Clinical validation of an artificial intelligence‐enabled wound imaging mobile application in diabetic foot ulcers

BACKGROUND Without effective self-care, people with diabetic foot ulcers (DFUs) are at risk of prolonged healing times, hospitalization, amputation, and reduced quality of life. Despite these consequences, adherence to DFU self-care remains low. New strategies are needed to engage people in the self-care of their DFUs. OBJECTIVE We aimed to evaluate the usability and usefulness of a new mobile application to engage people with DFUs in self-care. METHODS We developed a new mobile application, “MyFootCare”, to engage patients with DFU through goal-setting, progress monitoring, and reminders in self-care. Key features included novel visual analytics that automatically extracts and monitors DFU size information from mobile phone photos of the foot. A functional prototype of MyFootCare was created and evaluated through a user-centred design process with 11 participants with DFUs. Data were collected through semi-structured interviews discussing existing self-care practices and observations of MyFootCare with participants. Data were analysed qualitatively through thematic analysis. RESULTS Key themes were: (1) Participants already used mobile phone photos to monitor their DFU progress, but (2) had limited experience with using smartphone applications. (3) Participants desired the objective DFU size data provided by the tracking feature of MyFootCare to monitor their DFU progress. (4) Participants were ambivalent about the MyFootCare goal setting and diary features, commenting that these features were useful but also that it was unlikely that they would use them. (5) Participants desired to share their MyFootCare data with their clinicians to demonstrate engagement in self-care and to reflect on their progress. CONCLUSIONS MyFootCare shows promising features to engage people in DFU self-care. Most notably, ulcer size data is useful to monitor progress and engage people. However, more work is needed to improve the usability and accuracy of MyFootCare, i.e., by refining the process of taking and analysing DFU photos and removing unnecessary features. These findings open the door for further work to develop a system that is easy to use and functions in everyday life conditions, and to trial it with people with DFUs and their carers.

Download Full-text

A Clinical Study to Evaluate Autofluorescence Imaging of Diabetic Foot Ulcers Using a Novel Artificial Intelligence Enabled Noninvasive Device

The International Journal of Lower Extremity Wounds ◽

10.1177/15347346211047098 ◽

2021 ◽

pp. 153473462110470

Author(s):

Vijay Viswanathan ◽

Senthil Govindan ◽

Bamila Selvaraj ◽

Secunda Rupert ◽

Raghul Kumar

Keyword(s):

Artificial Intelligence ◽

Diabetic Foot ◽

Predictive Value ◽

Early Infection ◽

Foot Ulcers ◽

Diabetic Foot Ulcers ◽

Autofluorescence Imaging ◽

Gram Positive ◽

Tissue Samples ◽

Gram Negative

Diabetic foot ulcers, with worldwide prevalence ranging from 12%-25%, are an important cause of nontraumatic lower limb amputation. Evidence-based assessment of early infection can help the clinician provide the right first line treatment thus helping improve the wound closure rate. Illuminate®, a novel point of care device working on multispectral autofluorescence imaging, helps in the rapid identification and classification of bacteria. This study was aimed to evaluate the diagnostic accuracy of the device in detecting bacterial gram type against standard culture methods. A total of 178 patients from a tertiary care center for diabetes was recruited and 203 tissue samples were obtained from the wound base by the plastic surgeon. The device was handled by the trained investigator to take wound images. The tissue samples were taken from the color-coded infected region as indicated by the device's Artificial Intelligence algorithm and sent for microbial assessment. The results were compared against the Gram type inferred by the device and the device was found to have an accuracy of 89.54%, a positive predictive value of 86.27% for detecting Gram-positive bacteria, 80.77% for Gram-negative bacteria, and 91.67% for no infection. The negative predictive value corresponded to 87.25% for Gram-positive, 92% for Gram-negative, and 96.12% for no infection. The Results exhibited the accuracy of this novel autofluorescence device in identifying and classifying the gram type of bacteria and its potential in significantly aiding clinicians towards early infection assessment and treatment.

Download Full-text