Area of the diabetic ulcers estimated applying a foot scanner-based home telecare system and three reference methods

Data-driven digital health technologies in the remote clinical care of diabetic foot ulcers: a scoping review

Background

The availability and effectiveness of Digital Health Technologies (DHTs) to support clinicians, empower patients, and generate economic savings for national healthcare systems are growing rapidly. Of particular promise is the capacity of DHTs to autonomously facilitate remote monitoring and treatment. Diabetic Foot Ulcers (DFUs) are characterised by high rates of infection, amputation, mortality, and healthcare costs. With clinical outcomes contingent on activities that can be readily monitored, DFUs present a promising focus for the application of remote DHTs.

Objective

This scoping review has been conducted as a first step toward ascertaining fthe data-related challenges and opportunities for the development of more comprehensive, integrated, and individualised sense/act DHTs. We review the latest developments in the application of DHTs to the remote care of DFUs. We cover the types of DHTs in development and their features, technological readiness, and scope of clinical testing.

Eligibility criteria

Only peer-reviewed original experimental and observational studies, case series and qualitative studies were included in literature searches. All reviews and manuscripts presenting pre-trial prototype technologies were excluded.

Methods

An initial search of three databases (Web of Science, MEDLINE, and Scopus) generated 1,925 English-language papers for screening. 388 papers were assessed as eligible for full-text screening by the review team. 81 manuscripts were found to meet the eligibility criteria.

Results

Only 19% of studies incorporated multiple DHTs. We categorised 56% of studies as 'Treatment-Manual', i.e. studies involving technologies aimed at treatment requiring manual data generation, and 26% as 'Prevention-Autonomous', i.e. studies of technologies generating data autonomously through wearable sensors aimed at ulcer prevention through patient behavioural change. Only 10% of studies involved more ambitious 'Treatment-Autonomous' interventions. We found that studies generally reported high levels of patient adherence and satisfaction.

Conclusions

Our findings point to a major potential role for DHTs in remote personalised medical management of DFUs. However, larger studies are required to assess their impact. Here, we see opportunities for developing much larger, more comprehensive, and integrated monitoring and decision support systems with the potential to address the disease in a more complete context by capturing and integrating data from multiple sources from subjective and objective measurements.

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.

Digital Planimetry With a New Adaptive Calibration Procedure Results in Accurate and Precise Wound Area Measurement at Curved Surfaces

BACKGROUND

The purpose of this study was to determine the accuracy of wound area measurement at a curved surface using a digital planimetry (DP) with the newly proposed adaptive calibration.

METHODS

Forty wound shapes were printed and placed at the side surfaces of cylinders with diameters of 9.4 and 6.2 cm. Area measurements were carried out using a commercial device SilhouetteMobile (Aranz, New Zealand) and the planimetric app Planimator. Planimetric area measurements were carried out using 2 one-dimensional calibration markers placed above and below the wound shape. The method of adaptive calibration for DP was described. Reference area values of wound shapes were obtained by pixel counting on digital scans made with an optical scanner. Relative errors (REs) and relative differences (RDs) for area measurements were analyzed.

RESULTS

The median of REs for the DP with adaptive calibration (DPwAC) was equal to 0.60% and was significantly smaller than the median for the SilhouetteMobile device (SMD) (2.65%), and significantly smaller than the median for the DP (2.23%). The SD of RDs for the DPwAC of 0.87% was considerably lower than for the SMD (6.45%), and for the DP without adaptive calibration (2.51%). The mean of RDs for the DPwAC (0.082%) was not significantly different from zero, which means that the systematic error was not present for the DPwAC.

CONCLUSIONS

The use of the adaptive calibration in DP to measure the areas at curved surface resulted in a significant increase of accuracy and precision, and removal of systematic error. The DPwAC revealed 4.4 times lower error and 7.4 times higher precision of area measurement at curved surfaces than the SMD.

Telehealth and telemedicine applications for the diabetic foot: A systematic review

The aim of this systematic review is to assess the peer-reviewed literature on the psychometric properties, feasibility, effectiveness, costs, and current limitations of using telehealth and telemedicine approaches for prevention and management of diabetic foot disease. MEDLINE/PubMed was searched for peer-reviewed studies on telehealth and telemedicine approaches for assessing, monitoring, preventing, or treating diabetic foot disease. Four modalities were formulated: dermal thermography, hyperspectral imaging, digital photographic imaging, and audio/video/online communication. Outcome measures were: validity, reliability, feasibility, effectiveness, and costs. Sixty-one studies were eligible for analysis. Three randomized controlled trials showed that handheld infrared dermal thermography as home-monitoring tool is effective in reducing ulcer recurrence risk, while one small trial showed no effect. Hyperspectral imaging has been tested in clinical settings to assess and monitor foot disease and conflicting results on its diagnostic use show that this method is still in an experimental stage. Digital photography is used to assess and monitor foot ulcers and pre-ulcerative lesions and was found to be a valid, reliable, and feasible method for telehealth purposes. Audio/video/online communication is mainly used for foot ulcer monitoring. Two randomized controlled trials show similar healing efficacy compared with regular outpatient clinic visits, but no benefit in costs. In conclusion, several technologies with good psychometric properties are available that may be of benefit in helping to assess, monitor, prevent, or treat diabetic foot disease, but in most cases, feasibility, effectiveness, and cost savings still need to be demonstrated to become accepted and used modalities in diabetic foot care.

Ways to increase precision and accuracy of wound area measurement using smart devices: Advanced app Planimator

Introduction

Wound surface area measurement is important as therapeutic decisions may depend on the change of wound surface area over time. Digital planimetry is a popular technique in wound area measurement. It is accurate and repeatable when calibration is performed with 2 rulers placed at opposite sides of a wound. The aim of the current study was improving accuracy and precision of wound area measurement using capabilities of smart devices.

Methods

The correction of area measurement based on calculated camera tilt angle and the calculation of calibration coefficient of linear dimensions as weighted average were proposed. These and other improvements were applied in the Planimator app for Android, which was then used in the study. Accuracy and precision of the Planimator app were compared to the Visitrak device, the SilhouetteMobile device, the AreaMe software, and to the digital planimetry based on 2-ruler calibration with pictures taken by the smartphone, compact, and D-SLR cameras. Areas of 40 wound shapes of area ranged from 0.14 to 31.72 cm² were measured with each device. Medians of relative errors (REs) were compared in the accuracy tests and standard deviations (SDs) of relative differences (RDs) were compared in the tests of precision.

Results

The median of REs for the Planimator app was not significantly different from the medians of REs for the digital planimetry based on pictures from the compact or D-SLR cameras, but it was significantly lower than the medians of REs for the Visitrak and SilhouetteMobile devices, the AreaMe software and the digital planimetry based on pictures from a smartphone camera. The SD of RDs for the Planimator app was not significantly different from the SDs of RDs for the digital planimetry based on pictures from the compact or D-SLR cameras, but it was significantly lower than the SDs of RDs for the Visitrak and SilhouetteMobile devices, the AreaMe software and the digital planimetry based on pictures from a smartphone camera. The Planimator app installed at a smartphone revealed to be 2-fold more accurate and 1.5-fold more precise than the measurements with using ImageJ software based on pictures taken with the same smartphone.

Conclusions

The Planimator app occurred to have the same accuracy and precision as measurements with digital planimetry with 2-ruler calibration and based on pictures from a compact camera or a D-SLR camera. This app showed better accuracy and precision than the Visitrak and SilhouetteMobile devices, the AreaMe software and the digital planimetry based on pictures from a smartphone camera.

The validity and reliability of remote diabetic foot ulcer assessment using mobile phone images

Despite their potential for telemedicine in diabetic foot ulcer treatment, diagnostic accuracy of assessment of diabetic foot ulcers using mobile phone images is unknown. Our aim was to determine the validity and reliability of remote diabetic foot ulcer assessment using mobile phone images. Fifty diabetic foot ulcers were assessed live and photographed. Five independent observers remotely assessed the mobile phone images twice for presence of nine clinical characteristics and three treatment decisions. Positive likelihood (LLR+) and negative likelihood (LLR−) ratios were calculated for validity. Multirater Randolph’s and bi-rater Bennet kappa values were calculated for reliability. LLR+ ranged from 1.3–4.2; LLR− ranged from 0.13–0.88; the treatment decision ‘peri-wound debridement’ was the only item with ‘strong diagnostic evidence’. Inter-observer reliability kappa ranged from 0.09–0.71; test-retest reliability from 0.45–0.86; the treatment decision ‘peri-wound debridement’ was the only item with ‘adequate agreement’. In conclusion, mobile phone images had low validity and reliability for remote assessment of diabetic foot ulcers and should not be used as a stand-alone diagnostic instrument. Clinicians who use mobile phone images in clinical practice should obtain as much additional information as possible when making treatment decisions based on these images, and be cautious of the low diagnostic accuracy.

A study of the utility and equivalency of 2 methods of wound measurement: digitized tracing versus digital photography

OBJECTIVE

To examine agreement between digitized tracing and digital photography methods in measuring wound area and healing rate, and to compare and contrast the 2 methods on feasibility and utility in patient care and research settings.

SETTING

Toronto Rehabilitation Institute, University Health Network, Toronto, Ontario, Canada.

PARTICIPANTS

A total of 20 subjects aged 18 years or older with a spinal cord injury and pressure ulcers that were Stage II or higher, and who had received in- or outpatient wound care at the hospital for at least 3 consecutive weeks.

METHODS

Wound area was measured at weekly intervals. One assessor calculated wound area from a digitized tracing. A second assessor calculated wound area using a wound photograph. Both assessors used Image-J software. The 2 methods were compared for differences in weekly wound area and weekly healing rate.

RESULTS

Methods were different for wound area (P < .0001), whereas there was no difference between methods in weekly healing rate (P = .9429).

CONCLUSIONS

The 2 methods are in agreement on the important parameter of healing rate. Both methods are feasible in clinical settings. Wound photography may be more useful than digitized tracings because it simultaneously captures wound appearance.

Role of telehealth in diabetic foot ulcer management - A systematic review

OBJECTIVES

To review the use of telehealth in subjects with diabetic foot ulcer; evaluating its clinical outcomes, diagnostic accuracy, cost-effectiveness and behavioural perceptions.

DESIGN

Systematic review.

SETTING

Selected studies were conducted in Australia, USA, the Netherlands, Denmark, Poland and UK.

PARTICIPANTS

A total of 948 identified studies were evaluated against the inclusion criteria. Eleven eligible studies were included for review. Patients with diabetic foot ulcer had to have telehealth guided management.

MAIN OUTCOME MEASURES

Telehealth systems were evaluated against at least one of the following: clinical implications on ulcer healing and disease prognosis; diagnostic accuracy; cost-effectiveness; behavioural perceptions among health professionals or patients.

RESULT

Eleven eligible studies were included for review. Studies that evaluated telehealth against clinical outcomes were underpowered by study design, sample sizes and short duration follow-up. Telehealth systems demonstrated good intra- and inter-observer reproducibility, high diagnostic accuracy and agreement with live assessments. Authors rationalised the cost-effectiveness of their respective telehealth systems, but could not support this with long-term cost analysis. Both patient and health professionals responded positively towards telehealth in surveys and face-to-face interviews.

CONCLUSION

Telehealth yields high diagnostic accuracy, reproducibility and positive behavioural perceptions. However, it is not clear if telehealth use in diabetic foot management has favourable clinical and economic outcomes. More long-term prospective controlled trials on larger populations are needed to further characterise our findings.

Wound Area Measurement with Digital Planimetry: Improved Accuracy and Precision with Calibration Based on 2 Rulers

Introduction

In the treatment of chronic wounds the wound surface area change over time is useful parameter in assessment of the applied therapy plan. The more precise the method of wound area measurement the earlier may be identified and changed inappropriate treatment plan. Digital planimetry may be used in wound area measurement and therapy assessment when it is properly used, but the common problem is the camera lens orientation during the taking of a picture. The camera lens axis should be perpendicular to the wound plane, and if it is not, the measured area differ from the true area.

Results

Current study shows that the use of 2 rulers placed in parallel below and above the wound for the calibration increases on average 3.8 times the precision of area measurement in comparison to the measurement with one ruler used for calibration. The proposed procedure of calibration increases also 4 times accuracy of area measurement. It was also showed that wound area range and camera type do not influence the precision of area measurement with digital planimetry based on two ruler calibration, however the measurements based on smartphone camera were significantly less accurate than these based on D-SLR or compact cameras. Area measurement on flat surface was more precise with the digital planimetry with 2 rulers than performed with the Visitrak device, the Silhouette Mobile device or the AreaMe software-based method.

Conclusion

The calibration in digital planimetry with using 2 rulers remarkably increases precision and accuracy of measurement and therefore should be recommended instead of calibration based on single ruler.

Methods to assess area and volume of wounds - a systematic review

Wound measurement is important in monitoring the healing process of chronic wounds and in evaluating the effect of treatment. The objective of this systematic review was to evaluate evidence from the literature on accuracy, agreement, reliability and feasibility of wound measurement techniques described since 1994. Studies were identified by searching the electronic databases PubMed, Embase and Cochrane Library. Of the 12 013 studies identified, 43 were included in the review. A total of 30 papers evaluated techniques for measuring wound area and 13 evaluated techniques for measuring wound volume. The six approaches for measuring wound area were simple ruler method (10 papers), mathematical models (5 papers), manual planimetry (10 papers), digital planimetry (16 papers), stereophotogrammetry (2 papers) and digital imaging method (20 papers). Of these studies, 10 evaluated accuracy, 15 agreement, 17 reliability and 25 mentioned feasibility. The number of wounds examined in the studies was highly variable (n = 3-260). Studies evaluating techniques for measuring wound volume included between 1 and 50 wounds and evaluated accuracy (4 studies), agreement (6 studies), reliability (8 studies) and feasibility (12 studies). Digital planimetry and digital imaging were considered the most accurate and reliable methods for area measurement, particularly in larger and irregularly shaped wounds. None of the three-dimensional technologies have so far had a major impact, because of their low accuracy, high cost and complexity in handling the system set-up.

Assessment of signs of foot infection in diabetes patients using photographic foot imaging and infrared thermography

BACKGROUND

Patients with diabetic foot disease require frequent screening to prevent complications and may be helped through telemedical home monitoring. Within this context, the goal was to determine the validity and reliability of assessing diabetic foot infection using photographic foot imaging and infrared thermography.

SUBJECTS AND METHODS

For 38 patients with diabetes who presented with a foot infection or were admitted to the hospital with a foot-related complication, photographs of the plantar foot surface using a photographic imaging device and temperature data from six plantar regions using an infrared thermometer were obtained. A temperature difference between feet of >2.2 °C defined a "hotspot." Two independent observers assessed each foot for presence of foot infection, both live (using the Perfusion-Extent-Depth-Infection-Sensation classification) and from photographs 2 and 4 weeks later (for presence of erythema and ulcers). Agreement in diagnosis between live assessment and (the combination of ) photographic assessment and temperature recordings was calculated.

RESULTS

Diagnosis of infection from photographs was specific (>85%) but not very sensitive (<60%). Diagnosis based on hotspots present was sensitive (>90%) but not very specific (<25%). Diagnosis based on the combination of photographic and temperature assessments was both sensitive (>60%) and specific (>79%). Intra-observer agreement between photographic assessments was good (Cohen's κ=0.77 and 0.52 for both observers).

CONCLUSIONS

Diagnosis of foot infection in patients with diabetes seems valid and reliable using photographic imaging in combination with infrared thermography. This supports the intended use of these modalities for the home monitoring of high-risk patients with diabetes to facilitate early diagnosis of signs of foot infection.

Validation of a laser-assisted wound measurement device for measuring wound volume

BACKGROUND

Accurate and precise wound measurement is an essential part of the medical record when monitoring a patient with a chronic wound. This study was designed to determine if a new device, a laser-assisted wound measurement (LAWM) device, provides valid measurements for wound area, depth, and volume.

METHODS

We compared four methods to evaluate the area and volume of 12 wounds of differing size and depth that were created on the dorsum of a sacrificed pig. We evaluated the LAWM device, digital photograph assessment with National Institutes of Health ImageJ software, measurements of depth with a ruler, and weight-to-volume assessment with dental paste. We then sought to cross validate this data with further analyses obtained from these measurements using a Play-Doh®-based wound as a model for constant area with different depths.

RESULTS

We demonstrate that the LAWM device measures wound area accurately. Depth (and therefore volume) measurements, however, are artificially low. This inaccuracy is the same for shallow and deep wounds.

CONCLUSIONS

The inaccuracy in the depth and volume measurements with the LAWM device results in an artificially low measurement. However, this may not affect percentage difference measurements. Further studies will need to be performed to determine if this device can accurately determine wound changes in the clinical setting.

Accuracy and precision of selected wound area measurement methods in diabetic foot ulceration

AIM

The present study assesses precision and accuracy of four selected methods of wound area measurements in diabetic foot wounds.

MATERIALS AND METHODS

The areas of 16 wound shapes were measured using linear measurement with elliptical estimation (Elliptical method), using the Visitrak™ (Smith & Nephew, London, United Kingdom) device, the SilhouetteMobile™ device (ARANZ Medical Ltd., Christchurch, New Zealand), and the TeleDiaFoS system (Nalecz Institute of Biocybernetics and Biomedical Engineering, Warsaw, Poland). The actual area of a wound shape was determined with a tested scanner and specifically developed software. Accuracy of the area measurement method was assessed by the relative error (RE), whereas precision was assessed by the coefficient of variation (CV).

RESULTS

The overall absolute REs were 13.3%, 6.8%, 2.1%, and 2.3% for the Elliptical method, the Visitrak device, the TeleDiaFoS system, and the SilhouetteMobile device, respectively. The accuracy of the Visitrak device was remarkably reduced for wound areas smaller than 2 cm². The overall CVs were 6.0%, 6.3%, 1.6%, and 3.1% for the Elliptical method, the Visitrak device, the TeleDiaFoS system, and the SilhouetteMobile device, respectively. The precision of the Visitrak device was revealed to be remarkably lower for small wounds (<2 cm²).

CONCLUSIONS

The Elliptical method gives overestimation up to 33%; thus, it should not be used in applications where the actual wound area is an important parameter (like the prediction of wound healing). The TeleDiaFoS system and the SilhouetteMobile device showed the best accuracy of all used methods; however, the precision of the TeleDiaFoS system was revealed to be higher than the precision of the SilhouetteMobile device. The accuracy and the precision of the Visitrak device are significantly reduced for wounds smaller than 2 cm².