The Diabetic Foot

Predicting the diabetic foot in the population of type 2 diabetes mellitus from tongue images and clinical information using multi-modal deep learning

Aims

Based on the quantitative and qualitative fusion data of traditional Chinese medicine (TCM) and Western medicine, a diabetic foot (DF) prediction model was established through combining the objectified parameters of TCM and Western medicine.

Methods

The ResNet-50 deep neural network (DNN) was used to extract depth features of tongue demonstration, and then a fully connected layer (FCL) was used for feature extraction to obtain aggregate features. Finally, a non-invasive DF prediction model based on tongue features was realized.

Results

Among the 391 patients included, there were 267 DF patients, with their BMI (25.2 vs. 24.2) and waist-to-hip ratio (0.953 vs. 0.941) higher than those of type 2 diabetes mellitus (T2DM) group. The diabetes (15 years vs. 8 years) and hypertension durations (10 years vs. 7.5 years) in DF patients were significantly higher than those in T2DM group. Moreover, the plantar hardness in DF patients was higher than that in T2DM patients. The accuracy and sensitivity of the multi-mode DF prediction model reached 0.95 and 0.9286, respectively.

Conclusion

We established a DF prediction model based on clinical features and objectified tongue color, which showed the unique advantages and important role of objectified tongue demonstration in the DF risk prediction, thus further proving the scientific nature of TCM tongue diagnosis. Based on the qualitative and quantitative fusion data, we combined tongue images with DF indicators to establish a multi-mode DF prediction model, in which tongue demonstration and objectified foot data can correct the subjectivity of prior knowledge. The successful establishment of the feature fusion diagnosis model can demonstrate the clinical practical value of objectified tongue demonstration. According to the results, the model had better performance to distinguish between T2DM and DF, and by comparing the performance of the model with and without tongue images, it was found that the model with tongue images performed better.

Research progress of SIRTs activator resveratrol and its derivatives in autoimmune diseases

Autoimmune diseases (AID) have emerged as prominent contributors to disability and mortality worldwide, characterized by intricate pathogenic mechanisms involving genetic, environmental, and autoimmune factors. In response to this challenge, a growing body of research in recent years has delved into genetic modifications, yielding valuable insights into AID prevention and treatment. Sirtuins (SIRTs) constitute a class of NAD-dependent histone deacetylases that orchestrate deacetylation processes, wielding significant regulatory influence over cellular metabolism, oxidative stress, immune response, apoptosis, and aging through epigenetic modifications. Resveratrol, the pioneering activator of the SIRTs family, and its derivatives have captured global scholarly interest. In the context of AID, these compounds hold promise for therapeutic intervention by modulating the SIRTs pathway, impacting immune cell functionality, suppressing the release of inflammatory mediators, and mitigating tissue damage. This review endeavors to explore the potential of resveratrol and its derivatives in AID treatment, elucidating their mechanisms of action and providing a comprehensive analysis of current research advancements and obstacles. Through a thorough examination of existing literature, our objective is to advocate for the utilization of resveratrol and its derivatives in AID treatment while offering crucial insights for the formulation of innovative therapeutic approaches.

Videocapillaroscopy of the Oral Mucosa in Patients with Diabetic Foot: Possible Diagnostic Role of Microangiopathic Damage?

INTRODUCTION

Diabetic foot represents one of the most serious and expensive complications of diabetes and is subject to a high percentage of amputations that are almost always preceded by ulcers ascribable to neuropathy and/or vasculopathy. Videocapillaroscopy (VCS) can be a valuable aid in order to uncover morpho-structural anomalies in the vascular bed, both at the level of the oral mucosa and at the level of the terminal vessels of the lower limb.

MATERIALS AND METHODS

Sixty subjects divided into 4 groups were enrolled: 15 healthy subjects; 15 patients with diabetes for more than 10 years without ulcerative foot lesions; 15 patients with neuropathic diabetic foot (clinical diagnosis, MDNS); 15 patients with ischemic diabetic foot (clinical diagnosis, ABI, lower limb doppler). A complete videocapillaroscopic mapping of the oral mucosa was carried out on each patient. The areas investigated were: labial mucosa, the retro-commissural region of the buccal mucosa, and the vestibular masticatory mucosa (II and V sextant).

RESULTS

The analysis of the morphological and densitometric characteristics of the capillaries revealed the following: a significant reduction in capillary density in neuropathic (mean ± SD 7.32 ± 2.1) and ischemic patients (mean ± SD 4.32 ± 3.2) compared to the control group of patients (both diabetic mean ± SD 12.98 ± 3.1 and healthy mean ± SD 19.04 ± 3.16) (ANOVA test and Bonferroni t test p < 0.05); a reduction in the average length of the capillaries and a significant increase in tortuosity (ANOVA test and Bonferroni t test p < 0.05). In the neuropathic patients, a recurrent capillaroscopic pattern that we defined as "sun" was found, with capillaries arranged radially around an avascular area.

CONCLUSIONS

The data obtained from this preliminary study suggest a potential diagnostic role of oral capillaroscopy in the early and subclinical identification of microangiopathic damage in patients with diabetic foot.

Advancing pharmacotherapy for diabetic foot ulcers

INTRODUCTION

Standard treatment for diabetic foot ulcers (DFUs) includes off-loading, debridement, moisture balance, management of infection and peripheral arterial disease (PAD) as well as adequate glycemic control. The outcomes so far are unsatisfactory.

AREAS COVERED

Herein, the authors provide an outline of newer pharmacological agents for the management of DFUs and give their expert perspectives on future treatment strategies.

EXPERT OPINION

Evidence-based healthcare calls for high quality evidence from large RCTs before the implementation of new guidelines for the management of DFUs. Empagliflozin and liraglutide can be recommended for glucose control in patients with DFUs and PAD, while intensive lipid lowering therapy with evolocumab when primary cholesterol goals are not met could be offered to patients with DFUs. Further clinical studies are warranted to develop a structured algorithm for the treatment of DFUs that fail to heal after four weeks of current standard of care. Sucrose octasulfate dressings, becaplermin gel, and platelet-rich plasma (PRP) could also be considered as advanced treatment options for the management of hard to heal DFUs.