This poster was featured at the SAWC Spring 2025 in Grapevine, Texas.  

Authors: Heba Tallah Mohammed, Sheila Wang, Samantha Bestavros, Kaitlyn Ramsay, Ryan Geng, Samiha Mohsen, Katerina Bavaro, Robert D. J. Fraser 

This study assesses inter- and intra-rater reliability of AI-driven wound care technologies in wound tissue classification across clinicians with varying experience levels. Key findings include: 

• The 99% intra-rater agreement suggests high precision and minimal variability for the same rater in identifying and quantifying wound tissue types with repeated measures.   
• The strong inter-rater reliability observed suggests that the AI-WCT supports reliable measurements across different raters, ensuring highly reproducible results. 

Because of the high agreement, AI-assisted wound assessment tools could be instrumental in multi-clinician settings, enhancing the quality of documentation and ensuring consistent evaluations across providers for better wound progress tracking. 

To learn more about the research conducted for this poster, or to speak with the Swift Medical team about digital wound care, contact us.