文献速递心脏核医学肿瘤 PET/CT

基于钙化评分、PET显像与临床数据的机器学习模型诊断阻塞性冠状动脉疾病

Machine learning based model to diagnose obstructive coronary artery disease using calcium scoring, PET imaging, and clinical data.
PubMed 文献 · J Nucl Cardiol · 2023-01-09

本研究回顾性纳入1007例无既往冠状动脉疾病史、接受CT钙化评分(CACS)和铷-82 PET扫描的患者,按4:1分为训练集与测试集,开发并验证机器学习(ML)模型诊断阻塞性CAD(oCAD),以有创冠状动脉造影(ICA)为终点。训练集AUC为0.92(95%CI 0.90-0.94),测试集AUC为0.89(95%CI 0.84-0.93);ML模型与专家读者在准确率(89% vs 88%)、敏感度(68% vs 69%)和特异度(92% vs 90%)上无显著差异(p≥0.03)。作者认为ML模型诊断性能与专家读者相似,可能作为oCAD的风险分层工具。

要点

  • 训练集AUC 0.92(95%CI 0.90-0.94),测试集AUC 0.89(95%CI 0.84-0.93)。
  • ML模型与专家读者准确率89% vs 88%、敏感度68% vs 69%、特异度92% vs 90%,无显著差异(p≥0.03)。
  • 作者认为ML模型可能作为阻塞性CAD的风险分层工具。

核心结论

  • ML模型诊断性能与专家读者相似,可能作为阻塞性CAD的风险分层工具。
  • 本研究显示ML在阻塞性CAD诊断中的应用具有前景。

研究设计与样本

  • 回顾性纳入1007例无既往冠状动脉疾病史、接受CT钙化评分(CACS)和铷-82 PET扫描的患者。
  • 整个数据集按4:1分为训练集与测试集,训练集采用五折分层交叉验证开发ML模型。
  • 测试集用于比较专家读者与模型的诊断性能,主要终点为有创冠状动脉造影(ICA)诊断的阻塞性CAD(oCAD)。

主要发现

  • ROC曲线分析显示训练集AUC为0.92(95%CI 0.90-0.94),测试集AUC为0.89(95%CI 0.84-0.93)。
  • ML模型与专家读者相比,准确率89% vs 88%、敏感度68% vs 69%、特异度92% vs 90%,无显著差异(p≥0.03)。

关键数值与推荐

  • 训练集AUC 0.92(95%CI 0.90-0.94)。
  • 测试集AUC 0.89(95%CI 0.84-0.93)。
  • ML模型与专家读者准确率89% vs 88%、敏感度68% vs 69%、特异度92% vs 90%,p≥0.03。

临床怎么用

  • 作者认为ML模型可能作为阻塞性CAD的风险分层工具。

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)。

原文

INTRODUCTION: Accurate risk stratification in patients with suspected stable coronary artery disease is essential for choosing an appropriate treatment strategy. Our aim was to develop and validate a machine learning (ML) based model to diagnose obstructive CAD (oCAD). METHOD: We retrospectively have included 1007 patients without a prior history of CAD who underwent CT-based calcium scoring (CACS) and a Rubidium-82 PET scan. The entire dataset was split 4:1 into a training and test dataset. An ML model was developed on the training set using fivefold stratified cross-validation. The test dataset was used to compare the performance of expert readers to the model. The primary endpoint was oCAD on invasive coronary angiography (ICA). RESULTS: ROC curve analysis showed an AUC of 0.92 (95% CI 0.90-0.94) for the training dataset and 0.89 (95% CI 0.84-0.93) for the test dataset. The ML model showed no significant differences as compared to the expert readers (p ≥ 0.03) in accuracy (89% vs. 88%), sensitivity (68% vs. 69%), and specificity (92% vs. 90%). CONCLUSION: The ML model resulted in a similar diagnostic performance as compared to expert readers, and may be deployed as a risk stratification tool for obstructive CAD. This study showed that utilization of ML is promising in the diagnosis of obstructive CAD.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. van Dalen JA, Koenders SS, Metselaar RJ, et al. Machine learning based model to diagnose obstructive coronary artery disease using calcium scoring, PET imaging, and clinical data. J Nucl Cardiol. 2023. PMID: 36622542. doi:10.1007/s12350-022-03166-3

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。