Poster
PI-015
Charting Wound Healing: Using Centiles to Track Chronic Wounds’ Progress
Introduction: World Health Organization growth charts1 utilize Centile-based curves to track age-related growth dynamics. Identifying values outside of specific ranges indicates the need for further investigation or intervention. We adapted this methodology to develop Centile curves for chronic wounds, quantifying wound-age-related changes in healing, allowing clinicians to benchmark individual wound healing trajectories. Methods:De-identified data from 56451 evaluations of 11430 wounds were analyzed from 2,361 participating skilled nursing facilities. The analysis included different types of chronic wounds such as pressure injuries, diabetic wounds, venous ulcers, and arterial ulcers that healed within 4-16 weeks. An AI-based prognostic index2 was utilized to quantify wound healing at each evaluation. The prognostic index considers various wound characteristics such as wound area, tissue type, and more. Results:The best model fit, assessed using Q-statistics, was obtained using the Box-Cox Power Exponential (BCPE) distribution. The fitted centiles were observed to be very close to the nominal centiles. Centile curves above 25th percentile had an increasing long-term trend with a sharp rise in the initial 4 weeks. Discussion: The centile chart produced by this research can be used to plot a wound’s prognostic score over time to monitor the risk of delayed healing. The large dataset and variable wound aetiologies suggests that the developed centile curves are generalizable.
Implications for Practice
The developed centile charts can provide reference ranges that can identify high-risk (slowly healing) wounds or when a wound deteriorates from its expected trajectory, for example, moving from a higher percentile to a lower percentile.
Risk severity changes can help guide clinician interventions to prevent delays in wound healing and further complications.
AI and digital wound monitoring can help clinicians and wound programs assess the full wound history and provide prognostic guidance to help triage limited human resources.
References:1. Kiserud, T., Benachi, A., Hecher, K., Perez, R. G., Carvalho, J., Piaggio, G., & Platt, L. D. (2018). The World Health Organization fetal growth charts: concept, findings, interpretation, and application. American journal of obstetrics and gynecology, 218(2), S619-S629.
2. 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