Skip to main content

Advertisement

ADVERTISEMENT

Poster PI-016

Predicting delayed healing chronic wounds using big data and AI-based objective healing index 

Introduction: Chronic wounds may take 12 or more weeks to close1. These wounds cost medical systems billions of dollars worldwide2. Accurate and early detection of delayed wound healing may lead to better patient outcomes and lower treatment costs. Therefore, a wound classifier using an AI-based healing index (HI)3 was developed to classify wounds into early and delayed healing categories.   Methods:The model was trained using subjective and objective wound characteristics, including wound area and tissue characteristics of the wound bed obtained directly from wound images. The dataset comprised 161,635 wounds from skilled nursing and home healthcare settings. This prognostic index classified wounds that healed within the 12 weeks since first evaluation vs wounds that did not heal during the same period and was compared with a widely used metric called percentage area reduction (PAR)4. The accuracy was quantified and compared using the area under the receiver operating curve (AUC).   Results:The table below shows the AUCs for individual metrics computed using their values at 4 different weeks since the first evaluation. HI achieves better performance at week 3 than does PAR at week 4 (0.65 vs. 0.64).   Metric  Week 1  Week 2  Week 3  Week 4  PAR  0.55  0.58  0.60  0.64  Healing Index  0.60  0.63  0.65  0.69     Discussion: The model’s predictive capability to the accepted standard (PAR) established that the HI was better at classifying delayed healing chronic wounds at each week, and at earlier time periods than PAR.   Implications  The AI-based HI outperforms the commonly used PAR tool in early and accurate classification of delayed healing chronic wounds. Further study integrating the AI-based HI is needed to understand the benefits to healing outcomes for patients of earlier identification of delayed wound healing.   References:1. Beitz, J. M. (2022). Wound healing. In L. L. McNichol, C. R. Ratliff, & S. S. Yates (Eds.), Wound, Ostomy, and Continence Nurses Society Core Curriculum: Wound Management (2nd ed., pp. 38–54). Wolters Kluwer. 2. Queen, D., Botros, M., & Harding, K. (2023). International opinion—The true cost of wounds for Canadians. International Wound Journal, 21(1), e14522. https://doi.org/10.1111/iwj.14522 3. Gupta, R., Goldstone, L., Eisen, S., Ramachandram, D., Cassata, A., Fraser, R. D. J., Ramirez-GarciaLuna, J. L., Bartlett, R., & Allport, J. (2022). Towards an AI-based Objective Prognostic Model for Quantifying Wound Healing [Preprint]. https://doi.org/10.36227/techrxiv.21067261.v1 4. Bull, R. H., Staines, K. L., Collarte, A. J., Bain, D. S., Ivins, N. M., & Harding, K. G. (2022). Measuring progress to healing: A challenge and an opportunity. International Wound Journal, 19(4), 734–740. https://doi.org/10.1111/iwj.13669

Advertisement

Advertisement

Advertisement