Remote home monitoring to identify and prevent diabetic foot ulceration

Design and Implementation of a Smart Insole System to Measure Plantar Pressure and Temperature

An intelligent insole system may monitor the individual's foot pressure and temperature in real-time from the comfort of their home, which can help capture foot problems in their earliest stages. Constant monitoring for foot complications is essential to avoid potentially devastating outcomes from common diseases such as diabetes mellitus. Inspired by those goals, the authors of this work propose a full design for a wearable insole that can detect both plantar pressure and temperature using off-the-shelf sensors. The design provides details of specific temperature and pressure sensors, circuit configuration for characterizing the sensors, and design considerations for creating a small system with suitable electronics. The procedure also details how, using a low-power communication protocol, data about the individuals' foot pressure and temperatures may be sent wirelessly to a centralized device for storage. This research may aid in the creation of an affordable, practical, and portable foot monitoring system for patients. The solution can be used for continuous, at-home monitoring of foot problems through pressure patterns and temperature differences between the two feet. The generated maps can be used for early detection of diabetic foot complication with the help of artificial intelligence.

A Novel Machine Learning Approach for Severity Classification of Diabetic Foot Complications Using Thermogram Images

Diabetes mellitus (DM) is one of the most prevalent diseases in the world, and is correlated to a high index of mortality. One of its major complications is diabetic foot, leading to plantar ulcers, amputation, and death. Several studies report that a thermogram helps to detect changes in the plantar temperature of the foot, which may lead to a higher risk of ulceration. However, in diabetic patients, the distribution of plantar temperature does not follow a standard pattern, thereby making it difficult to quantify the changes. The abnormal temperature distribution in infrared (IR) foot thermogram images can be used for the early detection of diabetic foot before ulceration to avoid complications. There is no machine learning-based technique reported in the literature to classify these thermograms based on the severity of diabetic foot complications. This paper uses an available labeled diabetic thermogram dataset and uses the k-mean clustering technique to cluster the severity risk of diabetic foot ulcers using an unsupervised approach. Using the plantar foot temperature, the new clustered dataset is verified by expert medical doctors in terms of risk for the development of foot ulcers. The newly labeled dataset is then investigated in terms of robustness to be classified by any machine learning network. Classical machine learning algorithms with feature engineering and a convolutional neural network (CNN) with image-enhancement techniques are investigated to provide the best-performing network in classifying thermograms based on severity. It is found that the popular VGG 19 CNN model shows an accuracy, precision, sensitivity, F1-score, and specificity of 95.08%, 95.08%, 95.09%, 95.08%, and 97.2%, respectively, in the stratification of severity. A stacking classifier is proposed using extracted features of the thermogram, which is created using the trained gradient boost classifier, XGBoost classifier, and random forest classifier. This provides a comparable performance of 94.47%, 94.45%, 94.47%, 94.43%, and 93.25% for accuracy, precision, sensitivity, F1-score, and specificity, respectively.

Thermal Change Index-Based Diabetic Foot Thermogram Image Classification Using Machine Learning Techniques

Diabetes mellitus (DM) can lead to plantar ulcers, amputation and death. Plantar foot thermogram images acquired using an infrared camera have been shown to detect changes in temperature distribution associated with a higher risk of foot ulceration. Machine learning approaches applied to such infrared images may have utility in the early diagnosis of diabetic foot complications. In this work, a publicly available dataset was categorized into different classes, which were corroborated by domain experts, based on a temperature distribution parameter—the thermal change index (TCI). We then explored different machine-learning approaches for classifying thermograms of the TCI-labeled dataset. Classical machine learning algorithms with feature engineering and the convolutional neural network (CNN) with image enhancement techniques were extensively investigated to identify the best performing network for classifying thermograms. The multilayer perceptron (MLP) classifier along with the features extracted from thermogram images showed an accuracy of 90.1% in multi-class classification, which outperformed the literature-reported performance metrics on this dataset.

Guidelines and standards for comprehensive clinical diagnosis and interventional treatment for diabetic foot in China (Issue 7.0)

Diabetic foot (DF) is one of the most common complications of diabetes and is associated with high morbidity, disability, lethality and low cure-rate. The clinical diagnosis and treatment of DF need to be standardized. The Chinese Diabetic Foot Cell and Interventional Therapy Technology Alliance has released six editions of guidelines and standards for clinical diagnosis and interventional treatment of DF, which filled the gap in the domestic DF treatment standard and played an important role in improving the level of diagnosis and treatment in China. In line with the latest developments in diagnosis and treatment, the Alliance, along with other 89 institutions, developed and issued the new edition based on the sixth edition to help standardize the clinical diagnosis and treatment of DF in China.

A machine learning model for early detection of diabetic foot using thermogram images

Diabetes foot ulceration (DFU) and amputation are a cause of significant morbidity. The prevention of DFU may be achieved by the identification of patients at risk of DFU and the institution of preventative measures through education and offloading. Several studies have reported that thermogram images may help to detect an increase in plantar temperature prior to DFU. However, the distribution of plantar temperature may be heterogeneous, making it difficult to quantify and utilize to predict outcomes. We have compared a machine learning-based scoring technique with feature selection and optimization techniques and learning classifiers to several state-of-the-art Convolutional Neural Networks (CNNs) on foot thermogram images and propose a robust solution to identify the diabetic foot. A comparatively shallow CNN model, MobilenetV2 achieved an F1 score of ∼95% for a two-feet thermogram image-based classification and the AdaBoost Classifier used 10 features and achieved an F1 score of 97%. A comparison of the inference time for the best-performing networks confirmed that the proposed algorithm can be deployed as a smartphone application to allow the user to monitor the progression of the DFU in a home setting.

Remote Temperature Monitoring of the Diabetic Foot: From Research to Practice

INTRODUCTION

Diabetic foot ulcers (DFUs) are devastating, common, and costly. The mortality of veterans following a DFU is sobering with ulceration recognized as a significant marker of disease severity. Given the dramatic impact of diabetic foot complications to the veteran and the US health care system, the US Department of Veterans Affairs (VA) has long recognized the importance of preventive care for those at risk. Telemedicine has been suggested as a modality to reach veterans at high risk of chronic wound formation.

OBSERVATIONS

The purpose of this review is to: (1) present the evidence supporting once-daily remote temperature monitoring (RTM), a telemedicine approach critical to improving both veteran access to care and diabetic foot outcomes; (2) summarize a 2017 study published by VA providers who have advanced clinical understanding of RTM; (3) present previously unpublished data from this study comparing high-risk VA and non-VA cohorts, highlighting the opportunity for additional focus on DFU prevention within the VA; and (4) report on recent VA use of a RTM technology based on this research, emphasizing lessons learned and best practices.

CONCLUSIONS

There is a significant opportunity to shift diabetic foot care from treatment to prevention, improving veteran outcomes and reducing resource utilization. RTM is an evidence-based, recommended, but underused telemedicine solution that can catalyze this needed paradigm shift.

Remote Temperature Monitoring in Patients With Visual Impairment Due to Diabetes Mellitus: A Proposed Improvement to Current Standard of Care for Prevention of Diabetic Foot Ulcers

BACKGROUND

Two debilitating sequelae of diabetes are foot ulcerations and vision impairing conditions including retinopathy, open-angle glaucoma, and cataracts. Current standard of care recommends daily visual screening of feet. Despite willingness, many patients are impeded by visual impairment. We investigate whether once-daily remote temperature monitoring can improve self-screening for patients at risk for diabetic foot complications.

METHODS

We followed four male veterans with diabetes mellitus, peripheral neuropathy, impaired visual acuity, and at least one other diabetes-related visual impairment in a high-risk podiatry clinic. Patients received a telemedicine remote temperature monitoring mat and instructed on proper daily use. Each patient developed a "hotspot," defined as a 1.75°C localized temperature difference between matched pedal locations, which resulted in telephone triage outreach.

RESULTS

In three cases, outreach resulted in a sooner appointment where patients were found to have a relevant outcome at the hotspot. Patients in cases 1-3 had University of Texas (UT) 1A ulcerations. The patient in case 4 had inflammation from trauma. All patients had refractive errors plus another vision impairing condition that potentially delayed identification of lesions. Patients in cases 1 and 2 have cataracts, patients in cases 2 and 3 have retinopathy, and patient in case 4 has glaucoma.

CONCLUSIONS

As an adjunct to daily preventative diabetic self-care, once-daily remote temperature monitoring technology can augment self-screening to prompt necessary outreach and treatment and potentially prevent costly and debilitating diabetic foot complications. This case series serves as a pilot study for real-world application of thermometry, where further large-scale research is needed.

Unilateral remote temperature monitoring to predict future ulceration for the diabetic foot in remission

OBJECTIVE

Daily remote foot temperature monitoring is an evidence-based preventive practice for patients at risk for diabetic foot complications. Unfortunately, the conventional approach requires comparison of temperatures between contralaterally matched anatomy, limiting practice in high-risk cohorts such as patients with a wound to one foot and those with proximal lower extremity amputation (LEA). We developed and assessed a novel approach for monitoring of a single foot for the prevention and early detection of diabetic foot complications. The purpose of this study was to assess the sensitivity, specificity, and lead time associated with unilateral diabetic foot temperature monitoring.

RESEARCH DESIGN AND METHODS

We used comparisons among ipsilateral foot temperatures and between foot temperatures and ambient temperature as a marker of inflammation. We analyzed data collected from a 129-participant longitudinal study to evaluate the predictive accuracy of our approach. To evaluate classification accuracy, we constructed a receiver operator characteristic curve and reported sensitivity, specificity, and lead time for four different monitoring settings.

RESULTS

Using this approach, monitoring a single foot was found to predict 91% of impending non-acute plantar foot ulcers on average 41 days before clinical presentation with a resultant mean 4.2 alerts per participant-year. By adjusting the threshold temperature setting, the specificity could be increased to 78% with corresponding reduced sensitivity of 53%, lead time of 33 days, and 2.2 alerts per participant-year.

CONCLUSIONS

Given the high incidence of subsequent diabetic foot complications to the sound foot in patients with a history of proximal LEA and patients being treated for a wound, practice of daily temperature monitoring of a single foot has the potential to significantly improve outcomes and reduce resource utilization in this challenging high-risk population.