Alexander Morzycki

Burn injuries, resulting from thermal, chemical, and electrical mechanisms, require prompt and accurate assessment for effective treatment. The primary method, relying on visual and tactile evaluations, offers 50%–80% accuracy, while noninvasive methods such as laser Doppler imaging (LDI) reach up to 97% accuracy. This article presents a machine learning (ML) pipeline for assessing burn severity and segmenting affected skin regions. We trained a convolutional neural network (CNN) to classify four burn severities: superficial (SPF), superficial partial thickness (SPT), deep partial thickness (DPT), and full thickness (FT). In addition, we introduced boundary attention mapping (BAM), a saliency mapping method that leverages the trained CNN to accurately segment burn regions. Our pipeline was validated using two datasets: a Burn Injury Image dataset with 1385 images and an LDI dataset with 184 images. The CNN achieved 80% accuracy, a 79.5% average F1-score, and 95% ROC in classifying burn severities. Comparing BAM with LDI, our method achieved 91.39% accuracy, 78.12% sensitivity, and 95.07% specificity in segmenting burn regions. These findings demonstrate the robustness of our AI model and its potential clinical application.

Appropriate identification of burn depth and size is paramount. Despite the development of burn depth assessment aids [eg, laser Doppler imaging (LDI)], clinical assessment, which assesses partial-thickness burn depth with 67% accuracy, currently remains the most consistent standard of practice. We sought to develop an image-based artificial intelligence system that predicts burn severity and wound margins for use as a triaging tool in thermal injury management. Modified EfficientNet architecture trained by 1684 mobile-device-captured images of different burn depths was previously used to create a convoluted neural network (CNN). The CNN was modified to a novel boundary attention mapping (BAM) algorithm using elements of saliency mapping, which was used to recognize the boundaries of burns. For validation, 144 patient charts that included clinical assessment, burn location, total body surface area, and LDI assessment were retrieved for a retrospective study. The clinical images underwent CNN-BAM assessment and were directly compared with the LDI assessment. CNN using a 4-level burn severity classification achieved an accuracy of 85% (micro/macro-averaged receiver operating characteristic scores). The CNN-BAM system can successfully highlight burns from surrounding tissue with high confidence. CNN-BAM burn area segmentations attained a 91.6% accuracy, 78.2% sensitivity, and 93.4% specificity, when compared to LDI methodology. Results comparing the CNN-BAM outputs to clinical and LDI assessments have shown a high degree of correlation between the CNN-BAM burn severity predictions to those extrapolated from LDI healing potential (66% agreement). CNN-BAM algorithm gives equivalent burn-depth detection accuracy as LDI with a more economical and accessible application when embedded in a mobile device.

Burn care management includes assessing the severity of burns accurately, especially distinguishing superficial partial-thickness burns from deep partial-thickness burns, in the context of providing definitive, downstream treatment. Moreover, the healing of the wound in the subacute care setting requires continuous tracking to avoid complications. Artificial intelligence (AI) and computer vision (CV) provide a unique opportunity to build low-cost and accessible tools to classify burn severity and track changes in wound parameters, both in the clinic by physicians and nurses and asynchronously in the remote setting by the patient themselves. Wound assessments can be achieved by AI–CV using the principles of image-guided therapy using high-quality 2D color images. Wound parameters can include wound 2D spatial dimension and the characterization of wound color changes, which demonstrates physiological changes such as the presentation of eschar/necrotic tissue, pustulence, granulation tissue, and scabbing. Here we present the development of AI–CV-based Skin Abnormality Tracking Algorithm pipeline. Additionally, we provide the results on a single localized burn tracked for a 6-week period in the clinic and an additional 2-week period of home monitoring.

Burn injuries can result from mechanisms such as thermal, chemical, and electrical insults. A prompt and accurate assessment of burns is essential for deciding definitive clinical treatments. Currently, the primary approach for burn assessments, via visual and tactile observations, is approximately 60%-80% accurate. The gold standard is biopsy and a close second would be non-invasive methods like Laser Doppler Imaging (LDI) assessments, which have up to 97% accuracy in predicting burn severity and the required healing time. In this paper, we introduce a machine learning pipeline for assessing burn severities and segmenting the regions of skin that are affected by burn. Segmenting 2D colour images of burns allows for the injured versus non-injured skin to be delineated, clearly marking the extent and boundaries of the localized burn/region-of-interest, even during remote monitoring of a burn patient. We trained a convolutional neural network (CNN) to classify four severities of burns. We built a saliency mapping method, Boundary Attention Mapping (BAM), that utilises this trained CNN for the purpose of accurately localizing and segmenting the burn regions from skin burn images. We demonstrated the effectiveness of our proposed pipeline through extensive experiments and evaluations using two datasets; 1) A larger skin burn image dataset consisting of 1684 skin burn images of four burn severities, 2) An LDI dataset that consists of a total of 184 skin burn images with their associated LDI scans. The CNN trained using the first dataset achieved an average F1-Score of 78% and micro/macro- average ROC of 85% in classifying the four burn severities. Moreover, a comparison between the BAM results and LDI results for measuring injury boundary showed that the segmentations generated by our method achieved 91.60% accuracy, 78.17% sensitivity, and 93.37% specificity.

Insufflation of epinephrine-containing solutions (clysis) has shown to decrease blood loss in burn surgery. Current delivery methods are associated with significant cost and may predispose burn patients to hypothermia. This was a proof-of-concept study to evaluate a novel surgeon-operated clysis delivery system. Our initial experience with a novel fluid management system is presented. Temperature, pressure, and volume of clysis was recorded. Patient and burn factors were evaluated and complications collected. Finally, a cost-effectiveness analysis was conducted. Thirty-seven consecutive cases comprising 22 adult patients (15/22, 68% male), with a mean age of 49 years (+/−19) were reviewed. The mean % total body surface area of all patients was 39 (+/−21.7). The mean temperature, pressure, and volume of administered clysis was 32.2 degrees Celsius (+/−4.4), 265.04 mmHg (+/−56.17), and 5805.8 mL (+/−4844.4), respectively. The mean dose of epinephrine administered was 14.5 mg (+/−12.1). The mean temperature variability was 1.1 °C (+/−1.2). The total mean of packed red blood cells (PRBC) transfused was 507.6 mL (+/−624.4). There were no recorded complications. We identified a cost savings of CAD 20,766 over the cases examined, compared to our conventional clysis delivery technique. This novel technique provides rapid and safe infiltration of warmed clysis in burn surgery. We were able to maintain intra-operative euthermia. In addition, this technique may be transfusion-sparing. The introduction of this method of clysis administration was associated with significant cost-savings. Future randomized study is necessary.

Burn injuries significantly increase a patient’s metabolic demand. Adequate nutrition is essential as an adjunct to recovery and reducing morbidity and mortality. In contrast to adults, this is especially important for pediatric patients who have limited reserves and are in a period of growth. Burn patients often require multiple anesthetic procedures that are accompanied by standard perioperative fasting periods that result in substantial nutritional interruptions. Continuous intraoperative feeding has been proposed as a solution, but there is no current consensus on its role and safety, particularly in the pediatric population. Thus, the goal of this study was to examine the safety and benefits of intraoperative nutrition in critically-ill pediatric burn injured patients. A systematic review of MEDLINE, PubMed, Scopus, and Web of Science was conducted using the following terms: feeding or enteral or nutrition or fasting and adolescent or youth or pediatric or child or teen and burn or thermal injury or fire. The primary outcome was incidence of aspiration. Secondary outcomes included patient nutritional status (caloric deficit and weight), wound healing, days spent in the intensive care unit, ventilator days, pneumonia, number of surgeries, length of hospital stay, and mortality. Pooled analyses of binary outcomes were computed. Four studies consisting of 496 patients, met inclusion criteria. All studies were level IV evidence, but had high methodological quality. The median burn total body surface area (TBSA) was 43.8% (IQR 33.4-58.8%), with a median of 30% of patients having an inhalational injury. Patients underwent a median of 4.2 surgeries (IQR 1.8-7.4). Intraoperative feeding was conducted through nasoduodenal tubes. There were no aspiration events. Pooled analysis demonstrated that there were no differences in rates of aspiration, pneumonia, or wound infection (p>0.05) between patients who were intraoperatively fed and those who were not. Those fed intraoperatively had significantly more surgeries, ventilator days, longer hospital stays, but lower mortality (p<0.05). There was large heterogeneity in nutritional assessment methods. Intraoperatively fed patients had an average gain of 144.4 kcal/kg,1.7 days of exclusive enteral nutrition (vs. loss of -119.1 kcal/kg and -1.4 days), and a cumulative positive caloric balance of +2673kcal ±2147 (vs. loss of -7899kcal ±3123) compared to those with interrupted feeding. Continuous intraoperative duodenal feeding during burn surgery appears to be safe in the pediatric burn population, with no reported episodes of aspiration. Uninterrupted feeding was also associated with weight maintenance and reduced caloric deficit. It may also have a survival benefit, as continuously fed patients needed more surgeries and intensive/hospital care, but had decreased mortality.

Introduction: One of the important factors in achieving gender equity is ensuring equitable surgical training for all. Previous studies have shown that females get significantly lower surgical exposure than males in certain surgical specialties. Gender gap in surgical exposure has never been assessed in plastic surgery. To that end, the goal of this study was to assess if there are any differences in plastic surgery training between male and female residents. Methods: A survey was sent to all plastic surgery residency programs in Canada to assess the No. of surgeries residents operated on as a co-surgeon or primary assistant during their training. The survey also assessed career goals, level of interest in the specialty, and subjective perception of gender bias. Results: A total of 89 plastic surgery residents (59.3% participation rate) completed the survey and were included in the study. The average No. of reconstructive cases residents operated on as a co-surgeon or primary assistant was 245 ± 312 cases. There was no difference in either reconstructive or aesthetic surgery case logs between male and female residents ( p > .05). However, a significantly larger proportion of females (39%) compared to males (4%) felt that their gender limited their exposure to surgical cases and led to a worsening of their overall surgical training ( p < .001). Finally, a larger proportion of male residents were interested in academic careers while a larger proportion of female residents were interested in a community practice ( p = .024). Conclusion: While there is no evidence of differences in the volume of logged cases between genders, female surgical residents still feel that their respective gender limits their overall surgical training. Gender inequalities in training should be addressed by residency programs.

Background Microsurgical free tissue transfers are a mainstay of lower extremity reconstruction. Despite being a reliable source of soft tissue, complications do arise. Venous congestion is among the most common causes of flap failure in lower extremity reconstruction, an issue that is attributed to venous stasis and impaired venous return in this region. There remains significant debate whether dual venous drainage improves outcomes. The aim of this study was thus to compare one versus two venous anastomoses in lower limb free flap reconstruction. Methods A systematic review of Medline, EMBASE, EBSCO CINAHL, SCOPUS, Proquest Dissertations and Theses Global, Cochrane Library, and PROSPERO from inception to May 20, 2020, was conducted. Two independent reviewers screened titles and extracted data. Our primary outcome was total free flap necrosis. Secondary outcomes were partial flap necrosis, minor complications, flap reoperation, venous thrombosis, and amputation. Methodological quality was assessed using the MINORS criteria and level of evidence. Results Three-hundred and fourteen unique titles were identified. All studies were level VI evidence and had a mean MINORS score of 16.1/24. Seven studies (comprising 1499 patients, 910 single venous anastomoses, and 579 double venous anastomoses) met criteria for inclusion. The mean (SD) patient age was 46.5 (7.1) years. Double venous anastomoses did not reduce the rate of minor complications, flap takeback, venous thrombosis, total flap necrosis, or partial flap necrosis when compared to a single vein (all p > .05). Conclusion In microvascular lower extremity reconstruction, two venous anastomoses did not reduce the rate of minor or major complications.

Background: Restoration of shoulder function in obstetrical brachial plexus injury is paramount. There remains debate as to the optimal method of upper trunk reconstruction. The purpose of this study was to test the hypothesis that spinal accessory nerve to suprascapular nerve transfer leads to improved shoulder external rotation relative to sural nerve grafting. Methods: A systematic review of Medline, EMBASE, EBSCO CINAHL, SCOPUS, Cochrane Library, and TRIP Pro from inception was conducted. Our primary outcome was shoulder external rotation. Results: Four studies were included. Nerve transfer was associated with greater shoulder external rotation relative to nerve grafting (mean difference: 0.82 AMS 95% confidence interval [CI]: 0.27-1.36, P < .005). Patients undergoing nerve grafting were more likely to undergo a secondary shoulder stabilizing procedure (odds ratio [OR]: 1.27, 95% CI: 0.8376-1.9268). Conclusion: In obstetrical brachial plexus injury, nerve transfer is associated with improved shoulder external rotation and a lower rate of secondary shoulder surgery. Level of Evidence: Level III; Therapeutic