Prediction of revascularization after myocardial perfusion SPECT by machine learning in a large population.
Prediction of revascularization after myocardial perfusion SPECT by machine learning in a large population.
复制标题
DOI：
10.1007/s12350-014-0027-x
复制
发表时间：
2015-10
期刊：
影响因子：
--
通讯作者：
Slomka P
中科院分区：
文献类型：
--
作者：
Arsanjani R;Dey D;Khachatryan T;Shalev A;Hayes SW;Fish M;Nakanishi R;Germano G;Berman DS;Slomka P
我们旨在通过机器学习（ML）方法整合临床数据和灌注SPECT （MPS）获得的定量图像特征，研究是否可以有效预测疑似冠状动脉疾病（CAD）患者的早期血运重建。研究人员考虑了有创血管造影(MPS后90天内发生372例血运重建术（275例PCI / 97例CABG）（91%在30天内发生）与铊/应激相关的锝MPS研究。短暂性脑缺血扩张（TID）、应激合并仰卧/俯卧位总灌注缺陷（TPD）、定量休息和应激TPD、运动射血分数、收缩期终容积以及临床参数，包括患者性别、高血压和糖尿病史、基线心电图st段抑郁、应激时的心电图和临床反应，以及通过增强集合ML算法（LogitBoost）预测血运重建事件的ECG后概率。使用自动特征选择算法从所有可用的临床和定量数据（33个参数）中选择这些特征。采用10倍交叉验证对预测模型进行训练和检验。通过ML算法预测血运重建与独立的灌注测量和视觉分析进行比较，由两位经验丰富的读者利用所有成像，定量和临床数据。机器学习预测血运重建的敏感性（73.6±4.3%）与单一阅读器（73.9±4.6%）和独立灌注测量（75.5±4.5%）相似。机器学习的特异性（74.7±4.2%）也优于专家阅读者（67.2±4.9%和66.0±5.0%,P < 0.05），但与缺血性TPD相似（68.3±4.9%,P < 0.05）。机器学习的接受者-操作者-特征曲线下面积（0.81±0.02）与阅读器1（0.81±0.02）相似，但优于阅读器2（0.72±0.02,P < 0.01）和单独的灌注测量（0.77±0.02,P < 0.01）。ML方法在预测MPS后早期血运重建方面与经验丰富的读者相当或更好，并且明显优于MPS衍生的灌注单独测量。
We aimed to investigate if early revascularization in patients with suspected coronary artery disease (CAD) can be effectively predicted by integrating clinical data and quantitative image features derived from perfusion SPECT (MPS) by machine learning (ML) approach. 713 rest 201Thallium/stress 99mTechnetium MPS studies with correlating invasive angiography (372 revascularization events (275 PCI / 97 CABG) within 90 days after MPS (91% within 30 days) were considered. Transient ischemic dilation (TID), stress combined supine/prone total perfusion deficit (TPD), quantitative rest and stress TPD, exercise ejection fraction, and end-systolic volume along with clinical parameters including patient gender, history of hypertension and diabetes mellitus, ST-depression on baseline ECG, ECG and clinical response during stress, and post-ECG probability by boosted ensemble ML algorithm (LogitBoost) to predict revascularization events. These features were selected using an automated feature selection algorithm from all available clinical and quantitative data (33 parameters). 10-fold cross-validation was utilized to train and test the prediction model. The prediction of revascularization by ML algorithm was compared to standalone measures of perfusion and visual analysis by two experienced readers utilizing all imaging, quantitative, and clinical data. The sensitivity of machine learning (73.6±4.3%) for prediction of revascularization was similar to one reader (73.9±4.6%) and standalone measures of perfusion (75.5±4.5%). The specificity of machine learning (74.7±4.2%) was also better than both expert readers (67.2±4.9% and 66.0±5.0%, P < 0.05), but was similar to ischemic TPD (68.3±4.9%, P < 0.05). The Receiver-Operator-Characteristics areas-under-curve for machine learning (0.81±0.02) was similar to reader 1 (0.81±0.02) but superior to reader 2 (0.72±0.02, P < 0.01) and standalone measure of perfusion (0.77±0.02, P < 0.01). ML approach is comparable or better than experienced reader in prediction of the early revascularization after MPS and is significantly better than standalone measures of perfusion derived from MPS.