Assessment of Simple Bedside Wound Characteristics for a Prediction Model for Diabetic Foot Ulcer Outcomes

The impact of machine learning on the prediction of diabetic foot ulcers - A systematic review

INTRODUCTION

Globally, diabetes mellitus poses a significant health challenge as well as the associated complications of diabetes, such as diabetic foot ulcers (DFUs). The early detection of DFUs is important in the healing process and machine learning may be able to help inform clinical staff during the treatment process.

METHODS

A PRISMA-informed search of the literature was completed via the Cochrane Library and MEDLINE (OVID), EMBASE, CINAHL Plus and Scopus databases for reports published in English and in the last ten years. The primary outcome of interest was the impact of machine learning on the prediction of DFUs. The secondary outcome was the statistical performance measures reported. Data were extracted using a predesigned data extraction tool. Quality appraisal was undertaken using the evidence-based librarianship critical appraisal tool.

RESULTS

A total of 18 reports met the inclusion criteria. Nine reports proposed models to identify two classes, either healthy skin or a DFU. Nine reports proposed models to predict the progress of DFUs, for example, classing infection versus non-infection, or using wound characteristics to predict healing. A variety of machine learning techniques were proposed. Where reported, sensitivity = 74.53-98 %, accuracy = 64.6-99.32 %, precision = 62.9-99 %, and the F-measure = 52.05-99.0 %.

CONCLUSIONS

A variety of machine learning models were suggested to successfully classify DFUs from healthy skin, or to inform the prediction of DFUs. The proposed machine learning models may have the potential to inform the clinical practice of managing DFUs and may help to improve outcomes for individuals with DFUs. Future research may benefit from the development of a standard device and algorithm that detects, diagnoses and predicts the progress of DFUs.

Development of an explainable artificial intelligence model for Asian vascular wound images

Chronic wounds contribute to significant healthcare and economic burden worldwide. Wound assessment remains challenging given its complex and dynamic nature. The use of artificial intelligence (AI) and machine learning methods in wound analysis is promising. Explainable modelling can help its integration and acceptance in healthcare systems. We aim to develop an explainable AI model for analysing vascular wound images among an Asian population. Two thousand nine hundred and fifty-seven wound images from a vascular wound image registry from a tertiary institution in Singapore were utilized. The dataset was split into training, validation and test sets. Wound images were classified into four types (neuroischaemic ulcer [NIU], surgical site infections [SSI], venous leg ulcers [VLU], pressure ulcer [PU]), measured with automatic estimation of width, length and depth and segmented into 18 wound and peri-wound features. Data pre-processing was performed using oversampling and augmentation techniques. Convolutional and deep learning models were utilized for model development. The model was evaluated with accuracy, F1 score and receiver operating characteristic (ROC) curves. Explainability methods were used to interpret AI decision reasoning. A web browser application was developed to demonstrate results of the wound AI model with explainability. After development, the model was tested on additional 15 476 unlabelled images to evaluate effectiveness. After the development on the training and validation dataset, the model performance on unseen labelled images in the test set achieved an AUROC of 0.99 for wound classification with mean accuracy of 95.9%. For wound measurements, the model achieved AUROC of 0.97 with mean accuracy of 85.0% for depth classification, and AUROC of 0.92 with mean accuracy of 87.1% for width and length determination. For wound segmentation, an AUROC of 0.95 and mean accuracy of 87.8% was achieved. Testing on unlabelled images, the model confidence score for wound classification was 82.8% with an explainability score of 60.6%. Confidence score was 87.6% for depth classification with 68.0% explainability score, while width and length measurement obtained 93.0% accuracy score with 76.6% explainability. Confidence score for wound segmentation was 83.9%, while explainability was 72.1%. Using explainable AI models, we have developed an algorithm and application for analysis of vascular wound images from an Asian population with accuracy and explainability. With further development, it can be utilized as a clinical decision support system and integrated into existing healthcare electronic systems.

Which biomarkers predict hard-to-heal diabetic foot ulcers? A scoping review

Diabetic foot ulcers (DFUs) often develop into hard-to-heal wounds due to complex factors. Several biomarkers capable of identifying those at risk of delayed wound healing have been reported. Controlling or targeting these biomarkers could prevent the progression of DFUs into hard-to-heal wounds. This scoping review aimed to identify the key biomarkers that can predict hard-to-heal DFUs. Studies that reported biomarkers related to hard-to-heal DFUs, from 1980 to 2023, were mapped. Studies were collected from the following databases: MEDLINE, CINAHL, EMBASE, and ICHUSHI (Japana Centra Revuo Medicina), search terms included "diabetic," "ulcer," "non-healing," and "biomarker." A total of 808 articles were mapped, and 14 (10 human and 4 animal studies) were included in this review. The ulcer characteristics in the clinical studies varied. Most studies focused on either infected wounds or neuropathic wounds, and patients with ischemia were usually excluded. Among the reported biomarkers for the prediction of hard-to-heal DFUs, the pro-inflammatory cytokine CXCL-6 in wound fluid from non-infected and non-ischemic wounds had the highest prediction accuracy (area under the curve: 0.965; sensitivity: 87.27%; specificity: 95.56%). CXCL-6 levels could be a useful predictive biomarker for hard-to-heal DFUs. However, CXCL6, a chemoattractant for neutrophilic granulocytes, elicits its chemotactic effects by combining with the chemokine receptors CXCR1 and CXCR2, and is involved in several diseases. Therefore, it's difficult to use CXCL6 as a prevention or treatment target. Targetable specific biomarkers for hard-to-heal DFUs need to be determined.

Validity and reliability of Chinese version of the new diabetic foot ulcer assessment scale

A specific assessment tool is urgently needed to guide effective wound care for diabetic foot ulcers. However, the tool has not been available in Chinese. We aimed to culturally translate and verify the validity and reliability of the new Diabetic Foot Ulcer Assessment Scale (DFUAS). The original scale was translated into Chinese according to the Brislin guidelines. Patients satisfying the inclusion and exclusion criteria were recruited. Each of the included foot ulcers was evaluated independently by two wound care specialists using the new DFUAS and by the third wound care specialists at the same time using the Bates-Jensen Wound Assessment Tool according to per guidelines. 210 diabetic foot ulcers were included for data analysis. The S-CVI of the Chinese version of the DFUAS was 0.96, and the I-CVIs ranged from 0.89 to 0.98. The total Cronbach's Alpha of the scale was 0.709, and the corrected item-total correlation of the items ranged from 0.4 to 0.872. The DFUAS had high inter-observer reliability of 0.997, and there were weak, moderate, and strong correlations between each pair of the items. The Bland-Altman plots showed a good agreement between the scale and the Bates-Jensen Wound Assessment Tool. We concluded that the Chinese version of the DFUAS showed good validity and reliability and is a reliable instrument for the assessment of diabetic foot ulcers.

Using Case-Based Reasoning in a Learning System: A Prototype of a Pedagogical Nurse Tool for Evidence-Based Diabetic Foot Ulcer Care

BACKGROUND

Currently, evidence-based learning systems to increase knowledge and evidence level of wound care are unavailable to wound care nurses in Denmark, which means that they need to learn about diabetic foot ulcers from experience and peer-to-peer training, or by asking experienced colleagues. Interactive evidence-based learning systems built on case-based reasoning (CBR) have the potential to increase wound care nurses' diabetic foot ulcer knowledge and evidence levels.

METHOD

A prototype of a CBR-interactive, evidence-based algorithm-operated learning system calculates a dissimilarity score (DS) that gives a quantitative measure of similarity between a new case and cases stored in a case base in relation to six variables: necrosis, wound size, granulation, fibrin, dry skin, and age. Based on the DS, cases are selected by matching the six variables with the best predictive power and by weighing the impact of each variable according to its contribution to the prediction. The cases are ranked, and the six cases with the lowest DS are visualized in the system.

RESULTS

Conventional education, that is, evidence-based learning material such as books and lectures, may be less motivating and pedagogical than peer-to-peer training, which is, however, often less evidence-based. The CBR interactive learning systems presented in this study may bridge the two approaches. Showing wound care nurses how individual variables affect outcomes may help them achieve greater insights into pathophysiological processes.

CONCLUSION

A prototype of a CBR-interactive, evidence-based learning system that is centered on diabetic foot ulcers and related treatments bridges the gap between traditional evidence-based learning and more motivating and interactive learning approaches.

Endovascular surgery for the treatment of purulent and necrotic complications in diabetic foot syndrome

Background: Diabetic foot syndrome (DFS) causes damage to the peripheral arteries in 50% of patients with diabetes mellitus (DM). The purpose of this study was to evaluate the efficacy of endovascular interventions, stenting, and balloon angioplasty for the treatment of patients with purulent and necrotic lesions in DFS. Methods: This was a retrospective study. During 2019-2020, stenting and balloon angioplasty were performed in 51 patients (study group) with purulent and necrotic complications of diabetic foot with limb ischemia. There were 32 women (62.7%) and 19 men (37.3%). The age of the patients varied from 45 to 81 years. Endovascular interventions were performed in combination with conservative therapy and topical treatment on 2 to 3 days after the debridement of the purulent lesions. To assess the outcomes of endovascular interventions, we studied the nature of changes in arterial circulation in the lower extremities. The mean blood flow velocity was calculated using the Doppler ultrasonography. The study was performed on the popliteal artery (PA), the posterior tibial artery (PTA), and on the dorsalis pedis artery. In this study, patients were divided into 2 groups: the study group- those who received endovascular intervention- and the control group- those who received only conservative therapy, which included local treatment without surgery. Results: The weightbearing function of the foot at discharge from the hospital was preserved in 94.2% (48 patients) of the study group and in 73.4% (22 patients) of the control group. During the next 6 months, repeated small foot surgeries were required in 7.3% (3 patients) of patients from the study group and in 20% (4 patients) of patients from the control group. Six months after discharge, the weightbearing function of the foot was preserved in all the patients from the study group available for follow-up and in 85% of the patients from the control group. Conclusion: The results of the study demonstrate the positive corrective effects of endovascular interventions, stenting, and balloon angioplasty on the clinical course of ischemic and neuroischemic forms of DFS.

How patients interpret early signs of foot problems and reasons for delays in care: Findings from interviews with patients who have undergone toe amputations

Aims

To describe how patients respond to early signs of foot problems and the factors that result in delays in care.

Methods

Semi-structured interviews were conducted with a large sample of Veterans from across the United States with diabetes mellitus who had undergone a toe amputation. Data were analyzed using inductive content analysis.

Results

We interviewed 61 male patients. Mean age was 66 years, 41% were married, and 37% had a high school education or less. The patient-level factors related to delayed care included: 1) not knowing something was wrong, 2) misinterpreting symptoms, 3) “sudden” and “unexpected” illness progression, and 4) competing priorities getting in the way of care-seeking. The system-level factors included: 5) asking patients to watch it, 6) difficulty getting the right type of care when needed, and 7) distance to care and other transportation barriers.

Conclusion

A confluence of patient factors (e.g., not examining their feet regularly or thoroughly and/or not acting quickly when they noticed something was wrong) and system factors (e.g., absence of a mechanism to support patient’s appraisal of symptoms, lack of access to timely and convenient-located appointments) delayed care. Identifying patient- and system-level interventions that can shorten or eliminate care delays could help reduce rates of limb loss.