Background
Coronary Flow Reserve (CFR) assessment has proven clinical utility, but Doppler-based methods are sensitive to noise and operator bias, limiting their clinical applicability.
Objectives
To expand the adoption of invasive Doppler CFR, through the development of artificial intelligence (AI) algorithms to automatically quantify coronary Doppler quality and track flow velocity.
Methods
A neural network was trained on images extracted from coronary Doppler flow recordings to score signal quality and derive values for coronary flow velocity and CFR. The outputs were independently validated against expert consensus.
Results
AI successfully quantified Doppler signal quality, with high agreement with expert consensus (Spearman’s Rho: 0.94), and within individual experts. AI automatically tracked flow velocity with superior numerical agreement against experts, when compared to the current console algorithm (AI flow vs Expert flow bias -1.68cm/s, 95% CI -2.13cm/s to -1.23, p<0.001 with Limits of agreement (LOA): -4.03cm/s to 0.68cm/s; console flow vs Expert flow bias -2.63cm/s, 95 CI -3.74 to -1.52, p<0.001, 95% LOA -8.45cm/s to -3.19cm/s). AI yielded more precise CFR values (median absolute difference (MAD) against Expert CFR: 4.0% for AI and 7.4% for console). AI tracked lower quality Doppler signals with lower variability (MAD against Expert CFR 8.3% for AI 8.3% and 16.7% for console).
Conclusions
An AI-based system, trained by experts and independently validated, could assign a quality score to Doppler traces and derive coronary flow velocity and CFR. By making Doppler CFR more automated, precise and operator-independent, AI could expand the clinical applicability of coronary microvascular assessment.