CT-FFR measurements showed only moderate consistency between K and S software (ICC 0.581), with significant differences influenced by vessel shifting length, image quality, heart rate variability, and lumen diameter.
Observational (n=72)
Single-blind
No
Does CT-FFR measurement consistency vary between different artificial intelligence software programs in patients with suspected coronary artery disease?
CT-FFR measurements vary significantly between different software platforms, with discrepancies influenced by vessel shifting length, image quality, heart rate variability, and lumen diameter.
Estimación del efecto: ICC 0.581 (95% CI 0.452-0.679)
Tasa de eventos absoluta: 0.867% vs 0.886%
valor p: p=<0.001
OBJECTIVE: This study aims to assess the consistency of various CT-FFR software, to determine the reliability of current CT-FFR software, and to measure relevant influence factors. The goal is to build a solid foundation of enhanced workflow and technical principles that will ultimately improve the accuracy of measurements of coronary blood flow reserve fractions. This improvement is critical for assessing the level of ischemia in patients with coronary heart disease. METHODS: 103 participants were chosen for a prospective research using coronary computed tomography angiography (CCTA) assessment. Heart rate, heart rate variability, subjective picture quality, objective image quality, vascular shifting length, and other factors were assessed. CT-FFR software including K software and S software are used for CT-FFR calculations. The consistency of the two software is assessed using paired-sample t-tests and Bland-Altman plots. The error classification effect is used to construct the receiver operating characteristic curve. RESULTS: The CT-FFR measurements differed significantly between the K and S software, with a statistical significance of P < 0.05. In the Bland-Altman plot, 6% of the points (14 out of 216) fell outside the 95% consistency level. Single-factor analysis revealed that heart rate variability, vascular dislocation offset distance, subjective image quality, and lumen diameter significantly influenced the discrepancies in CT-FFR measurements between two software programs (P < 0.05). The ROC curve shows the highest AUC for the vessel shifting length, with an optimal cut-off of 0.85 mm. CONCLUSION: CT-FFR measurements vary among software from different manufacturers, leading to potential misclassification of qualitative diagnostics. Vessel shifting length, subjective image quality score, HRv, and lumen diameter impacted the measurement stability of various software.
Li et al. (Thu,) conducted a observational in Suspected coronary artery disease (n=72). CT-FFR software (K software) vs. CT-FFR software (S software) was evaluated on Consistency of CT-FFR measurements (ICC 0.581, 95% CI 0.452-0.679, p=<0.001). CT-FFR measurements showed only moderate consistency between K and S software (ICC 0.581), with significant differences influenced by vessel shifting length, image quality, heart rate variability, and lumen diameter.