Key result
ML-based CT-FFR shows a ~0.05 interobserver difference that moderately impacts diagnostic accuracy regardless of image quality.
Why the study?
While cCTA is limited by specificity prior to TAVR and CT-FFR reliability is presumed, little is known about the reproducibility of ML-based CT-FFR.
What is the interrater variability of ML-based CT-FFR in patients with obstructive CAD prior to TAVR?
Observational (n=214)
No
What is the interrater variability of ML-based CT-FFR in patients with obstructive CAD prior to TAVR?
ML-based CT-FFR shows moderate interrater variability that increases below the cut-off, but this has only a moderate influence on diagnostic accuracy independent of image quality or calcification.
Answers are grounded in this paper and cite their sources.
Observer training may affect pre-TAVR ML CT-FFR; leaves open need for standardization before clinical adoption.
Objective To compare machine learning (ML)-based CT-derived fractional flow reserve (CT-FFR) in patients before transcatheter aortic valve replacement (TAVR) by observers with differing training and to assess influencing factors. Background Coronary computed tomography angiography (cCTA) can effectively exclude CAD, e.g. prior to TAVR, but remains limited by its specificity. CT-FFR may mitigate this limitation also in patients prior to TAVR. While a high reliability of CT-FFR is presumed, little is known about the reproducibility of ML-based CT-FFR. Methods Consecutive patients with obstructive CAD on cCTA were evaluated with ML-based CT-FFR by two observers. Categorization into hemodynamically significant CAD was compared against invasive coronary angiography. The influence of image quality and coronary artery calcium score (CAC) was examined. Results CT-FFR was successfully performed on 214/272 examinations by both observers. The median difference of CT-FFR between both observers was −0.05(−0.12-0.02) ( p < 0.001). Differences showed an inverse correlation to the absolute CT-FFR values. Categorization into CAD was different in 37/214 examinations, resulting in net recategorization of Δ13 (13/214) examinations and a difference in accuracy of Δ6.1%. On patient level, correlation of absolute and categorized values was substantial (0.567 and 0.570, p < 0.001). Categorization into CAD showed no correlation to image quality or CAC ( p > 0.13). Conclusion Differences between CT-FFR values increased in values below the cut-off, having little clinical impact. Categorization into CAD differed in several patients, but ultimately only had a moderate influence on diagnostic accuracy. This was independent of image quality or CAC.
No takes yet. Share an insight, caveat, or question.
Gohmann et al. (2023) conducted an observational in Coronary artery disease in patients evaluated for transcatheter aortic valve replacement (TAVR) (n=214). ML-based CT-derived fractional flow reserve (CT-FFR) vs. Inter-observer comparison (differing training levels) was evaluated on Interobserver difference of absolute CT-FFR values on patient level (Median difference -0.05, 95% CI -0.065, -0.035, p=<0.001). ML-based CT-FFR measurements by two observers with differing training showed a median difference of -0.05, which had a moderate influence on diagnostic accuracy independent of image quality or calcification.
Synapse has enriched 10 related papers. Consider them for comparative context: