Barbieri Andrea, Bursi Francesca, Camaioni Giovanni, Maisano Anna, Imberti Jacopo Francesco, Albini Alessandro, De Mitri Gerardo, Mantovani Francesca, Boriani Giuseppe
Division of Cardiology, Department of Diagnostics, Clinical and Public Health Medicine, Policlinico University Hospital of Modena, University of Modena and Reggio Emilia, 41121 Modena, Italy.
Division of Cardiology, San Paolo Hospital, ASST Santi Paolo and Carlo, Department of Health Sciences, University of Milan, 20142 Milan, Italy.
J Clin Med. 2021 Mar 19;10(6):1279. doi: 10.3390/jcm10061279.
A recently developed algorithm for 3D analysis based on machine learning (ML) principles detects left ventricular (LV) mass without any human interaction. We retrospectively studied the correlation between 2D-derived linear dimensions using the ASE/EACVI-recommended formula and 3D automated, ML-based methods (Philips HeartModel) regarding LV mass quantification in unselected patients undergoing echocardiography. We included 130 patients (mean age 60 ± 18 years; 45% women). There was only discrete agreement between 2D and 3D measurements of LV mass (r = 0.662, r = 0.348, < 0.001). The automated algorithm yielded an overestimation of LV mass compared to the linear method (Bland-Altman positive bias of 13.1 g with 95% limits of the agreement at 4.5 to 21.6 g, = 0.003, ICC 0.78 (95%CI 0.68-8.4). There was a significant proportional bias (Beta -0.22, t = -2.9) = 0.005, the variance of the difference varied across the range of LV mass. When the published cut-offs for LV mass abnormality were used, the observed proportion of overall agreement was 77% (kappa = 0.32, < 0.001). In consecutive patients undergoing echocardiography for any indications, LV mass assessment by 3D analysis using a novel ML-based algorithm showed systematic differences and wide limits of agreements compared with quantification by ASE/EACVI- recommended formula when the current cut-offs and partition values were applied.
一种最近基于机器学习（ML）原理开发的用于三维分析的算法，无需任何人工干预即可检测左心室（LV）质量。我们回顾性研究了在接受超声心动图检查的未选择患者中，使用ASE/EACVI推荐公式得出的二维衍生线性尺寸与基于ML的三维自动化方法（飞利浦心脏模型）在左心室质量量化方面的相关性。我们纳入了130例患者（平均年龄60±18岁；45%为女性）。左心室质量的二维和三维测量之间仅有离散一致性（r = 0.662，r = 0.348，<0.001）。与线性方法相比，自动化算法高估了左心室质量（布兰德-奥特曼阳性偏差为13.1 g，一致性界限为95%时为4.5至21.6 g，=0.003，组内相关系数0.78（95%CI 0.68 - 8.4）。存在显著的比例偏差（β -0.22，t = -2.9）=0.005，差异的方差在左心室质量范围内有所不同。当使用已公布的左心室质量异常临界值时，观察到的总体一致性比例为77%（kappa = 0.32，<0.001）。在因任何适应症接受超声心动图检查的连续患者中，当应用当前临界值和划分值时，与使用ASE/EACVI推荐公式进行量化相比，使用基于ML的新型算法进行三维分析评估左心室质量显示出系统差异和较宽的一致性界限。
