Department of Cardiovascular Medicine, Mayo Clinic, Rochester, Minnesota.
Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, Minnesota.
J Am Soc Echocardiogr. 2022 Dec;35(12):1214-1225.e8. doi: 10.1016/j.echo.2022.06.013. Epub 2022 Jul 12.
The 2016 American Society of Echocardiography guidelines have been widely used to assess left ventricular diastolic function. However, limitations are present in the current classification system. The aim of this study was to develop a data-driven, unsupervised machine learning approach for diastolic function classification and risk stratification using the left ventricular diastolic function parameters recommended in the 2016 American Society of Echocardiography guidelines; the guideline grading was used as the reference standard.
Baseline demographics, heart failure hospitalization, and all-cause mortality data were obtained for all adult patients who underwent transthoracic echocardiography at Mayo Clinic Rochester in 2015. Patients with prior mitral valve intervention, congenital heart disease, cardiac transplantation, or cardiac assist device implantation were excluded. Nine left ventricular diastolic function variables (mitral E- and A-wave peak velocities, E/A ratio, deceleration time, medial and lateral annular e' velocities and E/e' ratio, and tricuspid regurgitation peak velocity) were used for an unsupervised machine learning algorithm to identify different phenotype clusters. The cohort average of each variable was used for imputation. Patients were grouped according to the algorithm-determined clusters for Kaplan-Meier survival analysis.
Among 24,414 patients (mean age, 63.6 ± 16.2 years), all-cause mortality occurred in 4,612 patients (18.9%) during a median follow-up period of 3.1 years. The algorithm determined three clusters with echocardiographic measurement characteristics corresponding to normal diastolic function (n = 8,312), impaired relaxation (n = 11,779), and increased filling pressure (n = 4,323), with 3-year cumulative mortality of 11.8%, 19.9%, and 33.4%, respectively (P < .0001). All 10,694 patients (43.8%) classified as indeterminate were reclassified into the three clusters (n = 3,324, n = 5,353, and n = 2,017, respectively), with 3-year mortality of 16.6%, 22.9%, and 34.4%, respectively. The clusters also outperformed guideline-based grade for prognostication (C index = 0.607 vs 0.582, P = .013).
Unsupervised machine learning identified physiologically and prognostically distinct clusters on the basis of nine diastolic function Doppler variables. The clusters can be potentially applied in echocardiography laboratory practice and future clinical trials for simple, replicable diastolic function-related risk stratification.
2016 年美国超声心动图学会指南已被广泛用于评估左心室舒张功能。然而，目前的分类系统存在局限性。本研究旨在使用 2016 年美国超声心动图学会指南推荐的左心室舒张功能参数，开发一种数据驱动的、无监督的机器学习方法来进行舒张功能分类和危险分层；指南分级作为参考标准。
纳入 2015 年在梅奥诊所罗切斯特院区接受经胸超声心动图检查的所有成年患者的基线人口统计学资料、心力衰竭住院和全因死亡率数据。排除既往二尖瓣介入治疗、先天性心脏病、心脏移植或心脏辅助装置植入的患者。使用 9 个左心室舒张功能变量（二尖瓣 E 波和 A 波峰值速度、E/A 比值、减速时间、内侧和外侧瓣环 e'速度和 E/e'比值以及三尖瓣反流峰值速度）进行无监督机器学习算法以识别不同的表型簇。使用协变量平均法对每个变量进行插补。根据算法确定的簇对患者进行分组，进行 Kaplan-Meier 生存分析。
在 24414 例患者（平均年龄 63.6±16.2 岁）中，中位随访 3.1 年期间，共有 4612 例（18.9%）患者发生全因死亡。该算法确定了 3 个具有与正常舒张功能（n=8312）、舒张功能不全（n=11779）和充盈压升高（n=4323）相对应的超声心动图测量特征的簇，其 3 年累积死亡率分别为 11.8%、19.9%和 33.4%（P<.0001）。所有 10694 例（43.8%）被归类为不确定的患者被重新分类为 3 个簇（n=3324、n=5353 和 n=2017），其 3 年死亡率分别为 16.6%、22.9%和 34.4%。这些簇在预后方面也优于基于指南的分级（C 指数=0.607 比 0.582，P=.013）。
无监督机器学习根据 9 个舒张功能多普勒变量识别出具有生理和预后意义的不同簇。这些簇可潜在应用于超声心动图实验室实践和未来的临床试验，用于进行简单、可重复的与舒张功能相关的危险分层。
