Development of a Non-Invasive Imaging Device for Prediction of Diabetic Foot Ulcer Healing Potential

Background. Diabetic foot ulcer (DFU) incidence in the diabetic population has been reported between 15% to 25% and leads to increased morbidity and mortality, higher risk of amputation, and millions of dollars in health care cost annually. Current reported DFU healing rates are about 30% by 12 weeks and 45% overall. Standard clinical practice evaluates DFU healing via changes in wound size and appearance after a time of routine wound treatment. This can delay the application of more effective treatment methods. The ability to predict wound healing potential at the initial DFU evaluation could significantly decrease periods of healing stasis and increase the resolution rates of DFUs.

Objective. For this institutional review board-approved study, multispectral imaging data were obtained from 8 DFUs using a noncontact imaging device during the initial clinic visit.

Materials and Methods. These data were analyzed by an artificial intelligence (AI) deep learning program to predict areas of nonhealing within the DFUs. After 4 weeks, actual area of nonhealing wound bed was compared to AI prediction. Accuracy of the AI program was evaluated using cross-validation due to the small sample size.

Results. The AI program demonstrated a sensitivity of 98.8% and specificity of 93.9% in predicting areas of the DFUs that would not heal by the 28-day healing assessment. Every DFU displayed some degree of healing but none of the DFUs healed completely within 28 days.

Conclusions. Although this initial study sample size is small, the use of AI with multispectral imaging data for DFU healing prediction is promising. Further training of the AI program on a larger patient population is currently underway to develop a more robust prediction algorithm.

Citation: Baxter RD, Thatcher J, Plant K, et al. Development of a non-invasive imaging device for prediction of diabetic foot ulcer healing potential. Poster presented at: Symposium on Advanced Wound Care Spring; May 7-11, 2019; San Antonio, TX.

Products: DeepView Imaging Technology

Sponsor: Baylor Scott & White Healthcare System (Dallas, TX)

IRB: Baylor Scott & White Research Institute (Dallas, TX) – Blue division IRB No: 015-253

This abstract was not subject to the WOUNDS^® peer-review process.

Interested in seeing more posters exhibited at SAWC Spring 2019? Register for the conference and attend the Poster Gala on Thursday, May 9!