No abstract

Introduction Pediatric friction hand injuries are prevalent, likely due to the increasing presence of home exercise equipment. While friction injuries often appear deeper on initial assessment, not all are treated surgically during the acute phase. We sought to characterize our experience with outcomes based on acute (< 30 days) surgical intervention compared to delayed intervention. Methods Patients were queried from a single institution, verified pediatric burn center database. A retrospective chart review of pediatric patients (< 18 years) over a 5 year period was performed. Data collected included demographics, treatment methods (acute vs. delayed), dressing type, scar management, and follow-up. Outcomes included additional surgical and non-surgical adjuncts to treat the sequela of injury. Results Our institution treated 23 treadmill hand injuries over the 5-year period. There was a slight predominance of female (n=13, 57%) vs. male (n=10, 43%) patients. Median age at injury was 2 years (IQR 1–3). Thirteen patients (57%) sustained an injury equivalent to a second degree burn and ten (43%) to third degree. Injuries were initially treated with silvadene (n=14) and/or xeroform (n=21). Involvement of left and right hands were equally divided and all injuries involved the digits. The median number of digits involved was 2 (range 1–4). The most commonly injured digits were the middle and ring fingers (19 each). Average length of stay was 14 hours. All but one patient followed-up with a median number of 4 clinic visits. All of these patients were reported as healed at time of last follow-up. Median time to healing was 31.5 days (IQR 29 – 58). Overall, 4 patients (17%) underwent acute surgical intervention with a median of 7 days from injury (IQR 1.75–13.5). Of these 4 patients, 2 (50%) required additional operations for scar management and 2 (50%) required non-surgical management. Of the 19 (83%) who did not undergo early surgical management, only 1 patient (6%) required a Z-plasty, 12 (63%) were managed with non-surgical intervention and 6 (31%) needed no further treatment after healing. Conclusions Pediatric friction hand injuries often affect multiple digits and lead to a median of 4 clinic visits. Our data suggest that early surgical intervention in this cohort did not minimize future surgical procedures or non-surgical management. Rather, delayed intervention appears to allow for fewer surgical procedures and similar non-surgical management. Larger studies are required to validate this finding; however, this data suggests that continued initial management with a combination of silvadene and xeroform may be a safe option. Applicability of Research to Practice Our study provides guidance in the evaluation and treatment of pediatric treadmill friction injury. This data supports delaying surgical interventions on these seemingly deep hand injuries.

Introduction Though widely used, current scar assessment scales are inaccurate and highly subjective, further complicating the already difficult task of determining the optimal management of burn patients. Additional disadvantages of these tools include the need for direct examination by an experienced clinician and the inability to retrospectively review them. The lack of an accurate assessment tool inevitably impairs any research examining novel therapeutic strategies designed to improve burn scar outcomes by introducing observer bias at every step. Common examples of these tools include the Vancouver Scar Scale and Visual analog scale. New imaging and processing technologies have the potential of bringing accuracy, reproducibility, and accessibility to burn scar assessments. With these goals in mind, our team developed a novel scoring system and a classification model based on Machine Learning algorithms and analyzed 87 pictures to obtain scores on Inflammation (I), Scar (S), Uniformity (U), and Pigmentation (P). Methods All algorithms were trained using both the sub-acute and the long-term phase pictures. The classification model is based on supervised learning, which requires many examples of annotated pictures and corresponding scar scores. The model used a Linear Discriminant Analysis (LDA) algorithm and visual features of the scars and the natural skin. To train and evaluate this model, four burn care providers individually annotated 186 pictures of skin grafts and later formed a committee to annotate by consensus a subset of representative pictures. While the individual predictions were used as an accuracy baseline, the consensus annotation was the true score and used to train the model. Results The model predictions were more accurate in scores mainly based on color (I and P), rather than texture (S and U), as shown by the micro-averaged Area Under the Curve (AUC) of 0.86, 0.61, 0.51, and 0.80 for I, S, U, and P, respectively (Figure 1). The model accuracy was higher than the human baseline for the I (F1 of 0.60 vs. 0.59±0.13, respectively) and P scores (0.54 vs. 0.51±0.09), but lower in the S (0.30 vs. 0.63±0.22) and U scores (0.62 vs. 0.86±0.19). Conclusions Our findings are encouraging and suggest that further improvement of the accuracy of the algorithm could be achieved on the second phase of our assessment development project by increasing the number of pictures it learns from and adding more visual features related to skin texture. Applicability of Research to Practice Our study provides an accurate and reproducible evaluation of burn scars, that leads to newer therapeutic strategies employed by specialized burn care facilities.