Seligman Henry, Patel Sapna B, Alloula Anissa, Howard James P, Cook Christopher M, Ahmad Yousif, de Waard Guus A, Pinto Mauro Echavarría, van de Hoef Tim P, Rahman Haseeb, Kelshiker Mihir A, Rajkumar Christopher A, Foley Michael, Nowbar Alexandra N, Mehta Samay, Toulemonde Mathieu, Tang Meng-Xing, Al-Lamee Rasha, Sen Sayan, Cole Graham, Nijjer Sukhjinder, Escaned Javier, Van Royen Niels, Francis Darrel P, Shun-Shin Matthew J, Petraco Ricardo
National Heart and Lung Institute, Imperial College London, B Block, Hammersmith Hospital, London W12 0HS, UK.
Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK.
Eur Heart J Digit Health. 2023 May 3;4(4):291-301. doi: 10.1093/ehjdh/ztad030. eCollection 2023 Aug.
Coronary flow reserve (CFR) assessment has proven clinical utility, but Doppler-based methods are sensitive to noise and operator bias, limiting their clinical applicability. The objective of the study is 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.
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. Artificial intelligence successfully quantified Doppler signal quality, with high agreement with expert consensus (Spearman's rho: 0.94), and within individual experts. Artificial intelligence automatically tracked flow velocity with superior numerical agreement against experts, when compared with the current console algorithm [AI flow vs. expert flow bias -1.68 cm/s, 95% confidence interval (CI) -2.13 to -1.23 cm/s, < 0.001 with limits of agreement (LOA) -4.03 to 0.68 cm/s; console flow vs. expert flow bias -2.63 cm/s, 95% CI -3.74 to -1.52, < 0.001, 95% LOA -8.45 to -3.19 cm/s]. Artificial intelligence yielded more precise CFR values [median absolute difference (MAD) against expert CFR: 4.0% for AI and 7.4% for console]. Artificial intelligence tracked lower-quality Doppler signals with lower variability (MAD against expert CFR 8.3% for AI and 16.7% for console).
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.
冠状动脉血流储备（CFR）评估已被证明具有临床应用价值，但基于多普勒的方法对噪声和操作者偏差敏感，限制了其临床适用性。本研究的目的是通过开发人工智能（AI）算法来自动量化冠状动脉多普勒质量并跟踪流速，从而扩大有创多普勒CFR的应用。
在从冠状动脉多普勒血流记录中提取的图像上训练神经网络，以对信号质量进行评分，并得出冠状动脉流速和CFR值。输出结果与专家共识进行独立验证。人工智能成功地量化了多普勒信号质量，与专家共识高度一致（斯皮尔曼相关系数：0.94），且在各专家之间也高度一致。与当前的控制台算法相比，人工智能在自动跟踪流速方面与专家的数值一致性更高[人工智能流速与专家流速偏差为-1.68 cm/s，95%置信区间（CI）为-2.13至-1.23 cm/s，P<0.001，一致性界限（LOA）为-4.03至0.68 cm/s；控制台流速与专家流速偏差为-2.63 cm/s，95%CI为-3.74至-1.52，P<0.001，95%LOA为-8.45至-3.19 cm/s]。人工智能得出的CFR值更精确[与专家CFR的中位数绝对差（MAD）：人工智能为4.0%，控制台为7.4%]。人工智能跟踪质量较低的多普勒信号时变异性较小（与专家CFR的MAD：人工智能为8.3%，控制台为16.7%）。
一个由专家训练并经过独立验证的基于人工智能的系统，可以为多普勒轨迹分配质量分数，并得出冠状动脉流速和CFR。通过使多普勒CFR更加自动化、精确且不依赖操作者，人工智能可以扩大冠状动脉微血管评估的临床适用性。
