文献速递心脏核医学

整合心电图与门控SPECT的机器学习方法用于心脏再同步化治疗决策支持

A machine learning method integrating ECG and gated SPECT for cardiac resynchronization therapy decision support.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2023-05-17

本研究基于前瞻性队列中153例符合心脏再同步化治疗(CRT)标准的患者,开发并验证整合心电图、门控SPECT心肌灌注显像(GMPS)及临床变量的机器学习模型以预测CRT应答。以左室射血分数(LVEF)随访升高≥5%定义应答、≥15%定义超应答,PAM模型预测应答的曲线下面积(AUC)为0.80,对比指南变量偏最小二乘判别分析的0.72(P=0.52);朴素贝叶斯预测超应答的AUC为0.87,神经网络使用指南变量AUC为0.93(P=0.48)。作者认为机器学习方法相较指南标准在预测CRT应答与超应答方面呈改善趋势,需进一步研究验证模型。

要点

  • PAM模型预测CRT应答AUC 0.80,对比指南变量偏最小二乘判别分析0.72,差异无统计学意义(P=0.52)。
  • PAM模型敏感度0.86、特异度0.75,优于指南单独敏感度0.75、特异度0.24。
  • 神经网络使用指南变量预测超应答AUC 0.93,对比朴素贝叶斯0.87,差异无统计学意义(P=0.48)。

核心结论

  • 相较指南标准,机器学习方法在预测CRT应答与超应答方面呈改善趋势,GMPS在多数参数获取中处于核心地位,需进一步研究验证模型。

研究设计与样本

  • 本分析纳入一项前瞻性队列研究中153例符合CRT标准的患者,开发并验证整合心电图、GMPS及临床变量的机器学习模型。

主要发现

  • 以LVEF随访升高≥5%定义应答,PAM模型AUC为0.80,对比指南变量偏最小二乘判别分析AUC为0.72(P=0.52)。
  • PAM模型敏感度0.86、特异度0.75,优于指南单独敏感度0.75、特异度0.24。
  • 以LVEF随访升高≥15%定义超应答,神经网络使用指南变量AUC为0.93,对比朴素贝叶斯0.87,差异无统计学意义(P=0.48)。
  • 神经网络使用指南变量敏感度1.0、特异度0.75,优于指南单独敏感度0.78、特异度0.25。

关键数值与推荐

  • CRT应答定义为随访时LVEF升高≥5%,超应答定义为随访时LVEF升高≥15%。
  • 机器学习中采用变量筛选,以微阵列预测分析(PAM)建模应答,以朴素贝叶斯(NB)建模超应答。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文结论指出需进一步研究验证模型。

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)。

原文

PURPOSE: Cardiac resynchronization therapy (CRT) has been established as an important therapy for heart failure. Mechanical dyssynchrony has the potential to predict responders to CRT. The aim of this study was to report the development and the validation of machine learning models which integrate ECG, gated SPECT MPI (GMPS), and clinical variables to predict patients' response to CRT. METHODS: This analysis included 153 patients who met criteria for CRT from a prospective cohort study. The variables were used to model predictive methods for CRT. Patients were classified as "responders" for an increase of LVEF ≥ 5% at follow-up. In a second analysis, patients were classified as "super-responders" for an increase of LVEF ≥ 15%. For ML, variable selection was applied, and Prediction Analysis of Microarrays (PAM) approach was used to model response while Naïve Bayes (NB) was used to model super-response. These ML models were compared to models obtained with guideline variables. RESULTS: PAM had AUC of 0.80 against 0.72 of partial least squares-discriminant analysis with guideline variables (p = 0.52). The sensitivity (0.86) and specificity (0.75) were better than for guideline alone, sensitivity (0.75) and specificity (0.24). Neural network with guideline variables was better than NB (AUC = 0.93 vs. 0.87) however without statistical significance (p = 0.48). Its sensitivity and specificity (1.0 and 0.75, respectively) were better than guideline alone (0.78 and 0.25, respectively). CONCLUSIONS: Compared to guideline criteria, ML methods trended toward improved CRT response and super-response prediction. GMPS was central in the acquisition of most parameters. Further studies are needed to validate the models.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. de A Fernandes F, Larsen K, He Z, et al. A machine learning method integrating ECG and gated SPECT for cardiac resynchronization therapy decision support. Eur J Nucl Med Mol Imaging. 2023. PMID: 37195444. doi:10.1007/s00259-023-06259-4

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。