Why the study?
It would be ideal for a non-hyperaemic index to predict fractional flow reserve more accurately, given the extensive validation of FFR across clinical settings.
Does a deep learning algorithm applied to resting coronary pressure curves improve the prediction of fractional flow reserve compared to standard non-hyperaemic pressure ratios in patients with coronary lesions?
Population
1,666 patients with 1,718 coronary lesions and 2,928 coronary pressure tracings
Comparison
Deep learning algorithms vs non-hyperaemic pressure ratio to predict FFR
Design
Post hoc analysis of three previously published studies with derivation and validation cohorts
Authors
Loading...
May support non-hyperaemic FFR estimation; leaves open external validation and outcome trials before practice change.
Does a deep learning algorithm applied to resting coronary pressure curves improve the prediction of fractional flow reserve compared to standard non-hyperaemic pressure ratios in patients with coronary lesions?
Deep learning analysis of resting coronary pressure curves does not significantly improve the prediction of FFR compared to standard resting pressure ratios, suggesting hyperaemia remains necessary for accurate FFR assessment.
Zimmermann et al. (2021) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: