Background: Current literature suggests relatively low accuracy of multi-class wound classification tasks using deep learning networks. Solutions are needed to address the increasing diagnostic burden of wounds on wound care professionals and to aid non-wound care professionals in wound management.
Objective: To develop a reliable, accurate 9-class classification system to aid wound care professionals and perhaps eventually, patients and non-wound care professionals, in managing wounds.
Methods: A total of 8173 training data images and 904 test data images were classified into 9 categories: operation wound, laceration, abrasion, skin defect, infected wound, necrosis, diabetic foot ulcer, chronic ulcer, and wound dehiscence. Six deep learning networks, based on VGG16, VGG19, EfficientNet-B0, EfficientNet-B5, RepVGG-A0, and RepVGG-B0, were established, trained, and tested on the same images. For each network the accuracy rate, defined as the sum of true positive and true negative values divided by the total number, was analyzed.
Results: The overall accuracy varied from 74.0% to 82.4%. Of all the networks, VGG19 achieved the highest accuracy, at 82.4%. This result is comparable to those reported in previous studies.
Conclusion: These findings indicate the potential for VGG19 to be the basis for a more comprehensive and detailed AI-based wound diagnostic system. Eventually, such systems also may aid patients and non-wound care professionals in diagnosing and treating wounds.
Background: Accurate burn wound size estimation is important for resuscitation and subsequent management. It is also important for the development of referral guidelines in Nigeria.
Objective: To establish whether a significant discrepancy exists in burn size estimation between referral centers and burn units.
Methods: A retrospective review of burn patients managed at the burn unit of a premier tertiary hospital in Ibadan, southwestern Nigeria, between January 1, 2016, and October 31, 2019 was conducted. Patients' demographic and other characteristics, inclusive of TBSA estimation from point of referral and the burn unit, were retrieved and analyzed.
Results: A total of 96 burn injury records were found for the study period, with a male-to-female ratio of 1.3:1. Thirty-five records (36.5%) included no burn size estimation by the referring physician. There was a statistically significant difference in TBSA estimation between referring physicians and burn unit physicians (P = .015). Burn wounds were more likely to be overestimated than underestimated (P = .016). Overestimation is more likely with minor burns and in pediatric patients. Underestimation was more likely in adults.
Conclusion: There is a significant difference in burn size estimation between burn unit physicians and referring physicians. This finding underscores the need for continuous education on burn estimation to aid proper referral and management.
Background: Marjolin ulcer is an SCC arising from chronic inflammatory tissue. Such ulcers pose a high risk for metastasis; the 5-year survival rate of 40% to 69% suggests that improvement is possible with early diagnosis.
Objective: To raise awareness and update education in the medical community regarding this manifestation of SCC.
Methods: The authors performed a retrospective literature review specifically for SCC arising in the context of HS. A PubMed search yielded 81 articles reporting SCC in the context of HS from 1958 to November 2022, with a total of 123 cases. The authors' additional patient, who was treated in practice, is included as Case 1, bringing the total number of patients to 124.
Results: Seventy-three percent of patients were male. The mean age at the time of SCC diagnosis was 53 years ± 10.25 standard deviation. The mean interval between HS diagnosis and SCC development was 24.4 years ± 11.33. Thirty-six percent of patients had metastatic disease. Of the 102 cases that included details on life and death, 58 were noted to have died; of those 58, 60% died within the first year following diagnosis.
Conclusion: Given the poor prognosis of Marjolin ulcer, with rapid progression after diagnosis, frequent visual examination and biopsies with a high index of suspicion for HS are recommended to identify SCC prior to metastatic transformation and subsequent unresectable disease. If surgical intervention is performed in the management of HS, tissue should always be sent for pathologic examination.
Introduction: Diabetic foot infection is a serious and painful process for patients with diabetes, and the considerable morbidity associated with the condition warrants attention. Effective inflammatory markers may become important in the detection of diabetic foot infection.
Objective: The goal of the research was to systematically assess the function of inflammatory markers in the detection of diabetic foot infection.
Methods: Online databases including PubMed, SpringerLink, and Web of Science were searched. The quality of research and data was assessed using the Newcastle-Ottawa Scale. A random-effects model was used to compare changes in inflammatory markers between patients with infected diabetic foot (IDF) and patients with non-infected diabetic foot.
Results: Ten studies with 785 participants were included in the systematic review. The study analyzed 3 inflammatory markers: white blood cell (WBC) count, C-reactive protein (CRP) level, and procalcitonin (PCT) level. The meta-analysis indicated that mean WBC count (standardized mean differences [SMD]: 0.51, 95% CI: 0.23, 0.79; P < .0001), mean CRP level (SMD: 1.05, 95% CI: 0.60, 1.50; P < .0001) and mean PCT level (SMD: 0.80, 95% CI: 0.36, 1.24; P < .0001) were higher in patients with IDF. The differences were statistically significant, but the funnel plots indicated the existence of publication bias.
Conclusions: The meta-analysis further confirmed the significant association between inflammatory markers and diabetic foot infection. It also confirmed that WBC count, CRP level, and PCT level can be used as laboratory auxiliary indexes in the detection of diabetic foot infection, providing information for improved diagnosis and prevention.
Background: Most chronic wounds contain biofilm, and debridement remains the centerpiece of treatment. Enzymatic debridement is an effective tool in removing nonviable tissue, however, there is little evidence supporting its effect on planktonic and biofilm bacteria.
Objective: This study evaluated the effects of a novel BBD agent on removal of nonviable tissue, biofilm, and microbial loads in patients with chronic ulcers.
Materials and methods: Twelve patients with DFU or VLU were treated with up to 8 once-daily applications of BBD and then followed for an additional 2 weeks. Punch biopsy specimens were collected and analyzed for biofilm, and fluorescence imaging was used to measure bacterial load.
Results: Ten patients completed treatment, and 7 achieved complete debridement within a median of 2 applications (range, 2-8). By the end of the 2-week follow-up period, the mean ± SD reduction in wound area was 35% ± 38. In all 6 patients who were positive for biofilm at baseline, the biofilm was reduced to single individual or no detected microorganisms by the end of treatment. Red fluorescence for Staphylococcus aureus decreased from a mean of 1.09 cm² ± 0.58 before treatment to 0.39 cm² ± 0.25 after treatment. BBD was safe and well tolerated.
Conclusion: Preliminary data suggest that BBD is safe and that it can be used to effectively debride DFU and VLU, reduce biofilm and planktonic bacterial load, and promote reduction in wound size.
Each year, 27.5% of the 150 000 people in the United States who require lower extremity amputation experience significant postoperative complications, including pain, infection, and need for reoperation. Postamputation pain, including RLP and PLP, is debilitating. While the causes of such pain remain unknown, neuroma formation following sensory nerve transection is believed to be a major contributor. Various techniques exist for management of a symptomatic neuroma, but few data exist on which technique is superior. Furthermore, there are few data on primary prevention of neuroma formation following injury or intentional transection. The TMR technique shows promise for both management of PLP and RLP and prevention of neuroma formation. Following amputation, transected sensory nerves are coapted to nearby motor nerve supplying remaining extremity musculature. Not only does this procedure generate increased myoelectric signals for improved prosthesis control, TMR appears to neurophysiologically alter sensory nerves, preventing formation of painful sensory neuromas. The sole RCT to date evaluating the efficacy of TMR showed statistically significant reduction in PLP. TMR is not limited to use in the setting of major limb amputation. It has also been used in the setting of post-mastectomy pain, abdominal wall neuromas, digital amputations, and headache surgeries. This article reviews the origin of TMR and provides a brief description of histologic changes following the procedure, as well as current data regarding the efficacy of TMR with regard to postoperative pain relief. It also seeks to provide a concise, comprehensive resource for providers to facilitate better discussions with patients about treatment options.
Background: Small-area burn is a common but specific type of injury that can still lead to serious complications if not managed properly. Researchers have introduced a number of interventions.
Objective: The objective of this study was to compare the effects of eCASH concept-based care (ie, eBCare) with those of standard treatment on wound healing in patients with small-area burns.
Methods: In this prospective randomized controlled trial, patients with small-area burns received either eBCare (n = 35) or standard burn treatment (n = 35) for 2 weeks. Pain, anxiety, heart rate, exudate, and wound area were measured during and after dressing changes. Scar color and thickness were assessed 4 years or longer after discharge.
Results: The eBCare group had a lower median pain score, anxiety score, and heart rate compared with the control group (P < .001). The eBCare group also had a higher median wound healing rate on day 14 than the control group (P < .05). At follow-up 4 years or more after discharge, the eBCare group had better scar color and thickness than the control group (P < .05).
Conclusion: The use of eBCare reduced pain and anxiety, accelerated wound healing, and improved scar outcomes in patients with small-area burns, which suggests that eBCare may be a feasible option for this population.