The abbreviated injury score (AIS) is commonly used as a grading system for inhalation injuries. While inhalation injury grades have inconsistently been shown to correlate positively with the time mechanical ventilation is needed, grading is subjective and relies heavily on the clinicians’ experience and expertise. Additionally, no correlation has been shown between these patients’ inhalation injury grades and outcomes. In this paper, we propose a novel inhalation injury grading method which uses deep learning algorithms in bronchoscopy images to determine the injury grade from the carbonaceous deposits, blistering, and fibrin casts in the bronchoscopy images. The proposed method adopts transfer learning and data augmentation concepts to enhance the accuracy performance to avoid overfitting. We tested our proposed model on the bronchoscopy images acquired from eighteen patients who had suffered inhalation injuries, with the degree of severity 1, 2, 3, 4, 5, or 6. As performance metrics, we consider accuracy, sensitivity, specificity, F-1 score, and precision. Experimental results show that our proposed method, with both transfer learning and data augmentation components, provides an overall 86.11% accuracy. Moreover, the experimental results also show that the performance of the proposed method outperforms the method without transfer learning or data augmentation.

Toxic epidermal necrolysis is a drug-mediated disease process which mimics a partial thickness thermal injury. It has long been treated with frequent wound dressing changes and supportive care. There has been minimal efficacious system therapy. The pathophysiology is poorly understood but causes necrosis of keratinocytes at the dermal-epidermal junction leading to sloughing of the epidermis. The disease is rare with high mortality rates associated with long hospital stays. This case report describes the application of autologous skin cell suspension to a patient with toxic epidermal necrolysis after antihypertensive and hyperglycemic therapy. This was associated with minimal wound care and efficacious arrest of patient disease process and timely closure of wound.

This study analyzed the geographic variation in annual Medicare reimbursement changes for common burn surgery procedures from 2011 to 2022 to clarify trends in reimbursement. The Center for Medicare and Medicaid Services’ Physician fee schedule database was analyzed to find state-by-state reimbursement rates for the most common burn surgery procedures. Physician reimbursement was adjusted for inflation utilizing the consumer price index. Procedures were weighted according to frequency, and an inflation-adjusted percent change was identified for each state. Since 2011, the inflation-adjusted Medicare reimbursement for the top burn surgery procedures for all U.S. states decreased by a yearly average of 2.67%. Washington (-2.17%), New York (-2.31%), Oregon (-2.33%), and the District of Columbia (-2.35%) showed the smallest annual percent change. Illinois (-3.34%), Mississippi (-3.04%), Idaho (-2.99%), and Michigan (-2.96%) were the states with the greatest annual decrease. The most common procedures included initial treatment of burns (16000), burn dressing and debridement (16020, 16025, 16030), and burn eschar incision (16035). Medicare reimbursement for burn surgery procedures decreased from 2011 to 2022. The geographic variance in reimbursement patterns may incentivize physicians to pursue other surgical specialties or practice in certain areas which could limit access to care in low reimbursement areas. Further research is needed to examine disparities that may have arisen due to decreasing reimbursement over the last decade. New action is also needed to moderate diminishing burn surgery reimbursement to ensure quality care for Medicare beneficiaries in low-reimbursement states.