当前位置: X-MOL 学术Eur. Heart J. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry
European Heart Journal ( IF 37.6 ) Pub Date : 2019-09-12 , DOI: 10.1093/eurheartj/ehz565
Subhi J Al'Aref 1 , Gabriel Maliakal 1 , Gurpreet Singh 1 , Alexander R van Rosendael 1 , Xiaoyue Ma 2 , Zhuoran Xu 1 , Omar Al Hussein Alawamlh 1 , Benjamin Lee 1 , Mohit Pandey 1 , Stephan Achenbach 3 , Mouaz H Al-Mallah 4 , Daniele Andreini 5 , Jeroen J Bax 6 , Daniel S Berman 7 , Matthew J Budoff 8 , Filippo Cademartiri 9 , Tracy Q Callister 10 , Hyuk-Jae Chang 11 , Kavitha Chinnaiyan 12 , Benjamin J W Chow 13 , Ricardo C Cury 14 , Augustin DeLago 15 , Gudrun Feuchtner 16 , Martin Hadamitzky 17 , Joerg Hausleiter 18 , Philipp A Kaufmann 19 , Yong-Jin Kim 20 , Jonathon A Leipsic 21 , Erica Maffei 22 , Hugo Marques 23 , Pedro de Araújo Gonçalves 23 , Gianluca Pontone 5 , Gilbert L Raff 12 , Ronen Rubinshtein 24 , Todd C Villines 25 , Heidi Gransar 7 , Yao Lu 2 , Erica C Jones 1 , Jessica M Peña 1 , Fay Y Lin 1 , James K Min 1 , Leslee J Shaw 1
Affiliation  

AIMS Symptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model, utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA). METHODS AND RESULTS The study screened 35 281 participants enrolled in the CONFIRM registry, who underwent ≥64 detector row CCTA evaluation because of either suspected or previously established CAD. A boosted ensemble algorithm (XGBoost) was used, with data split into a training set (80%) on which 10-fold cross-validation was done and a test set (20%). Performance was assessed of the (1) ML model (using 25 clinical and demographic features), (2) ML + CACS, (3) CAD consortium clinical score, (4) CAD consortium clinical score + CACS, and (5) updated Diamond-Forrester (UDF) score. The study population comprised of 13 054 patients, of whom 2380 (18.2%) had obstructive CAD (≥50% stenosis). Machine learning with CACS produced the best performance [area under the curve (AUC) of 0.881] compared with ML alone (AUC of 0.773), CAD consortium clinical score (AUC of 0.734), and with CACS (AUC of 0.866) and UDF (AUC of 0.682), P < 0.05 for all comparisons. CACS, age, and gender were the highest ranking features. CONCLUSION A ML model incorporating clinical features in addition to CACS can accurately estimate the pretest likelihood of obstructive CAD on CCTA. In clinical practice, the utilization of such an approach could improve risk stratification and help guide downstream management.

中文翻译:


临床变量和冠状动脉钙评分的机器学习用于预测冠状动脉计算机断层扫描血管造影中的阻塞性冠状动脉疾病:来自 CONFIRM 注册中心的分析



目的 基于症状的预测概率评分​​可估计稳定胸痛中阻塞性冠状动脉疾病 (CAD) 的可能性,具有中等准确性。我们试图开发一种机器学习 (ML) 模型,利用临床因素和冠状动脉钙化评分 (CACS),通过冠状动脉计算机断层扫描血管造影 (CCTA) 预测阻塞性 CAD 的存在。方法和结果 该研究筛选了登记在 CONFIRM 注册表中的 35 281 名参与者,这些参与者因怀疑或既往患有 CAD 而接受了≥64 排探测器的 CCTA 评估。使用增强型集成算法 (XGBoost),将数据分为训练集 (80%) 和测试集 (20%),在训练集上进行 10 倍交叉验证。性能评估包括 (1) ML 模型(使用 25 种临床和人口统计特征)、(2) ML + CACS、(3) CAD 联合临床评分、(4) CAD 联合临床评分 + CACS 和 (5) 更新的 Diamond -Forrester (UDF) 分数。研究人群包括 13054 名患者,其中 2380 名(18.2%)患有阻塞性 CAD(狭窄≥50%)。与单独的 ML(AUC 为 0.773)、CAD 联合临床评分(AUC 为 0.734)以及 CACS(AUC 为 0.866)和 UDF 相比,CACS 的机器学习产生了最佳性能 [曲线下面积 (AUC) 为 0.881]。 AUC 为 0.682),所有比较的 P < 0.05。 CACS、年龄和性别是排名最高的特征。结论 除了 CACS 之外,结合临床特征的 ML 模型可以准确估计 CCTA 上阻塞性 CAD 的预测可能性。在临床实践中,利用这种方法可以改善风险分层并有助于指导下游管理。
更新日期:2019-09-12
down
wechat
bug