机器学习整合CT衰减扫描的冠状动脉钙化评分改善接受SPECT/CT心肌灌注显像患者的不良心血管事件预测
研究基于REFINE SPECT注册中心单中心4770例接受SPECT/CT心肌灌注显像的患者,评估将CT衰减扫描的冠状动脉钙化(CAC)评分纳入机器学习(XGBoost)模型是否改善主要不良心血管事件(MACE)预测。中位随访24.1个月期间475例(10%)发生MACE,含CAC的CAC-ML评分ROC曲线下面积0.77(95%CI 0.75-0.79),高于不含CAC的ML评分0.75(95%CI 0.73-0.77,P=.005)及单独CAC评分0.71(95%CI 0.68-0.73,P<.001)。
要点
- 含CAC的CAC-ML评分预测MACE的AUC为0.77,高于不含CAC的ML评分0.75和单独CAC评分0.71。
- CAC-ML评分>0.091的患者事件率高于低评分患者(HR 5.3,95%CI 4.3-6.5,P<.001)。
- 在临床、影像和负荷参数中,CAC评分对ML模型的变量重要性最高。
核心结论
- 将衰减CT的CAC评分整合入机器学习风险评分可改善接受SPECT MPI患者MACE预测的预测价值。
研究设计与样本
- 来自REFINE SPECT注册中心的单中心4770例接受SPECT/CT的患者(年龄64±12岁,45%女性)。
- 机器学习算法(XGBoost)输入包括临床危险因素、负荷变量、SPECT影像参数和专家观察者基于CT衰减校正扫描的CAC评分。
- 采用十折留出法验证训练ML模型,用ROC曲线分析MACE预测,并用标准生存分析评估无MACE生存。
主要发现
- 中位随访24.1个月期间,475例患者(10%)发生MACE。
- CAC-ML评分预测MACE的AUC为0.77(95%CI 0.75-0.79),高于不含CAC的ML评分0.75(95%CI 0.73-0.77,P=.005)。
- CAC-ML评分AUC 0.77(95%CI 0.75-0.79)高于单独CAC评分0.71(95%CI 0.68-0.73,P<.001)。
- 在临床、影像和负荷参数中,CAC评分对ML模型的变量重要性最高。
- CAC-ML评分>0.091的患者事件率高于低CAC-ML评分患者(HR 5.3,95%CI 4.3-6.5,P<.001)。
临床怎么用
- 原文未据此给出推荐。
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
BACKGROUND: Machine learning (ML) has been previously applied for prognostication in patients undergoing SPECT myocardial perfusion imaging (MPI). We evaluated whether including attenuation CT coronary artery calcification (CAC) scoring improves ML prediction of major adverse cardiovascular events (MACE) in patients undergoing SPECT/CT MPI. METHODS: From the REFINE SPECT Registry 4770 patients with SPECT/CT performed at a single center were included (age: 64 ± 12 years, 45% female). ML algorithm (XGBoost) inputs were clinical risk factors, stress variables, SPECT imaging parameters, and expert-observer CAC scoring using CT attenuation correction scans performed to obtain CT attenuation maps. The ML model was trained and validated using tenfold hold-out validation. Receiver Operator Characteristics (ROC) curves were analyzed for prediction of MACE. MACE-free survival was evaluated with standard survival analyses. RESULTS: During a median follow-up of 24.1 months, 475 patients (10%) experienced MACE. Higher area under the ROC curve for MACE was observed with ML when CAC scoring was included (CAC-ML score, 0.77, 95% confidence interval [CI] 0.75-0.79) compared to ML without CAC (ML score, 0.75, 95% CI 0.73-0.77, P = .005) and when compared to CAC score alone (0.71, 95% CI 0.68-0.73, P < .001). Among clinical, imaging, and stress parameters, CAC score had highest variable importance for ML. On survival analysis patients with high CAC-ML score (> 0.091) had higher event rate when compared to patients with low CAC-ML score (hazard ratio 5.3, 95% CI 4.3-6.5, P < .001). CONCLUSION: Integration of attenuation CT CAC scoring improves the predictive value of ML risk score for MACE prediction in patients undergoing SPECT MPI.
引用
- Feher A, Pieszko K, Miller R, et al. Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging. J Nucl Cardiol. 2022. PMID: 36195826. doi:10.1007/s12350-022-03099-x
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。