Machine learning to predict cardiovascular risk
Machine learning to predict cardiovascular risk
复制标题
DOI：
10.1111/ijcp.13389
复制
发表时间：
2019-08-04
影响因子：
2.6
通讯作者：
Carratala-Munuera, Concepcion
中科院分区：
文献类型：
--
作者：
Quesada, Jose A.;Lopez-Pineda, Adriana;Carratala-Munuera, Concepcion
目的 分析 15 种机器学习方法用于估计队列中心血管风险的预测能力，并将其与其他风险量表进行比较。方法 我们通过 15 种机器学习方法并使用 SCORE 和 REGICOR 量表，对西班牙 ESCARVAL RISK 队列中的 38 527 名患者进行了心血管风险计算，并进行了 5 年随访。当心血管事件的风险超过 5%（根据 SCORE 和机器学习方法）或超过 10%（使用 REGICOR）时，我们认为患者处于高风险。计算受试者工作曲线下面积 (AUC) 和 C 指数，以及诊断准确率、错误率、敏感性、特异性、阳性和阴性预测值、阳性似然比以及预防有害结果所需治疗的数量。结果预测能力最强的是二次判别分析法，AUC为0.7086，其次是朴素贝叶斯法和神经网络法，AUC分别为0.7084和0.7042。 REGICOR 和 SCORE 在预测能力方面分别排名第 11 和第 12，AUC 为 0.63。七种机器学习方法的预测能力 (AUC) 比 REGICOR 和 SCORE 量表高出 7%，灵敏度和特异性也更高。结论 测试的 15 种机器学习方法中有 10 种比西班牙临床实践中常用的 SCORE 和 REGICOR 风险评估量表具有更好的心血管事件预测能力和更好的分类指标。在未来心血管风险量表的开发中应考虑机器学习方法。
Aims To analyse the predictive capacity of 15 machine learning methods for estimating cardiovascular risk in a cohort and to compare them with other risk scales. Methods We calculated cardiovascular risk by means of 15 machine-learning methods and using the SCORE and REGICOR scales and in 38 527 patients in the Spanish ESCARVAL RISK cohort, with 5-year follow-up. We considered patients to be at high risk when the risk of a cardiovascular event was over 5% (according to SCORE and machine learning methods) or over 10% (using REGICOR). The area under the receiver operating curve (AUC) and the C-index were calculated, as well as the diagnostic accuracy rate, error rate, sensitivity, specificity, positive and negative predictive values, positive likelihood ratio, and number needed to treat to prevent a harmful outcome. Results The method with the greatest predictive capacity was quadratic discriminant analysis, with an AUC of 0.7086, followed by Naive Bayes and neural networks, with AUCs of 0.7084 and 0.7042, respectively. REGICOR and SCORE ranked 11th and 12th, respectively, in predictive capacity, with AUCs of 0.63. Seven machine learning methods showed a 7% higher predictive capacity (AUC) as well as higher sensitivity and specificity than the REGICOR and SCORE scales. Conclusions Ten of the 15 machine learning methods tested have a better predictive capacity for cardiovascular events and better classification indicators than the SCORE and REGICOR risk assessment scales commonly used in clinical practice in Spain. Machine learning methods should be considered in the development of future cardiovascular risk scales.