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
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.
引用
- 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。