Australian guideline on wound classification of diabetes-related foot ulcers: part of the 2021 Australian evidence-based guidelines for diabetes-related foot disease

Background Wound classification systems are useful tools to characterise diabetes-related foot ulcers (DFU) and are utilised for the purpose of clinical assessment, to promote effective communication between health professionals, and to support clinical audit and benchmarking. Australian guidelines regarding wound classification in patients with DFU are outdated. We aimed to adapt existing international guidelines for wound classification to develop new evidence-based Australian guidelines for wound classification in people with diabetes and DFU. Methods Recommended NHRMC procedures were followed to adapt suitable International Working Group on the Diabetic Foot (IWGDF) guidelines on wound classification to the Australian health context. Five IWGDF wound classification recommendations were evaluated and assessed according to the ADAPTE and GRADE systems. We compared our judgements with IWGDF judgements to decide if recommendations should be adopted, adapted or excluded in an Australian context. We re-evaluated the quality of evidence and strength of recommendation ratings, provided justifications for the recommendation and outlined any special considerations for implementation, subgroups, monitoring and future research in an Australian setting. Results After the five recommendations from the IWGDF 2019 guidelines on the classification of DFUs were evaluated by the panel, two were adopted and three were adapted to be more suitable for Australia. The main reasons for adapting, were to align the recommendations to existing Australian standards of care, especially in specialist settings, to maintain consistency with existing recommendations for documentation, audit and benchmarking and to be more appropriate, acceptable and applicable to an Australian context. In Australia, we recommend the use of the SINBAD system as a minimum standard to document the characteristics of a DFU for the purposes of communication among health professionals and for regional/national/international audit. In contrast to the IWGDF who recommend against usage, in Australia we recommend caution in the use of existing wound classification systems to provide an individual prognosis for a person with diabetes and a foot ulcer. Conclusions We have developed new guidelines for wound classification for people with diabetes and a foot ulcer that are appropriate and applicable for use across diverse care settings and geographical locations in Australia.

P084 MESH USE IN THE UNITED STATES: MESH TYPES AND THEIR INDICATIONS

Aim Synthetic non-absorbable mesh repair is considered standard of care for most hernias in the United States (US). The introduction of biologic absorbable mesh in the 2000’s has changed this practice and now novel synthetic absorbable and hybrid meshes are available. We aim to describe US trends of mesh use. Material and Methods We surveyed the Abdominal Core Health Quality Collaborative database for all repairs using mesh from 2012 to 2021. Mesh types and indications were analysed. Results Among 47,555 patients who underwent hernia repair with mesh, the majority were with synthetic non-absorbable meshes (96%). Absorbable mesh was placed in 2,039 (4%) patients and included biologic absorbable (893, 44%), synthetic absorbable (1,070, 52%), and hybrid (76, 4%) meshes. Synthetic non-absorbable mesh use was significantly predominant in all wound classes, including dirty/contaminated wounds (P < 0.01) [Figure 1]. Over time, we noted a trend toward lower incidence of absorbable and hybrid mesh use, from 18% to 2% (P < 0.01). Interestingly, we noted a relative increase in annual incidence of absorbable and hybrid mesh use in clean wounds, from 20% to 63% (P < 0.01) [Figure 2]. Figure 1Mesh type used in each wound classFigure 2Absorbable mesh use in clean vs. not clean wounds. Conclusions In the United States, synthetic non-absorbable meshes are commonly used during hernia repairs in dirty and contaminated fields. At the same time, there is a significant increase in the use of absorbable and hybrid meshes in the repair of hernias with clean wound classification. The costs and long-term outcomes of such surgeon choices have yet to be validated.

The Enlightening Role of Explainable Artificial Intelligence in Chronic Wound Classification

Artificial Intelligence (AI) has been among the most emerging research and industrial application fields, especially in the healthcare domain, but operated as a black-box model with a limited understanding of its inner working over the past decades. AI algorithms are, in large part, built on weights calculated as a result of large matrix multiplications. It is typically hard to interpret and debug the computationally intensive processes. Explainable Artificial Intelligence (XAI) aims to solve black-box and hard-to-debug approaches through the use of various techniques and tools. In this study, XAI techniques are applied to chronic wound classification. The proposed model classifies chronic wounds through the use of transfer learning and fully connected layers. Classified chronic wound images serve as input to the XAI model for an explanation. Interpretable results can help shed new perspectives to clinicians during the diagnostic phase. The proposed method successfully provides chronic wound classification and its associated explanation to extract additional knowledge that can also be interpreted by non-data-science experts, such as medical scientists and physicians. This hybrid approach is shown to aid with the interpretation and understanding of AI decision-making processes.

A Highly Transparent and Explainable Artificial Intelligence Tool for Chronic Wound Classification: XAI-CWC

Artificial Intelligence (AI) has seen increased application and widespread adoption over the past decade despite, at times, offering a limited understanding of its inner working. AI algorithms are, in large part, built on weights, and these weights are calculated as a result of large matrix multiplications. Computationally intensive processes are typically harder to interpret. Explainable Artificial Intelligence (XAI) aims to solve this black box approach through the use of various techniques and tools. In this study, XAI techniques are applied to chronic wound classification. The proposed model classifies chronic wounds through the use of transfer learning and fully connected layers. Classified chronic wound images serve as input to the XAI model for an explanation. Interpretable results can help shed new perspectives to clinicians during the diagnostic phase. The proposed method successfully provides chronic wound classification and its associated explanation. This hybrid approach is shown to aid with the interpretation and understanding of AI decision-making processes.

AI technology for remote clinical assessment and monitoring

Objective: To report the clinical validation of an innovative, artificial intelligence (AI)-powered, portable and non-invasive medical device called Wound Viewer. The AI medical device uses dedicated sensors and AI algorithms to remotely collect objective and precise clinical data, including three-dimensional (3D) wound measurements, tissue composition and wound classification through the internationally recognised Wound Bed Preparation (WBP) protocol; this data can then be shared through a secure General Data Protection Regulation (GDPR)- and Health Insurance Portability and Accountability Act (HIPAA)-compliant data transfer system. This trial aims to test the reliability and precision of the AI medical device and its ability to aid health professionals in clinically evaluating wounds as efficiently remotely as at the bedside. Method: This non-randomised comparative clinical trial was conducted in the Clinica San Luca (Turin, Italy). Patients were divided into three groups: (i) patients with venous and arterial ulcers in the lower limbs; (ii) patients with diabetes and presenting with diabetic foot syndrome; and (iii) patients with pressure ulcers. Each wound was evaluated for area, depth, volume and WBP wound classification. Each patient was examined once and the results, analysed by the AI medical device, were compared against data obtained following visual evaluation by the physician and research team. The area and depth were compared with a Kruskal–Wallis one-way analysis of variations in the obtained distribution (expected p-value>0.1 for both tests). The WBP classification and tissue segmentation were analysed by directly comparing the classification obtained by the AI medical device against that of the testing physician. Results: A total of 150 patients took part in the trial. The results demonstrated that the AI medical device's AI algorithm could acquire objective clinical parameters in a completely automated manner. The AI medical device reached 97% accuracy against the WBP classification and tissue segmentation analysis compared with that performed in person by the physician. Moreover, data regarding the measurements of the wounds, as analysed through the Kruskal–Wallis technique, showed that the data distribution proved comparable with the other methods of measurement previously clinically validated in the literature (p=0.9). Conclusion: These findings indicate that remote wound assessment undertaken by physicians is as effective through the AI medical device as bedside examination, and that the device was able to assess wounds and provide a precise WBP wound classification. Furthermore, there was no need for manual data entry, thereby reducing the risk of human error while preserving high-quality clinical diagnostic data.

Triaged Treatment-Based Conventional Weapon Combat Wound Classification Code Design and Injury Spectrum Statistical Analysis

Introduction We create an expandable combat wound classification coding system and a stratified standardized combat wound injury spectrum to support triage according to the treatment echelon and to provide the basis for the rapid and efficient classification of combat casualties. The coding system simultaneously assists in identifying injuries with a high incidence of fatality that require emergency treatment, and provides a framework for the triage of combat wounds in mass casualty situations. Materials and Methods The three-tiered treatment echelon consisting of battlefield on-site first aid, emergency treatment, and early treatment was used to design an expanded combat wound classification coding system according to the differential needs of combat wound treatment. The Herfindahl−Hirschman Index (HHI) index was used as the key indicator for injury spectrum ranking and was applied to select the key anatomical structures that require the highest priority treatment in the three treatment echelons. The combat wound classification codes were based on the results of consultations with selected experts and results from the HHI index calculations. The use of the classification codes at the battlefield on-site first aid stage and emergency treatment stage was evaluated in exercises to test and compare the effectiveness of the classification codes against current classification systems. Results We obtained exhaustive combinations from the vast number of combat wound factors in combat wound classification codes, constructed injury spectrum frameworks within the different treatment echelons, and identified injuries with a high-incidence of fatality in each of the treatment echelons. Compared with traditional methods, the time spent on coding was reduced and classification accuracy was improved when using the new classification codes, which led to improved efficiency of classification and a reduced workload for hospital staff. Conclusions The combat wound classification codes that were established through the HHI index and expert consultations achieved good results in terms of having higher classification speed and accuracy than traditional methods. This means they could be used to identify injuries with a high-incidence of fatality and provide guidance to improve the efficiency of treatment among all treatment echelons in the army.