.03) and similarly, IL-18 levels were greater in AUD+, TBSA ≥20% (p = 0.009). Eotaxin (also known as cytokine CC motif ligand 11, CCL11) was markedly elevated in the AUD+, TBSA ≥20% cohort with a 2.4-fold increase over the AUD-, TBSA ≥20%, and a 1.7-fold rise compared to the AUD-, TBSA <20% cohorts (p = 0.04). Interestingly, there was also a marked rise in CAM + delirium scores (85.7%) among the AUD + patients with TBSA ≥20% (p = 0.02). Not surprisingly, we found that hospital stays increased with AUD+ and larger burns (p = 0.0009). Our findings reveal that burn patients who misuse alcohol have aberrant inflammatory responses that may lead to greater immune dysregulation and worse clinical outcomes.

Impact of elevated body mass index on burn injury-associated mortality in a representative US sample

BACKGROUND

The impact of obesity on burn-related mortality is inconsistent and incongruent; despite being a risk factor for numerous comorbidities that would be expected to increase complications and worsen outcomes, there is evidence of a survival advantage for patients with high body mass index-the so-called obesity paradox. We used a national data set to explore further the relationship between body mass index and burn-related mortality.

METHODS

Deidentified data from patients with second and third-degree burns between 2014 and 2018 were obtained from the Cerner Health Facts Database. Univariate and multivariate regression models were created to identify potential factors related to burn-related mortality. A restricted cubic spline model was built to assess the nonlinear association between body mass index and burn-related mortality. All statistical analyses were conducted using R (R Foundation for Statistical Computing).

RESULTS

The study included 9,405 adult burn patients. Univariate and multivariate analyses revealed that age (odds ratio = 2.189 [1.771, 2.706], P < .001), total burn surface area (odds ratio = 1.824 [1.605, 2.074], P < .001), full-thickness burns (odds ratio = 1.992 [1.322, 3.001], P < .001), and comorbidities (odds ratio = 2.03 [1.367, 3.014], P < .001) were associated with increased mortality. Sensitivity analysis showed similar results. However, a restricted cubic spline indicated a U-shaped relation between body mass index and burn-related mortality. The nadir of body mass index was 28.92 kg/m², with the lowest mortality. This association persisted even after controlling for age, total burn surface area, full-thickness burns, and comorbidities, which all remained significant.

CONCLUSION

This study confirms a U-shaped association between body mass index and burn-related mortality along with age, total burn surface area, full-thickness burns, and comorbidities as risk factors.

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.

Differences by age in the obesity paradox in severe burns

BACKGROUND

Many studies show a "obesity paradox", which seems to protect against death. Whether an obesity paradox space is present in severe burn patients remains a matter of great debate. Most research on the obesity paradox of burn injuries is classified by body mass index (BMI) rather than by age.

OBJECTIVE

To investigate whether the obesity paradox exists in severe burn patients stratified by age.

METHODS

Retrospective analysis was performed on 490 patients with severe burns who were ≥ 18 years of age and were admitted to Fujian Medical University Union Hospital from January 2005 to December 2020. Demographic and clinical characteristics were collected, including age, BMI, total body surface area (TBSA), presence of inhalation injury, abbreviated burn severity index (ABSI) score, diabetes comorbidities, hypertension comorbidities, and in-hospital mortality. The patients were divided into the younger group (18 ≤ age<65 years) and the older group (age ≥ 65 years). The important variables of the two groups were compared. The predictive value of BMI stratified by age on in-hospital mortality was evaluated by binary logistic regression analysis and the Cochran's and Mantel-Haenszel statistics.

RESULTS

A total of 490 patients were selected for this study, and were divided into the younger group (413) and the elderly group (77) according to their ages. In the younger group, logistic regression analyses indicated that high BMI remained significantly and independently associated with decreased in-hospital mortality (P = 0.021). That is, in-hospital mortality decreased by 17.8% when BMI increased by 1 kg/m². In the older group, BMI was not associated with in-hospital mortality (P = 0.808). In the younger group, the results of Pearson's chi-square test was less than 0.05, indicating a correlation between BMI and prognosis. In the older group, the conclusion was contrary with, no correlation between BMI and prognosis. If the confounding factors of age were not considered, this results in no correlation between BMI and prognosis. In the younger group, the survival/death ratio of patients with overweight and obesity was 2.078 times that of patients with normal weight.

CONCLUSION

In this study of patients with severe burns, overweight and obesity had protective effect on burn injury in the younger group (18 ≤ age<65 years), but not in the older group (age ≥ 65 years). Investigating the obesity paradox in burn patients needs to consider age differences. However, multicentre clinical trials are needed to verify the results.