Journal of burn care & research : official publication of the American Burn Association
-
We present in this paper the application of deep convolutional neural networks (CNNs), which is a state-of-the-art artificial intelligence (AI) approach in machine learning, for automated time-independent prediction of burn depth. Color images of four types of burn depth injured in first few days, including normal skin and background, acquired by a TiVi camera were trained and tested with four pretrained deep CNNs: VGG-16, GoogleNet, ResNet-50, and ResNet-101. ⋯ The accuracy was compared with the clinical diagnosis obtained after the wound had healed. Hence, application of AI is very promising for prediction of burn depth and, therefore, can be a useful tool to help in guiding clinical decision and initial treatment of burn wounds.
-
Previous research on burn patients who test positive for methamphetamines (meth) has yielded mixed results regarding whether meth-positive status leads to worse outcomes and longer hospitalizations. We hypothesized that meth-positive patients at our regional burn center would have worse outcomes. We reviewed burn admissions from January 2014 to December 2017 and compared total patients versus meth-positive, and matched meth-negative versus meth-positive for total BSA burn, length of stay (LOS), intensive care unit (ICU) days, days on ventilator, discharge status (lived/died), number of operating room (OR) visits, number of procedures, socioeconomic status, comorbidities, and discharge disposition. ⋯ Meth-positive patients have lower socioeconomic status, larger burns, and longer LOS compared to the total burn population. Methamphetamine use, by itself, does not appear to change outcomes. Methamphetamine use leads to larger burns in a population with fewer resources than the general population.
-
Pruritus is a common problem following burn injuries; however, the literature to date has focused on adult survivors and/or pediatric survivors of large burns. The current study examines acute postburn pruritus in children under the age of 4 years (N = 256) with smaller burns (mean TBSA = 3.99%), which represents the most common type of patient typically treated in pediatric burn centers. Parents rated their child for pruritus, irritability, and sleep disturbances; additionally, parents completed a self-report of distress. ⋯ Regression analysis indicated that child minority status, greater burn TBSA, and more days elapsed since burn predicted higher levels of pruritus. In turn, pruritus was positively correlated with child irritability, delayed sleep onset, sleep disturbance, and parent distress. Thus, our results indicate that parent-rated pruritus in young pediatric burn patients is important to evaluate, as itch is significantly associated with other important clinical outcomes as early as the first month of the burn for pediatric patients and their parents.
-
Under ideal circumstances, severely frostbitten extremities are rapidly rewarmed and treated with thrombolytic therapy within 6 to 24 hours. In an "inner city," urban environment, most patients who suffer frostbite injuries present in a delayed fashion, sustain repeated injuries further complicated by psychological issues or intoxication, and are rarely ideal candidates for thrombolytic therapy within the prescribed timeframe. We describe our experience with the treatment of urban frostbite injuries. ⋯ Wound closure and limb-length salvage was then achieved by: free flap coverage (n = 2), local flaps (n = 8), split-thickness skin grafting (n = 22), and secondary intention healing (n = 6). While tissue plasminogen activator has been successful in reducing the need for digital amputation following frostbite injuries, in our experience, this treatment modality is not applicable to the urban patient population who often present late and after cycles of reinjury. Therefore, our approach focused on salvaging limb length with durable coverage, as the injuries were unable to be reversed.
-
Work integration and retention after burn injury is a key outcome. Little is known about how burn survivors reintegrate into the workplace. This article compares scores on the Life Impact Burn Recovery Evaluation (LIBRE) Profile, a burn-specific measure of social participation, between burn survivors and general population samples, focusing on the Work and Employment domain. ⋯ Distributions indicated higher social participation in the burn survivor sample than the general sample. Possible explanations include sample bias; resilience, posttraumatic growth, or response-shift of survivors; and limitations of using items in the general sample. Working burn survivors scored higher than those not working. Future work can explore factors that mediate higher scores and develop interventions.