Diagnosis Of Burns Research Articles

Application of metagenomic next-generation sequencing technology in pathogen detection in patients with burns and patients with acute or chronic wounds

Objective: To explore the value of using metagenomic next-generation sequencing (mNGS) technology to detect pathogens in patients with burns and patients with acute or chronic wounds. Methods: A retrospective observational study was conducted. From March 2019 to June 2020, 11 patients with burns and patients with acute or chronic wounds (including 10 males and 1 female, aged 23 to 85 years) in the Fourth Medical Center of PLA General Hospital met the inclusion criteria and were recruited. A total of 23 specimens were collected, including 6 whole blood specimens, 1 skin tissue specimen, 1 drained pus specimen, and 15 wound secretion swab specimens. Each specimen was divided into two parts, which were subjected for pathogen detection using microbial culture method and mNGS method, respectively. The number and types of pathogens detected by the 2 methods and the relative abundance detected by the mNGS method were recorded, and the consistency of the two methods were compared. Data were statistically analyzed with paired Wilcoxon rank sum test. Results: With the microbial culture method, no pathogen was detected in 5 of the 23 specimens, while 35 pathogens were detected in the remaining 18 specimens, belonging to 9 species of bacteria and 2 species of fungi. Five specimens had one pathogen while 9 specimens had 2 pathogens and 4 specimens had 3 pathogens detected in each specimen. With the mNGS method, no pathogen was detected in one of the 23 specimens, while 75 pathogens were detected in the remaining 22 specimens, belonging to 28 species of bacteria, 3 species of fungi, and 3 species of viruses. Eight specimens had one pathogen, 5 specimens had 2 pathogens, 2 specimens had 3 pathogens, 3 specimens had 4 pathogens, 2 specimens had 6 pathogens, and 1 specimen had 7 pathogens, and 1 specimen had 20 pathogens detected in each specimen. The number of pathogens detected in each specimen by microbial culture method was 2 (1, 2) types, which was significantly less than 2 (1, 4) types by mNGS method (Z=3.359, P<0.01). In 5 specimens, no bacteria were detected by microbial culture method but mNGS method detected bacteria in 2 specimens and virus in 2 different specimens. The mNGS method detected two or more types of bacteria in 13 specimens, the relative abundance of bacteria with the 1st relative abundance ranking ranged from 28.8% to 95.9% in each specimen. Of the 23 specimens detected by two detection methods, 7 specimens (30.4%) showed identical detection results, 5 specimens (21.7%) showed totally different detection results, and 11 specimens (47.8%) had partially consistent detection results. Conclusions: Compared with the traditional microbial culture method, the mNGS method has higher detection sensitivity and stronger capacity to detect pathogens, and can determine the relative abundance of pathogens in mixed infections. As a supplement to the culture method, the mNGS method is expected to play an important role in the diagnosis of infectious pathogens in burns and acute or chronic wounds.

Expert consensus on the clinical diagnosis and treatment of eye burns in China (2021)

Eye burns, which are usually caused by chemicals such as acidic, alkaline and heat-related substances, are true medical emergencies. These substances can lead to potential permanent damage to the eyelids, cornea, ocular surface and intraocular tissues. In severe cases, eye burns may result in blindness. Currently, there is a lack of uniform and standardized guidelines for the diagnosis and treatment of eye burns. As a result, a considerable number of patients have a poor prognosis. Therefore, the Cornea Group of Chinese Ophthalmological Society has developed this consensus statement after thorough discussions, hoping to provide guiding opinions on the clinical diagnosis and treatment of eye burns. (Chin J Ophthalmol, 2021, 57:254-260).

A Framework for Automatic Burn Image Segmentation and Burn Depth Diagnosis Using Deep Learning.

Burn is a common traumatic disease with high morbidity and mortality. The treatment of burns requires accurate and reliable diagnosis of burn wounds and burn depth, which can save lives in some cases. However, due to the complexity of burn wounds, the early diagnosis of burns lacks accuracy and difference. Therefore, we use deep learning technology to automate and standardize burn diagnosis to reduce human errors and improve burn diagnosis. First, the burn dataset with detailed burn area segmentation and burn depth labelling is created. Then, an end-to-end framework based on deep learning method for advanced burn area segmentation and burn depth diagnosis is proposed. The framework is firstly used to segment the burn area in the burn images. On this basis, the calculation of the percentage of the burn area in the total body surface area (TBSA) can be realized by extending the network output structure and the labels of the burn dataset. Then, the framework is used to segment multiple burn depth areas. Finally, the network achieves the best result with IOU of 0.8467 for the segmentation of burn and no burn area. And for multiple burn depth areas segmentation, the best average IOU is 0.5144.

516 Higher Risk of Acute Kidney Injury in Burn Patients with Rhabdomyolysis

Abstract Introduction Rhabdomyolysis, a rapid breakdown of damaged skeletal muscle, is a serious complication known to occur in approximately 1% of burn patients. Muscle breakdown products can accumulate in the renal tubules leading to acute kidney injury (AKI) and increased deaths. Burn-associated factors such as under-resuscitation, infection, and nephrotoxic drugs likely increase incidence of AKI in those with rhabdomyolysis after burn. Other variables such as age, sex, and pre-existing conditions may also be implicated in this relationship. We investigated whether burn patients with rhabdomyolysis are at greater risk of developing AKI than others with rhabdomyolysis. Methods TriNetX, a global health research network, was accessed in September 2020 to create three patient cohorts with a combination of rhabdomyolysis and burns. Data from years 2000 to 2020 from 38 health care organizations was used. Cohort 1 included burned patients who developed rhabdomyolysis within 14 days after injury. Cohort 2 were those with rhabdomyolysis who did not suffer a burn within 14 days prior to diagnosis. Cohort 3 included burned patients who did not develop rhabdomyolysis within 14 days of the burn. Burn diagnosis was identified by ICD-10 codes T20-25, T26-28, or T30-32; rhabdomyolysis was identified with M62.82. We identified 699 patients in Cohort 1. Propensity score matching was done to Cohorts 2 and 3 to balance similar demographics and pre-existing conditions to Cohort 1. Cohorts were then compared to assess the risk of developing AKI (N17) within 14 days of the initial event. Results Cohort 1 had a mean age at incidence of 48.4±19.8; 552 patients were male and 146 were female. 154 patients with hypertensive diseases, 66 with diabetes mellitus, 41 with chronic kidney disease, and 51 overweight or obese patients were identified. Matched Cohorts 2 and 3 had the same number of patients and similar demographics and pre-existing conditions as Cohort 1. 391 of 699 burn patients with rhabdomyolysis (56%), 293 of 699 non-burn patients with rhabdomyolysis (42%), and 23 of 699 burn patients without rhabdomyolysis (3%) developed AKI within 14 days. The risk ratio difference for developing AKI between burn patients and non-burn patients with rhabdomyolysis was 14.02% with a 95% CI of 8.831–19.209% (&amp;lt; 0.0001 p-value) and between burn patients with and without rhabdomyolysis was 52.647% with a 95% CI of 48.736–56.557% (&amp;lt; 0.0001 p-value). The odds ratios for developing AKI were 1.759 and 37.312, respectively. Conclusions We found the risk of developing AKI in burn patients with rhabdomyolysis to be significantly augmented compared to non-burn patients with rhabdomyolysis or burn patients without rhabdomyolysis.

652 Burns and Incidence of Operative Treatment

Abstract Introduction Over the past three decades, it has been repeatedly demonstrated that early surgical intervention is associated with improved outcomes in burns, however, large-scale studies regarding the incidence of operative treatment in burn patients are lacking. We conducted a retrospective study using the TriNetX database, a global, real-time electronic medical record driven index of patient populations, analyzing the incidence of grafting procedures in burned patients related to age and % total body surface area (TBSA) burned. Methods The population of burn patients and operative treatments were indexed using ICD-10 codes T31.0-T31.9 and 1013913, respectively. Queries were structured as sequential events allowing analysis of burn diagnosis to be followed by a subsequent operation. The patient population was partitioned by TBSA burned, and the number of grafting procedures were assessed. All patients were included and stratified by ages of 0–17, 18–34, 35–64, and 65–89. The data includes information collected between 2000–2020 from over 35 healthcare organizations comprising the Research network in TriNetX. Extracted data were analyzed using chi-square statistical analysis with p&amp;lt; 0.05 considered significant. Results Of 116,325 burn patients identified, 11.14% underwent at least one grafting procedure. Of surgeries performed, the majority occurred in the 35–64 years age group (45.3% p = &amp;lt; 0.001). Additionally, the incidence of grafting procedures was directly proportional to patient age: age groups of 0–17, 18–34, 35–64, and 65–89 years received grafting procedures in 6.5% (p = &amp;lt; 0.001), 9.8% (p = &amp;lt; 0.001), 12.9% (p = &amp;lt; 0.001), and 15.9% (p = &amp;lt; 0.001) of cases, respectively. When stratified by TBSA burned, those with 40–49% TBSA burns had the highest incidence of operations (50.7% p = &amp;lt; 0.001). Large TBSA burns correlated with increasing incidence of grafting procedures until 50–59% TBSA burned, where incidence begins to decrease, likely related to referral patterns which did not capture grafting procedures performed at specialized burn treatment centers or institution of palliative care. Conclusions This study reveals that the incidence of operational treatment increases with both age and percent TBSA burned. The data corroborate a referral pattern for burns that demonstrates a decline in operative treatments beginning with 50–59% TBSA, inconsistent with referral guidelines to specialized burn care centers published by the ABA.

674 Machine Learning and Automation in Burn Care: A Systematic Review

Abstract Introduction Current methods of burn evaluation and treatment are subjective and dependent on surgeon experience, with high rates of inter-rater variability leading to inaccurate diagnoses and treatment. Machine learning (ML) and automated methods are being used to develop more objective and accurate methods for burn diagnosis and triage. Defined as a subfield of artificial intelligence that applies algorithms capable of knowledge acquisition, machine learning draws patterns from data, which it can then apply to clinically relevant tasks. This technology has the potential to improve burn management by quantitating diagnoses, improving diagnostic accuracy, and increasing access to burn care. The aim of this systematic review is to summarize the literature regarding machine learning and automated methods for burn wound evaluation and treatment. Methods A systematic review of articles available on PubMed and MEDLINE (OVID) was performed. Keywords used in the search process included burns, machine learning, deep learning, burn classification technology, and mobile applications. Reviews, case reports, and opinion papers were excluded. Data were extracted on study design, study objectives, study models, devices used to capture data, machine learning, or automated software used, expertise level and number of evaluators, and ML accuracy of burn wound evaluation. Results The search identified 592 unique titles. After screening, 35 relevant articles were identified for systematic review. Nine studies used machine learning and automated software to estimate percent total body surface area (%TBSA) burned, 4 calculated fluid requirements, 18 estimated burn depth, 5 estimated need for surgery, 6 predicted mortality, and 2 evaluated scarring in burn patients. Devices used to estimate %TBSA burned showed an accuracy comparable to or better than traditional methods. Burn depth estimation sensitivities resulted in unweighted means &amp;gt;81%, which increased to &amp;gt;83% with equal weighting applied. Mortality prediction sensitivity had an unweighted mean of 96.75%, which increased to 99.35% with equal weighting. Conclusions Machine learning and automated technology are promising tools that provide objective and accurate measures of evaluating burn wounds. Existing methods address the key steps in burn care management; however, existing data reporting on their robustness remain in the early stages. Further resources should be dedicated to leveraging this technology to improve outcomes in burn care.

Characteristics of Burn-Injured Children in 117 U.S. PICUs (2009-2017): A Retrospective Virtual Pediatric Systems Database Study.

To describe characteristics and outcomes of children with burn injury treated in U.S. PICUs. Retrospective study of admissions in the Virtual Pediatric Systems, LLC, database from 2009 to 2017. One hundred and seventeen PICUs in the United States. Patients less than 18 years old admitted with an active diagnosis of burn at admission. None. A total of 2,056 patients were included. They were predominantly male (62.6%) and less than 6 years old (66.7%). Cutaneous burns were recorded in 92.1% of patients, mouth/pharynx burns in 5.8%, inhalation injury in 5.1%, and larynx/trachea/lung burns in 4.5%. Among those with an etiology recorded (n = 861), scald was most common (38.6%), particularly in children less than 2 years old (67.8%). Fire/flame burns were most common (46.6%) in children greater than or equal to 2 years. Multiple organ failure was present in 26.2% of patients. Most patients (89%) were at facilities without American Burn Association pediatric verification. PICU mortality occurred in 4.5% of patients. On multivariable analysis using Pediatric Index of Mortality 2, greater than or equal to 30% total body surface area burned was significantly associated with mortality (odds ratio, 5.40; 95% CI, 2.16-13.51; p = 0.0003). When Pediatric Risk of Mortality III was used, greater than or equal to 30% total body surface area burned (odds ratio, 5.45; 95% CI, 1.95-15.26; p = 0.001) and inhalation injury (odds ratio, 5.39; 95% CI, 1.58-18.42; p = 0.007) were significantly associated with mortality. Among 366 survivors (18.6%) with Pediatric Cerebral Performance Category or Pediatric Overall Performance Category data, 190 (51.9%) had a greater than or equal to 1 point increase in Pediatric Cerebral Performance Category or Pediatric Overall Performance Category disability category and 80 (21.9%) had a new designation of moderate or severe disability, or persistent vegetative state. Burn-injured patients in U.S. PICUs have a substantial burden of organ failure, morbidity, and mortality. Coordination among specialized facilities may be particularly important in this population, especially for those with higher % total body surface area burned or inhalation injury.

Diagnosis and management of gastrointestinal chemical burns and post-burn oesophageal stenosis.

Post-burn oesophageal stenosis occurs as a result of accidental or intentional ingestion of a corrosive substance. Global estimates indicate tens of thousands of acid or lye ingestion cases per year. In some cases patients in the early post-burn phase require urgent surgical intervention. Endoscopy, along with chest and abdominal computed tomography, form the basis of diagnosis. The need for emergency oesophageal or gastric resection is associated with a high mortality rate of up to 60%. Post-burn oesophageal stenosis is a challenging clinical problem that requires coordinated multispecialty treatment. The treatment of post-burn stenosis may be with endoscopic techniques or reconstructive surgery. Surgical reconstruction is performed once the scar has definitively formed. The extent of the injury, anatomical conditions, previous surgery and the team’s expertise determine the optimum reconstructive method. In this article, we present the current knowledge on the diagnosis and treatment of oesophageal burns.

Role of fibreoptic bronchoscopy in early diagnosis of inhalational burns in patients with facial burns

Introduction: Inhalation burn is a major cause of mortality in burn patients. Early diagnosis of smoke inhalation injury (SII) is imperative in the management and prevention of burn injury. The gold standard modality for the diagnosis of SII is fiber-optic bronchoscopy (FOB). Materials and Methods: This prospective, observational study included thirty patients and was conducted from November 2016 to May 2018. Patients with thermal burns sustained &lt; 72 h with facial burns, age group 18–60 years, were included in the study. Results: FOB was done in thirty patients. About 26.67% of patients had closed space injuries. Singeing of scalp hair/eyebrows was present in 46.67% of patients. Singeing of nasal vibrissae/mustache was present in 56.67% of patients. Eversion of eyelids and lips was present in 33.33% and 50% of patients, respectively. Hoarseness of voice, edema of tongue, and tachycardia were present in 16.67%, 50%, and 66.67% of cases, respectively. On auscultation, 26.67% patients had basal crepts. In the chest X-ray, 16.67% of patients had pulmonary edema. Forty percent of patients had arterial hypoxemia and acidosis at the time of arrival. About 56.67% of patients were proved bronchoscopically to have features of SII. Conclusions: FOB has significant value in evaluation, prediction of prognosis, and management of SII when performed within 72 h of burns.

Aspirin induced intraoral burn: A rare case report with emphasis on its diagnosis

Introduction: We present a case of chemical burn due to use of aspirin for pain control as self-medication. A patient placed Aspirin tablet in the right posterior lingual vestibule. A diagnosis of chemical burn was made based on history and clinical examination. Patient was advised to discontinue the habit and self- medication and was treated symptomatically. Keywords: Chemical burn, Aspirin, Recreational drugs.

Child Abuse Recognition Training for Prehospital Providers Using Deliberate Practice

Background In most states, prehospital professionals (PHPs) are mandated reporters of suspected abuse but cite a lack of training as a challenge to recognizing and reporting physical abuse. We developed a learning platform for the visual diagnosis of pediatric abusive versus non-abusive burn and bruise injuries and examined the amount and rate of skill acquisition. Methods This was a prospective cross-sectional study of PHPs participating in an online educational intervention containing 114 case vignettes. PHPs indicated whether they believed a case was concerning for abuse and would report a case to child protection services. Participants received feedback after submitting a response, permitting deliberate practice of the cases. We describe learning curves, overall accuracy, sensitivity (diagnosis of abusive injuries) and specificity (diagnosis of non-abusive injuries) to determine the amount of learning. We performed multivariable regression analysis to identify specific demographic and case variables associated with a correct case interpretation. After completing the educational intervention, PHPs completed a self-efficacy survey on perceived gains in their ability to recognize cutaneous signs of abuse and report to social services. Results We enrolled 253 PHPs who completed all the cases; 158 (63.6%) emergency medical technicians (EMT), 95 (36.4%) advanced EMT and paramedics. Learning curves demonstrated that, with one exception, there was an increase in learning for participants throughout the educational intervention. Mean diagnostic accuracy increased by 4.9% (95% CI 3.2, 6.7), and the mean final diagnostic accuracy, sensitivity, and specificity were 82.1%, 75.4%, and 85.2%, respectively. There was an increased odds of getting a case correct for bruise versus burn cases (OR = 1.4; 95% CI 1.3, 1.5); if the PHP was an Advanced EMT/Paramedic (OR = 1.3; 95% CI 1.1, 1.4) ; and, if the learner indicated prior training in child abuse (OR = 1.2; 95% CI 1.0, 1.3). Learners indicated increased comfort in knowing which cases should be reported and interpreting exams in children with cutaneous injuries with a median Likert score of 5 out of 6 (IQR 5, 6). Conclusion An online module utilizing deliberate practice led to measurable skill improvement among PHPs for differentiating abusive from non-abusive burn and bruise injuries.

Possibilities of Endoscopic Diagnosis of Airway Burn in Inhalation Trauma

ABSTRACT. The diagnostic standard for airway burn in inhalation trauma is bronchoscopy. Determining the severity of a burn of the respiratory tract within first 24 hours is difficult due to the multiple foci of fixed soot, therefore, this procedure is possible only after its removal. Optimization of the standard method of sanitation bronchoscopy in case of airway burn by removing soot with endoscopic forceps and brushes significantly increase the efficacy of primary endoscopic diagnosis, which amounts to 74.9%. The most common mistakes in diagnosing the severity of mucosal damage are associated with a burn of the 1st degree.

Convolution neural network for effective burn region segmentation of color images

BackgroundBurn injuries are one of the most severe forms of wounds and trauma across the globe. Automated burn diagnosis methods are needed to provide timely treatment to the concerned patients. Artificial intelligence is playing a vital role in developing automated tools and techniques for medical problems. However, the use of advanced AI techniques for color images based burn region segmentation is not much explored. MethodIn this work, we explore the use of deep learning for the challenging problem of burn region segmentation. We prepared a pixel-wise labelled new burn images dataset for segmentation and investigated the efficacy of existing state-of-the-art color images based semantic image segmentation techniques. Lately, we proposed a new convolution neural network (CNN) that uses atrous convolution for encoding rich contextual information and utilizes pre-trained model ResNet-101 for better extraction of low-level and middle-level layer features. ResultsThe proposed approach achieves the state-of-the-art performance on the prepared burn image dataset with 77.6% of Mathews correlation coefficient (MCC) and 93.4% of accuracy. The improvement of 11.6/5.8/6.9/1.2% is observed in precision, Dice similarity coefficient, Jaccard index and specificity, in comparison to the second best performance. ConclusionIn this work, we propose a CNN based novel method for performing burn-region segmentation in color images and evaluate it using newly prepared Burn Images dataset. The experimental results illustrate its effectiveness in comparison to existing approaches. Further, the proposed pixel-level segmentation method could be useful in estimating the burn surface area and burn severity in an accurate and time efficient manner.

Mardin İli Geleneksel Halk Hekimliğinde Yanık Uygulamaları

Çevresel etkenlerin, gelenek, görenek ve tecrübeyle birleştirilmesiyle beraber yüzyıllar içerisinde halk hekimliği ortaya çıkmıştır. Mardin'de, modern tıbbın gelişimine paralel olarak halk hekimliği yöntem ve uygulamaları da değişerek ve gelişerek varlığını sürdürmektedir. Bu çalışmada, Mardin geleneksel halk hekimliğinde önemli bir yeri olan yanık tedavisi uygulamaları, örnek bir yanık vakası üzerinden ele alınmıştır. Bu çalışmaya konu olan vaka, ilk günden itibaren izlemeye alınmış, yapılan uygulamalar düzenli aralıklarla görüntülenmiş ve kayıt altına alınmıştır. Kızgın yağın dökülmesi suretiyle hastanın sol eli yanmıştır. Mardin Devlet Hastanesi acil servisinde yapılan ilk muayenede 2. derece yanık teşhisi konulmuş, ilk müdahale yapılmış ve hasta taburcu edilmiştir. İlerleyen saatlerde ağrı dayanılmaz bir hale gelince halk hekimliği yöntemlerine başvurulma ihtiyacı duyulmuştur. Daha sonra hasta, Mardin ili Kızıltepe ilçesinde yaşayan halk hekimi Ş.B.'ye başvurmuştur. Halk hekiminin eczaneden getirttiği iki ilaç, bal mumu, mum, zeytinyağı ve köy yumurtasından oluşan malzemelerle hazırladığı karışım belirli aralıklarla yaraya uygulanmıştır. Yaklaşık iki buçuk aylık bir tedavi sürecinin ardından yaranın hemen hemen iz bırakmayacak şekilde iyileştiği gözlemlenmiştir. Bu uygulamanın en önemli özelliği tedavide geleneksel halk hekimliği ile modern tıbbın olanaklarının birleştirilmesidir. Bu vakada yapılan uygulama, hastalıkların tedavisinde halk hekimliği ve modern tıbbın olanaklarının bir arada kullanılmasının önemini ortaya koymaktadır.

Risk factors for nonaccidental burns in children

BackgroundThe relative influences of baseline risk factors for pediatric nonaccidental burns have not been well described. We evaluated baseline characteristics of pediatric nonaccidental burn patients and their primary caretakers. MethodsA single-center retrospective cohort study was conducted of pediatric (age < 17) burn patients from July 1, 2013, to June 30, 2018. The primary outcome was nonaccidental burn, defined as burn secondary to abuse or neglect as determined by the inpatient child protection team or Child Protective Services. Univariate and multivariate analyses were performed. ResultsOf 489 burn patients, 47 (9.6%) suffered nonaccidental burns. Nonaccidental burn patients more frequently had a history of Child Protective Services involvement (48.9% vs 9.7%, P < .001), as did their primary caretakers (59.6% vs 10.9%, P < .001). Non-Hispanic black children had higher rates of Child Protective Services referral (50.7% vs 26.7%, P < .001) and nonaccidental burn diagnosis (18.9% vs 5.6%, P < .001) than children of other races/ethnicities. On multivariate analysis, caretaker involvement with CPS (odds ratio 7.53, 95% confidence interval 3.38–16.77) and non-Hispanic black race/ethnicity (odds ratio 3.28, 95% confidence interval 1.29–8.36) were associated with nonaccidental burn. ConclusionCaretaker history of Child Protective Services involvement and non-Hispanic black race/ethnicity were associated with increased odds of pediatric nonaccidental burn. Prospective research is necessary to determine whether these represent true risk factors for nonaccidental burn or are the result of other confounders, such as socioeconomic status.

Diagnostic accuracy of a telemedicine tool for acute burns diagnosis

BackgroundTelemedicine technologies have a valuable potential when it comes to improving the accuracy of triage protocols in selecting severely injured patients who may benefit from transportation. The main objective of this study was to evaluate the correlation of the urgent diagnosis made by telemedicine through an App with traditional face-to-face urgent care and the final diagnosis, made by scheduled consultation. MethodsWe carried out a descriptive cross-sectional study to evaluate the accuracy of telemedicine in burns evaluation compared to gold standard (in-person consultation). An App was designed. All patients enrolled were evaluated by both teleconsultation and face-to-face approach on burn emergencies. Diagnosis on presentation made by a physician constituted the gold standard. ResultsA total of 202 patients were included in the study. The use of TM was able to detect that 83.17% of the patients attending the BU could have been managed on as outpatient basis. The intra-observer concordance was k=0.94 (95% CI: 0.90–0.97). These results highlight a very high sensitivity and specificity (99.40 and 100% respectively). ConclusionsThe telemedicine system for planning referrals is a useful tool that may make significant differences in the management of burned patients although further research needs to be taken in that direction.

BPBSAM: Body part-specific burn severity assessment model.

Burns are a serious health problem leading to several thousand deaths annually, and despite the growth of science and technology, automated burns diagnosis still remains a major challenge. Researchers have been exploring visual images-based automated approaches for burn diagnosis. Noting that the impact of a burn on a particular body part can be related to the skin thickness factor, we propose a deep convolutional neural network based body part-specific burns severity assessment model (BPBSAM). Considering skin anatomy, BPBSAM estimates burn severity using body part-specific support vector machines trained with CNN features extracted from burnt body part images. Thus BPBSAM first identifies the body part of the burn images using a convolutional neural network in training of which the challenge of limited availability of burnt body part images is successfully addressed by using available larger-size datasets of non-burn images of different body parts considered (face, hand, back, and inner forearm). We prepared a rich labelled burn images datasets: BI & UBI and trained several deep learning models with existing models as pipeline for body part classification and feature extraction for severity estimation. The proposed novel BPBSAM method classified the severity of burn from color images of burn injury with an overall average F1 score of 77.8% and accuracy of 84.85% for the test BI dataset and 87.2% and 91.53% for the UBI dataset, respectively. For burn images body part classification, the average accuracy of around 93% is achieved, and for burn severity assessment, the proposed BPBSAM outperformed the generic method in terms of overall average accuracy by 10.61%, 4.55%, and 3.03% with pipelines ResNet50, VGG16, and VGG19, respectively. The main contributions of this work along with burn images labelled datasets creation is that the proposed customized body part-specific burn severity assessment model can significantly improve the performance in spite of having small burn images dataset. This highly innovative customized body part-specific approach could also be used to deal with the burn region segmentation problem. Moreover, fine tuning on pre-trained non-burn body part images network has proven to be robust and reliable.

Extracorporeal Membrane Oxygenation Support for Pediatric Burn Patients: Is It Worth the Risk?

Examine the outcomes of pediatric burn patients requiring extracorporeal membrane oxygenation to determine whether extracorporeal membrane oxygenation should be considered in this special population. Retrospective cohort study. All extracorporeal membrane oxygenation centers reporting to the Extracorporeal Life Support Organization. Pediatric patients (birth to younger than 18 yr) who were supported with extracorporeal membrane oxygenation with a burn diagnosis between 1990 and 2016. None. A total of 113 patients were identified from the registry by inclusion criteria. Patients cannulated for respiratory failure had the highest survival (55.7%, n = 97) compared to those supported for cardiac failure (33.3%, n = 6) or extracorporeal cardiopulmonary resuscitation (30%, n = 10). Patients supported on venovenous extracorporeal membrane oxygenation for respiratory failure had the best overall survival at 62.2% (n = 37). Important for the burn population, rates of surgical site bleeding were similar to other surgical patients placed on extracorporeal membrane oxygenation at 22.1%. Cardiac arrest prior to cannulation was associated with increased hospital mortality (odds ratio, 3.41; 95% CI, 0.16-1.01; p = 0.048). Following cannulation, complications including the need for inotropes (odds ratio, 2.64; 95% CI, 1.24-5.65; p = 0.011), presence of gastrointestinal hemorrhage (p = 0.049), and hyperglycemia (glucose > 240 mg/dL) (odds ratio, 3.42; 95% CI, 1.13-10.38; p = 0.024) were associated with increased mortality. Of patients with documented burn percentage of total body surface area (n = 19), survival was 70% when less than 60% total body surface area was involved. Extracorporeal membrane oxygenation could be considered as an additional level of support for the pediatric burn population, especially in the setting of respiratory failure. Additional studies are necessary to determine the optimal timing of cannulation and other patient characteristics that may impact outcomes.

M-Health for Burn Injury Consultations in a Low-Resource Setting: An Acceptability Study Among Health Care Providers.

Introduction: The rapid adoption of smartphones, especially in low- and middle-income countries, has opened up novel ways to deliver health care, including diagnosis and management of burns. This study was conducted to measure acceptability and to identify factors that influence health care provider's attitudes toward m-health technology for emergency care of burn patients.Methods: An extended version of the technology acceptance model (TAM) was used to assess the acceptability toward using m-health for burns. A questionnaire was distributed to health professionals at four hospitals in Dar Es Salaam, Tanzania. The questionnaire was based on several validated instruments and has previously been adopted for the sub-Saharan context. It measured constructs, including acceptability, usefulness, ease of use, social influences, and voluntariness. Univariate analysis was used to test our proposed hypotheses, and structural equation modeling was used to test the extended version of TAM.Results: In our proposed test-model based on TAM, we found a significant relationship between compatibility—usefulness and usefulness—attitudes. The univariate analysis further revealed some differences between subgroups. Almost all health professionals in our sample already use smartphones for work purposes and were positive about using smartphones for burn consultations. Despite participants perceiving the application to be easy to use, they suggested that training and ongoing support should be available. Barriers mentioned include access to wireless internet and access to hospital-provided smartphones.

Advances in the research of artificial intelligence technology assisting the diagnosis of burn depth

The early accurate diagnosis of burn depth is of great significance in determining the corresponding clinical intervention methods and judging the prognosis quality of burn patients. However, the current diagnostic method of burn depth still relies mainly on the empirical subjective judgment of clinicians, with low diagnostic accuracy. Especially for deep partial-thickness burn wounds, the error of early diagnosis is pretty big. In recent years, with the rapid development of artificial intelligence technology, deep learning algorithm combined with image analysis technology can better identify and analyze the information of medical images. This article reviews the research progress of artificial intelligence technology in the diagnosis of burn depth.