JMIR Publications

ABSTRACT

Background:

Diabetes-related foot ulcers (DFUs) are common in people living with diabetes and are a major cause of poor quality of life and disability. If not treated in a timely and appropriate way, DFUs may result in prolonged hospitalization and possibly amputation. Major comorbidities and premature mortality are associated with DFUs. Currently, methods to predict the healing trajectory of DFUs lack accuracy. Thermal imaging has been proposed to overcome these limitations but to date, it has been unable to accurately predict delayed healing of DFUs in the early stages of ulcer management. This project aims to ascertain whether textural analysis of a thermal image taken at a clinic appointment can predict the healing trajectory of neuropathic DFUs.

Objective:

1. To codesign an accurate, fast, easy-to-use, computer-aided, non-touch test to predict DFU healing trajectory using texture analysis of thermal imaging that is fit for purpose and acceptable to both those being tested and users of the device, and 2. To validate whether textural analysis of thermal images can accurately predict healing of neuropathic DFUs at week 12 from an image taken at the first visit.

Methods:

This project will be undertaken in two phases: Phase 1) co-design and development of the prototype, and Phase 2) technology validation. Phase 1 will involve a participatory action, codesign approach, engaging key stakeholders, clinicians, adults living with diabetes and a DFU or who have a history of a DFU and biomedical engineers in four facilitated focus groups to shape the device so that is fit for purpose. Phase 2 will be a longitudinal observational study of 120 adults living with a neuropathic DFU over a 12-week period. Demographic and other data identified from published studies that have been shown to impact wound healing will be collected at baseline, including participant age, gender, wound area and duration, and biomedical markers. Thermal and colour (red, green, blue) images will be taken at weeks 1, 2 and 12. Wound textural features will be entered into a Bayesian neural network to identify the healing trajectory.

Results:

Phase 1 has been completed for one codesign focus group with clinicians from High-Risk Foot Services at two major hospitals in Melbourne, Australia, and will conclude in December 2024. Phase 2 data collection will be completed by April 2025.

Conclusions:

The study aims to codesign, test and validate an accurate, feasible and acceptable device to predict the healing of DFUs at week 12 from an image taken at the first visit. This has the potential to assist clinicians in making informed and timely decisions for instigating adjuvant therapies, thereby improving healing and preventing lower extremity amputations.