Fully Automated AI CT Analysis for TAVI Planning Alters Prosthesis Size in 21% of Cases

Fully automated AI-based CT analysis for TAVI planning had excellent agreement with semi-automated measurements (ICC>0.95), but would have changed prosthesis size selection in 21% of patients versus 14% with standard software, underscoring the need for expert interpretation.

• Mean absolute errors for annulus diameter, perimeter, and area were 0.6 mm, 2.0 mm, and 21.2 mm², respectively, with ICC >0.95 for all.
• Simulated prosthesis size selection based on AI-derived measurements differed from the implanted size in 21% of patients vs. 14% for the semi-automated method.
• Retrospective, two-center study of 247 patients; expert oversight remains essential to integrate broader anatomical and clinical context.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.