Division of Cardiology, Gordon and Leslie Diamond Health Care Centre.), University of British Columbia, Vancouver, British Columbia, Canada.
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada.
J Am Soc Echocardiogr. 2022 Dec;35(12):1247-1255. doi: 10.1016/j.echo.2022.06.005. Epub 2022 Jun 24.
Unlike left ventricular (LV) ejection fraction, which provides a precise, reliable, and prognostically valuable measure of systolic function, there is no single analogous measure of LV diastolic function.
We aimed to develop a continuous score to grade LV diastolic function using machine learning modeling of echocardiographic data.
Consecutive echo studies performed at a tertiary-care center between February 1, 2010, and March 31, 2016, were assessed, excluding studies containing features that would interfere with diastolic function assessment as well as studies in which 1 or more parameters within the contemporary diastolic function assessment algorithm were not reported. Diastolic function was graded based on 2016 American Society of Echocardiography (ASE)/European Association of Cardiovascular Imaging (EACVI) guidelines, excluding indeterminate studies. Machine learning models were trained (support vector machine [SVM], decision tree [DT], XGBoost [XGB], and dense neural network [DNN]) to classify studies within the training set by diastolic dysfunction severity, blinded to the ASE/EACVI classification. The DNN model was retrained to generate a regression model (R-DNN) to predict a continuous LV diastolic function score.
A total of 28,986 studies were included; 23,188 studies were used to train the models, and 5,798 studies were used for validation. The models were able to reclassify studies with high agreement to the ASE/EACVI algorithm (SVM, 83%; DT, 100%; XGB, 100%; DNN, 98%). The continuous diastolic function score corresponded well with ASE/EACVI guidelines, with scores of 1.00 ± 0.01 for studies with normal function and 0.74 ± 0.05, 0.51 ± 0.06, and 0.27 ± 0.11 for mild, moderate, and severe diastolic dysfunction, respectively (mean ± 1 SD). A score of <0.91 predicted abnormal diastolic function (area under the receiver operator curve = 0.99), while a score of <0.65 predicted elevated filling pressure (area under the receiver operator curve = 0.99).
Machine learning can assimilate echocardiographic data and generate an automated continuous diastolic function score that corresponds well with current diastolic function grading recommendations.
与提供精确、可靠和预后价值的左心室（LV）射血分数不同，目前尚无用于评估 LV 舒张功能的单一类似指标。
我们旨在使用机器学习对超声心动图数据进行建模，开发一种连续评分来分级 LV 舒张功能。
回顾性分析 2010 年 2 月 1 日至 2016 年 3 月 31 日在一家三级保健中心进行的连续超声心动图研究，排除了可能干扰舒张功能评估的研究以及未报告当代舒张功能评估算法内 1 个或多个参数的研究。根据 2016 年美国超声心动图学会（ASE）/欧洲心血管影像协会（EACVI）指南对舒张功能进行分级，排除不确定的研究。使用支持向量机（SVM）、决策树（DT）、XGBoost（XGB）和密集神经网络（DNN）等机器学习模型对训练集中的研究进行分类，分类依据是舒张功能障碍的严重程度，对 ASE/EACVI 分类结果设盲。重新训练 DNN 模型以生成预测 LV 舒张功能连续评分的回归模型（R-DNN）。
共纳入 28986 项研究；23188 项研究用于模型训练，5798 项研究用于验证。这些模型能够以高一致性重新对研究进行分类，与 ASE/EACVI 算法一致（SVM，83%；DT，100%；XGB，100%；DNN，98%）。连续舒张功能评分与 ASE/EACVI 指南吻合良好，功能正常的研究评分为 1.00±0.01，轻度、中度和重度舒张功能障碍的研究评分分别为 0.74±0.05、0.51±0.06 和 0.27±0.11（均为均值±1 个标准差）。评分＜0.91 预测舒张功能异常（接受者操作特征曲线下面积=0.99），评分＜0.65 预测充盈压升高（接受者操作特征曲线下面积=0.99）。
机器学习可以吸收超声心动图数据，并生成与当前舒张功能分级推荐吻合良好的自动连续舒张功能评分。
