使用机器学习联合临床与心肌灌注显像数据的预后价值
本研究纳入2619例连续接受运动或药物负荷高速SPECT心肌灌注显像的患者,用机器学习联合28项临床、17项负荷试验和25项影像变量预测主要不良心脏事件。随访3.2±0.6年,239例(9.1%)发生MACE;联合模型的AUC为0.81,高于仅影像机器学习模型(0.78)、医师视觉诊断(0.65)、自动负荷TPD(0.73)和自动缺血TPD(0.71),差异均有统计学意义(p<0.01)。
要点
- 机器学习联合临床与影像数据的MACE预测AUC为0.81,优于医师视觉诊断的0.65。
- 仅用影像数据的机器学习模型AUC为0.78,加入临床变量后提升至0.81(p<0.01)。
- 联合模型较医师视觉诊断的风险重分类比例为26%(p<0.001)。
核心结论
- 机器学习联合临床与影像数据变量对3年MACE风险具有高预测准确性,优于现有视觉或自动灌注评估;机器学习可使接受SPECT MPI患者的临床与影像数据整合用于个体化MACE风险计算。
研究设计与样本
- 研究纳入2619例连续患者(48%为男性,年龄62±13岁),38%接受运动负荷、62%接受药物负荷高速SPECT MPI,随访监测MACE;记录28项临床变量、17项负荷试验变量和25项影像变量(包括总灌注缺损TPD);机器学习采用信息增益排序自动变量选择、提升集成算法建模和10折分层交叉验证;比较四类模型的MACE预测AUC:联合全部数据的机器学习(ML-combined)、仅影像数据的机器学习(ML-imaging)、5级量表视觉诊断(医师诊断)、自动定量影像分析(负荷TPD和缺血TPD)。
诊断标准与关键数值
- MACE预测AUC:ML-combined 0.81 vs ML-imaging 0.78(p<0.01);ML-combined 0.81 vs 医师诊断0.65 vs 自动负荷TPD 0.73 vs 自动缺血TPD 0.71(各项p<0.01);ML-combined较视觉医师诊断的风险重分类为26%(p<0.001)。
临床应用与阅片要点
- 原文结论认为机器学习联合临床与影像数据可用于接受SPECT MPI患者的个体化MACE风险计算,其预测准确性优于视觉或自动灌注评估。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: This study evaluated the added predictive value of combining clinical information and myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) data using machine learning (ML) to predict major adverse cardiac events (MACE).
BACKGROUND: Traditionally, prognostication by MPI has relied on visual or quantitative analysis of images without objective consideration of the clinical data. ML permits a large number of variables to be considered in combination and at a level of complexity beyond the human clinical reader.
METHODS: A total of 2,619 consecutive patients (48% men; 62 ± 13 years of age) who underwent exercise (38%) or pharmacological stress (62%) with high-speed SPECT MPI were monitored for MACE. Twenty-eight clinical variables, 17 stress test variables, and 25 imaging variables (including total perfusion deficit [TPD]) were recorded. Areas under the receiver-operating characteristic curve (AUC) for MACE prediction were compared among: 1) ML with all available data (ML-combined); 2) ML with only imaging data (ML-imaging); 3) 5-point scale visual diagnosis (physician [MD] diagnosis); and 4) automated quantitative imaging analysis (stress TPD and ischemic TPD). ML involved automated variable selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross validation.
RESULTS: During follow-up (3.2 ± 0.6 years), 239 patients (9.1%) had MACE. MACE prediction was significantly higher for ML-combined than ML-imaging (AUC: 0.81 vs. 0.78; p < 0.01). ML-combined also had higher predictive accuracy compared with MD diagnosis, automated stress TPD, and automated ischemic TPD (AUC: 0.81 vs. 0.65 vs. 0.73 vs. 0.71, respectively; p < 0.01 for all). Risk reclassification for ML-combined compared with visual MD diagnosis was 26% (p < 0.001).
CONCLUSIONS: ML combined with both clinical and imaging data variables was found to have high predictive accuracy for 3-year risk of MACE and was superior to existing visual or automated perfusion assessments. ML could allow integration of clinical and imaging data for personalized MACE risk computations in patients undergoing SPECT MPI.
引用
- Betancur J, Otaki Y, Motwani M, et al. Prognostic Value of Combined Clinical and Myocardial Perfusion Imaging Data Using Machine Learning. JACC Cardiovasc Imaging. 2017. PMID: 29055639. doi:10.1016/j.jcmg.2017.07.024
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。