Artificial Intelligence Methodologies Applied to Technologies for Screening, Diagnosis and Care of the Diabetic Foot: A Narrative Review

Diabetic Foot Ulcers in Geriatric Patients

Care for the patient with diabetic foot ulcers (DFUs) entails understanding the epidemiology, pathophysiology, and a systematic approach to diagnosis and treatment. The authors will review elements of DFU in geriatric patients including the pathophysiology of diabetes, epidemiology and management of DFU in the context of developing a Plan for Healing. The authors will discuss comprehensive principles of a Plan for Healing, which applies to all aspects of chronic wounds.

GLI family zinc finger protein 2 promotes skin fibroblast proliferation and DNA damage repair by targeting the miR-200/ataxia telangiectasia mutated axis in diabetic wound healing

Diabetic foot ulcer (DFU) is a serious complication of diabetic patients which negatively affects their foot health. This study aimed to estimate the role and mechanism of the miR-200 family in DNA damage of diabetic wound healing. Human foreskin fibroblasts (HFF-1 cells) were stimulated with high glucose (HG). Db/db mice were utilized to conduct the DFU in vivo model. Cell viability was evaluated using 3-(4,5-dimethyl-2-thiazolyl)-2,5-diphenyl-2-H-tetrazolium bromide assays. Superoxide dismutase activity was determined using detection kits. Reactive oxygen species determination was conducted via dichlorodihydrofluorescein-diacetate assays. Enzyme-linked immunosorbent assay was used to evaluate 8-oxo-7,8-dihydro-2'deoxyguanosine levels. Genes and protein expression were analyzed by quantitative real-time polymerase chain reaction, western blotting, or immunohistochemical analyses. Luciferase reporter gene and RNA immunoprecipitation assays determined the interaction with miR-200a/b/c-3p and GLI family zinc finger protein 2 (GLI2) or ataxia telangiectasia mutated (ATM) kinase. HG repressed cell proliferation and DNA damage repair, promoted miR-200a/b/c-3p expression, and suppressed ATM and GLI2. MiR-200a/b/c-3p inhibition ameliorated HG-induced cell proliferation and DNA damage repair repression. MiR-200a/b/c-3p targeted ATM. Then, the silenced ATM reversed the miR-200a/b/c-3p inhibition-mediated alleviative effects under HG. Next, GLI2 overexpression alleviated the HG-induced cell proliferation and DNA damage repair inhibition via miR-200a/b/c-3p. MiR-200a/b/c-3p inhibition significantly promoted DNA damage repair and wound healing in DFU mice. GLI2 promoted cell proliferation and DNA damage repair by regulating the miR-200/ATM axis to enhance diabetic wound healing in DFU.

The role of machine learning in advancing diabetic foot: a review

Background

Diabetic foot complications impose a significant strain on healthcare systems worldwide, acting as a principal cause of morbidity and mortality in individuals with diabetes mellitus. While traditional methods in diagnosing and treating these conditions have faced limitations, the emergence of Machine Learning (ML) technologies heralds a new era, offering the promise of revolutionizing diabetic foot care through enhanced precision and tailored treatment strategies.

Objective

This review aims to explore the transformative impact of ML on managing diabetic foot complications, highlighting its potential to advance diagnostic accuracy and therapeutic approaches by leveraging developments in medical imaging, biomarker detection, and clinical biomechanics.

Methods

A meticulous literature search was executed across PubMed, Scopus, and Google Scholar databases to identify pertinent articles published up to March 2024. The search strategy was carefully crafted, employing a combination of keywords such as "Machine Learning," "Diabetic Foot," "Diabetic Foot Ulcers," "Diabetic Foot Care," "Artificial Intelligence," and "Predictive Modeling." This review offers an in-depth analysis of the foundational principles and algorithms that constitute ML, placing a special emphasis on their relevance to the medical sciences, particularly within the specialized domain of diabetic foot pathology. Through the incorporation of illustrative case studies and schematic diagrams, the review endeavors to elucidate the intricate computational methodologies involved.

Results

ML has proven to be invaluable in deriving critical insights from complex datasets, enhancing both the diagnostic precision and therapeutic planning for diabetic foot management. This review highlights the efficacy of ML in clinical decision-making, underscored by comparative analyses of ML algorithms in prognostic assessments and diagnostic applications within diabetic foot care.

Conclusion

The review culminates in a prospective assessment of the trajectory of ML applications in the realm of diabetic foot care. We believe that despite challenges such as computational limitations and ethical considerations, ML remains at the forefront of revolutionizing treatment paradigms for the management of diabetic foot complications that are globally applicable and precision-oriented. This technological evolution heralds unprecedented possibilities for treatment and opportunities for enhancing patient care.

Prediction model for lower limb amputation in hospitalized diabetic foot patients using classification and regression trees

BACKGROUND

The decision to perform amputation of a limb in a patient with diabetic foot ulcer (DFU) is not an easy task. Prediction models aim to help the surgeon in decision making scenarios. Currently there are no prediction model to determine lower limb amputation during the first 30 days of hospitalization for patients with DFU.

METHODS

Classification And Regression Tree analysis was applied on data from a retrospective cohort of patients hospitalized for the management of diabetic foot ulcer, using an existing database from two Orthopaedics and Traumatology departments. The secondary analysis identified independent variables that can predict lower limb amputation (mayor or minor) during the first 30 days of hospitalization.

RESULTS

Of the 573 patients in the database, 290 feet underwent a lower limb amputation during the first 30 days of hospitalization. Six different models were developed using a loss matrix to evaluate the error of not detecting false negatives. The selected tree produced 13 terminal nodes and after the pruning process, only one division remained in the optimal tree (Sensitivity: 69%, Specificity: 75%, Area Under the Curve: 0.76, Complexity Parameter: 0.01, Error: 0.85). Among the studied variables, the Wagner classification with a cut-off grade of 3 exceeded others in its predicting capacity.

CONCLUSIONS

Wagner classification was the variable with the best capacity for predicting amputation within 30 days. Infectious state and vascular occlusion described indirectly by this classification reflects the importance of taking quick decisions in those patients with a higher compromise of these two conditions. Finally, an external validation of the model is still required.

LEVEL OF EVIDENCE

III.

State-of-the-Art Features for Early-Stage Detection of Diabetic Foot Ulcers Based on Thermograms

Diabetic foot ulcers represent the most frequently recognized and highest risk factor among patients affected by diabetes mellitus. The associated recurrent rate is high, and amputation of the foot or lower limb is often required due to infection. Analysis of infrared thermograms covering the entire plantar aspect of both feet is considered an emerging area of research focused on identifying at an early stage the underlying conditions that sustain skin and tissue damage prior to the onset of superficial wounds. The identification of foot disorders at an early stage using thermography requires establishing a subset of relevant features to reduce decision variability and data misinterpretation and provide a better overall cost-performance for classification. The lack of standardization among thermograms as well as the unbalanced datasets towards diabetic cases hinder the establishment of this suitable subset of features. To date, most studies published are mainly based on the exploitation of the publicly available INAOE dataset, which is composed of thermogram images of healthy and diabetic subjects. However, a recently released dataset, STANDUP, provided data for extending the current state of the art. In this work, an extended and more generalized dataset was employed. A comparison was performed between the more relevant and robust features, previously extracted from the INAOE dataset, with the features extracted from the extended dataset. These features were obtained through state-of-the-art methodologies, including two classical approaches, lasso and random forest, and two variational deep learning-based methods. The extracted features were used as an input to a support vector machine classifier to distinguish between diabetic and healthy subjects. The performance metrics employed confirmed the effectiveness of both the methodology and the state-of-the-art features subsequently extracted. Most importantly, their performance was also demonstrated when considering the generalization achieved through the integration of input datasets. Notably, features associated with the MCA and LPA angiosomes seemed the most relevant.

Sleep disturbance exacerbates atherosclerosis in type 2 diabetes mellitus

Background

Short sleep duration and poor sleep quality are important risk factors for atherosclerosis. The use of smart bracelets that measure sleep parameters, such as sleep stage, can help determine the effect of sleep quality on lower-extremity atherosclerosis in patients with type 2 diabetes.

Objective

To investigate the correlation between sleep disorders and lower-extremity atherosclerosis in patients with type 2 diabetes.

Methods

After admission, all patients were treated with lower-extremity arterial ultrasound and graded as having diabetic lower-extremity vascular lesions according to the results. A smart bracelet was used to obtain the patient sleep data. The correlation between sleep patterns and diabetic lower-extremity atherosclerosis, diabetic foot, and various metabolic indices was verified.

Results

Between August 2021 and April 2022, we screened 100 patients with type 2 diabetes, with 80 completing sleep monitoring. Univariate ordered logistic regression analysis indicated that patients with a sleep score below 76 (OR = 2.707, 95%CI: 1.127-6.488), shallow sleep duration of 5.3 h or more (OR=3.040, 95 CI: 1.005-9.202), wakefulness at night of 2.6 times or more (OR = 4.112, 95%CI: 1.513-11.174), and a deep sleep continuity score below 70 (OR = 4.141, 95%CI: 2.460-615.674) had greater risk of high-grade lower limb atherosclerosis. Multivariate ordinal logistic regression analysis revealed that the risk of high-grade lower limb atherosclerosis was higher in patients with 2.6 or more instances of nighttime wakefulness (OR = 3.975, 95%CI: 1.297-12.182) compared with those with fewer occurrences. The sleep duration curve of patients with different grades of diabetic lower-extremity atherosclerosis was U-shaped. According to the results of the one-way analysis of variance, the higher the deep sleep continuity score, the lower the Wagner scale score for diabetic foot (P < 0.05).

Conclusions

Sleep disorders (long, shallow sleep duration, frequent wakefulness at night, and poor continuity of deep sleep) can worsen lower limb atherosclerosis in patients with type 2 diabetes. This finding can provide a new method for medical professionals to prevent and treat diabetic lower-extremity vascular lesions.

Development of Patient-Reported Outcome Scale for Patients with Diabetic Foot and Its Reliability and Validity Test

Objective

To construct a self-reported outcome scale for diabetic foot patients, and to test its reliability and validity.

Methods

Through literature reading and interviews with 30 patients, a pool of scale items was formed. The items were classified and sorted out according to the expected scale structure framework. After two rounds of expert consultation and a small range of test dressing, the initial scale was formed. Through the investigation of 85 patients with diabetic foot, item differentiation analysis, correlation analysis and exploratory factor analysis were used to screen the items. Cronbach's α coefficient, retest reliability and content and structure validity analysis were used to determine the feasibility and validity of the scale.

Results

The final scale included 4 first-level items and 22 second-level items. The critical ratio method showed that the scores of each item in the high group and the low group were significantly different (P < 0.05). Correlation analysis showed that the correlation coefficient between each item and the total score was 0.431 to 0.829; The content validity index of the scale was 0.91, the exploratory factor analysis identified three common factors, and the cumulative variance contribution rate was 75.381%. The confirmatory factor analysis showed that the model fit well. The Cronbach's α coefficient of the scale was 0.934 and the retest reliability coefficient was 0.926.

Conclusion

The self-reported outcome scale for diabetic foot patients has good reliability and validity, and can be used to investigate the health status of diabetic foot patients and evaluate the therapeutic effect.

Empowering Foot Health: Harnessing the Adaptive Weighted Sub-Gradient Convolutional Neural Network for Diabetic Foot Ulcer Classification

In recent times, DFU (diabetic foot ulcer) has become a universal health problem that affects many diabetes patients severely. DFU requires immediate proper treatment to avert amputation. Clinical examination of DFU is a tedious process and complex in nature. Concurrently, DL (deep learning) methodologies can show prominent outcomes in the classification of DFU because of their efficient learning capacity. Though traditional systems have tried using DL-based models to procure better performance, there is room for enhancement in accuracy. Therefore, the present study uses the AWSg-CNN (Adaptive Weighted Sub-gradient Convolutional Neural Network) method to classify DFU. A DFUC dataset is considered, and several processes are involved in the present study. Initially, the proposed method starts with pre-processing, excluding inconsistent and missing data, to enhance dataset quality and accuracy. Further, for classification, the proposed method utilizes the process of RIW (random initialization of weights) and log softmax with the ASGO (Adaptive Sub-gradient Optimizer) for effective performance. In this process, RIW efficiently learns the shift of feature space between the convolutional layers. To evade the underflow of gradients, the log softmax function is used. When logging softmax with the ASGO is used for the activation function, the gradient steps are controlled. An adaptive modification of the proximal function simplifies the learning rate significantly, and optimal proximal functions are produced. Due to such merits, the proposed method can perform better classification. The predicted results are displayed on the webpage through the HTML, CSS, and Flask frameworks. The effectiveness of the proposed system is evaluated with accuracy, recall, F1-score, and precision to confirm its effectual performance.

Innovative Functional Biomaterials as Therapeutic Wound Dressings for Chronic Diabetic Foot Ulcers

The imbalance of local and systemic factors in individuals with diabetes mellitus (DM) delays, or even interrupts, the highly complex and dynamic process of wound healing, leading to diabetic foot ulceration (DFU) in 15 to 25% of cases. DFU is the leading cause of non-traumatic amputations worldwide, posing a huge threat to the well-being of individuals with DM and the healthcare system. Moreover, despite all the latest efforts, the efficient management of DFUs still remains a clinical challenge, with limited success rates in treating severe infections. Biomaterial-based wound dressings have emerged as a therapeutic strategy with rising potential to handle the tricky macro and micro wound environments of individuals with DM. Indeed, biomaterials have long been related to unique versatility, biocompatibility, biodegradability, hydrophilicity, and wound healing properties, features that make them ideal candidates for therapeutic applications. Furthermore, biomaterials may be used as a local depot of biomolecules with anti-inflammatory, pro-angiogenic, and antimicrobial properties, further promoting adequate wound healing. Accordingly, this review aims to unravel the multiple functional properties of biomaterials as promising wound dressings for chronic wound healing, and to examine how these are currently being evaluated in research and clinical settings as cutting-edge wound dressings for DFU management.

Feature Ranking by Variational Dropout for Classification Using Thermograms from Diabetic Foot Ulcers

Diabetes mellitus presents a high prevalence around the world. A common and long-term derived complication is diabetic foot ulcers (DFUs), which have a global prevalence of roughly 6.3%, and a lifetime incidence of up to 34%. Infrared thermograms, covering the entire plantar aspect of both feet, can be employed to monitor the risk of developing a foot ulcer, because diabetic patients exhibit an abnormal pattern that may indicate a foot disorder. In this study, the publicly available INAOE dataset composed of thermogram images of healthy and diabetic subjects was employed to extract relevant features aiming to establish a set of state-of-the-art features that efficiently classify DFU. This database was extended and balanced by fusing it with private local thermograms from healthy volunteers and generating synthetic data via synthetic minority oversampling technique (SMOTE). State-of-the-art features were extracted using two classical approaches, LASSO and random forest, as well as two variational deep learning (DL)-based ones: concrete and variational dropout. Then, the most relevant features were detected and ranked. Subsequently, the extracted features were employed to classify subjects at risk of developing an ulcer using as reference a support vector machine (SVM) classifier with a fixed hyperparameter configuration to evaluate the robustness of the selected features. The new set of features extracted considerably differed from those currently considered state-of-the-art but provided a fair performance. Among the implemented extraction approaches, the variational DL ones, particularly the concrete dropout, performed the best, reporting an F1 score of 90% using the aforementioned SVM classifier. In comparison with features previously considered as the state-of-the-art, approximately 15% better performance was achieved for classification.