ADVERTISEMENT
Poster
PI-020
Accelerating Wound Depth Measurement Through Accessible AI-Powered Wound Care Solution
Introduction: Measuring wound dimensions through traditional methods can be time-consuming and prone to human error. However, integrating artificial intelligence (AI) into wound care solutions (AI-WCS) has enhanced the assessment process by making it faster and more accurate. 1,2 AI-WCS can now measure wound depth while integrated on various devices like tablets and smartphones, making it easier for clinicians to leverage this technology to efficiently and consistently track wound size changes regardless of the used device.
The AI-WCS leveraged the computer-visioning that uses multi-view geometry to reconstruct wound bed topography and support prognostic models. This validation research tested the improved algorithm pipeline and assessed its impact on speeding up the time to measure wound depth.Methods:This validation used data form 2,050 wound evaluations of different types assessed using the AI-WCS to test improvements in algorithm on the electronic devices released in 2016 and android tablet released in 2020. In addition, the time required to measure wound depth using new devices from 2013 and beyond was tested, utilizing (number) wounds.Results:By integrating the AI-WCS with an enhanced pipeline algorithm, significant improvements have been observed. This study found the depth assessment time improved by 90% with older iPhone (XR) generations from 2016, while an old generation of Android tablet (A7) recorded a 668% improvement. For newer models of iPhone and tablet devices, the average time required for wound depth evaluation has been accelerated to 10-12 seconds per assessment.Discussion: Advanced computer-vision technology can accelerate automatic wound assessment, reducing time spent on mechanical tasks and allowing clinicians to focus on improving care plans.
Wound care technology needs to deliver improved care quality and efficiency in clinical practice.
Computer Vision can be deployed on a range of generations of smartphone and tablet technology to enable standardized assessment of visible wound depth.
References:1. Mohammed HT, Bartlett RL, Babb D, Fraser RDJ, Mannion D. A time motion study of manual versus artificial intelligence methods for wound assessment. PLoS One. 2022 Jul 28;17(7):e0271742. doi: 10.1371/journal.pone.0271742. PMID: 35901189; PMCID: PMC9333325.
2. Wang SC, Anderson JAE, Evans R, Woo K, Beland B, Sasseville D, et al. (2017) Point-of-care wound visioning technology: Reproducibility and accuracy of a wound measurement app. PLoS ONE 12(8): e0183139.