Department of Anesthesiology and Critical Care, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA; Penn Center for Perioperative Outcomes Research and Transformation, University of Pennsylvania, Philadelphia, PA; Penn's Cardiovascular Outcomes, Quality and Evaluative Research Center, University of Pennsylvania, Philadelphia, PA; Leonard Davis Institute of Health Economics, University of Pennsylvania, Philadelphia, PA.
Philips Research, North America, Cambridge, MA.
J Cardiothorac Vasc Anesth. 2024 Apr;38(4):895-904. doi: 10.1053/j.jvca.2024.01.005. Epub 2024 Jan 11.
To test the correlation of ejection fraction (EF) estimated by a deep-learning-based, automated algorithm (Auto EF) versus an EF estimated by Simpson's method.
A prospective observational study.
A single-center study at the Hospital of the University of Pennsylvania.
Study participants were ≥18 years of age and scheduled to undergo valve, aortic, coronary artery bypass graft, heart, or lung transplant surgery.
This noninterventional study involved acquiring apical 4-chamber transthoracic echocardiographic clips using the Philips hand-held ultrasound device, Lumify.
In the primary analysis of 54 clips, compared to Simpson's method for EF estimation, bias was similar for Auto EF (-10.17%) and the experienced reader-estimated EF (-9.82%), but the correlation was lower for Auto EF (r = 0.56) than the experienced reader-estimated EF (r = 0.80). In the secondary analyses, the correlation between EF estimated by Simpson's method and Auto EF increased when applied to 27 acquisitions classified as adequate (r = 0.86), but decreased when applied to 27 acquisitions classified as inadequate (r = 0.46).
Applied to acquisitions of adequate image quality, Auto EF produced a numerical EF estimate equivalent to Simpson's method. However, when applied to acquisitions of inadequate image quality, discrepancies arose between EF estimated by Auto EF and Simpson's method. Visual EF estimates by experienced readers correlated highly with Simpson's method in both variable and inadequate imaging conditions, emphasizing its enduring clinical utility.
测试基于深度学习的自动算法（Auto EF）估计的射血分数（EF）与 Simpson 法估计的 EF 的相关性。
前瞻性观察性研究。
宾夕法尼亚大学医院的单中心研究。
研究参与者年龄≥18 岁，计划接受瓣膜、主动脉、冠状动脉旁路移植、心脏或肺移植手术。
本非介入性研究涉及使用飞利浦手持式超声设备 Lumify 获取心尖 4 腔经胸超声心动图剪辑。
在 54 个剪辑的主要分析中，与 Simpson 法估计 EF 相比，Auto EF（-10.17%）和经验丰富的读者估计 EF（-9.82%）的偏差相似，但 Auto EF 的相关性较低（r = 0.56）与经验丰富的读者估计 EF（r = 0.80）。在二次分析中，当应用于 27 个分类为足够的采集时，Simpson 法估计的 EF 与 Auto EF 之间的相关性增加（r = 0.86），但当应用于 27 个分类为不足的采集时，相关性降低（r = 0.46）。
应用于足够图像质量的采集时，Auto EF 产生了与 Simpson 法相当的数值 EF 估计值。然而，当应用于图像质量不足的采集时，Auto EF 估计的 EF 与 Simpson 法之间出现了差异。经验丰富的读者的视觉 EF 估计与 Simpson 法在可变和图像质量不足的条件下高度相关，强调了其持久的临床实用性。
