Machine learning approaches improve risk stratification for secondary cardiovascular disease prevention in multiethnic patients.
Machine learning approaches improve risk stratification for secondary cardiovascular disease prevention in multiethnic patients.
复制标题
DOI：
10.1136/openhrt-2021-001802
复制
发表时间：
2021-10
期刊：
影响因子：
2.7
通讯作者：
Rodríguez F
中科院分区：
文献类型：
--
作者：
Sarraju A;Ward A;Chung S;Li J;Scheinker D;Rodríguez F
识别高风险患者对于有效预防心血管疾病（CVD）至关重要。目前尚不清楚基于电子健康记录（EHR）的机器学习（ML）模型与随机临床试验开发的二级预防风险评分（二级预防心肌梗死溶栓风险评分，TRS 2°P）相比是否可以改善CVD风险分层。我们在一个大型卫生系统中确定了CVD患者，包括动脉粥样硬化CVD（ASCVD），分为80%的训练集和20%的测试集。提取了一组丰富的EHR患者特征。训练ML模型以估计5年CVD事件风险（随机森林（RF），梯度增强机器（GBM），极端梯度增强模型（XGBoost），具有L2惩罚和L1惩罚的逻辑回归（Lasso））。通过受试者工作特征曲线下面积（AUC）评价ML模型和TRS 2°P。该队列包括32192例患者（中位年龄74岁，46%为女性，63%为非西班牙裔白色患者，12%为亚洲患者，23475例ASCVD患者）。5年随访期间共发生4010起事件。ML模型表现出良好的总体性能; XGBoost在全CVD队列中表现出AUC 0.70（95% CI 0.68 - 0.71），在ASCVD患者中表现出AUC 0.71（95% CI 0.69 - 0.73），GBM、RF和Lasso的性能相当。TRS 2°P在所有CVD（AUC 0.51，95% CI 0.50 - 0.53）和ASCVD（AUC 0.50，95% CI 0.48 - 0.52）患者中表现较差。ML确定了非传统的预测变量，包括教育水平和初级保健访问。在多种族的真实世界人群中，基于EHR的ML方法显著改善了二级预防的CVD风险分层。
Identifying high-risk patients is crucial for effective cardiovascular disease (CVD) prevention. It is not known whether electronic health record (EHR)-based machine-learning (ML) models can improve CVD risk stratification compared with a secondary prevention risk score developed from randomised clinical trials (Thrombolysis in Myocardial Infarction Risk Score for Secondary Prevention, TRS 2°P). We identified patients with CVD in a large health system, including atherosclerotic CVD (ASCVD), split into 80% training and 20% test sets. A rich set of EHR patient features was extracted. ML models were trained to estimate 5-year CVD event risk (random forests (RF), gradient-boosted machines (GBM), extreme gradient-boosted models (XGBoost), logistic regression with an L2 penalty and L1 penalty (Lasso)). ML models and TRS 2°P were evaluated by the area under the receiver operating characteristic curve (AUC). The cohort included 32 192 patients (median age 74 years, with 46% female, 63% non-Hispanic white and 12% Asian patients and 23 475 patients with ASCVD). There were 4010 events over 5 years of follow-up. ML models demonstrated good overall performance; XGBoost demonstrated AUC 0.70 (95% CI 0.68 to 0.71) in the full CVD cohort and AUC 0.71 (95% CI 0.69 to 0.73) in patients with ASCVD, with comparable performance by GBM, RF and Lasso. TRS 2°P performed poorly in all CVD (AUC 0.51, 95% CI 0.50 to 0.53) and ASCVD (AUC 0.50, 95% CI 0.48 to 0.52) patients. ML identified nontraditional predictive variables including education level and primary care visits. In a multiethnic real-world population, EHR-based ML approaches significantly improved CVD risk stratification for secondary prevention.
登录
查看更多内容
他汀类药物治疗的成年人的残留动脉粥样硬化心血管疾病风险：动脉粥样硬化的多民族研究。
影响因子：
4.4
作者：
Wong ND;Zhao Y;Quek RGW;Blumenthal RS;Budoff MJ;Cushman M;Garg P;Sandfort V;Tsai M;Lopez JAG
通讯作者：
Lopez JAG
影响因子：
6.3
作者：
Dalton, Jarrod E.;Rothberg, Michael B.;Perzynski, Adam T.
通讯作者：
Perzynski, Adam T.
影响因子：
39.3
作者：
Rapsomaniki E;Shah A;Perel P;Denaxas S;George J;Nicholas O;Udumyan R;Feder GS;Hingorani AD;Timmis A;Smeeth L;Hemingway H
通讯作者：
Hemingway H
影响因子：
5.4
作者：
Nguyen QD;Odden MC;Peralta CA;Kim DH
通讯作者：
Kim DH
影响因子：
24
作者：
van den Ham, Hendrika A.;Klungel, Olaf H.;van Staa, Tjeerd P.
通讯作者：
van Staa, Tjeerd P.