基于常见临床数据的冠心病诊断模型构建  被引量:2

Develop a cardiovascular model for the presence of coronary artery disease from routine clinical data

在线阅读下载全文

作  者:徐洪增[1] 段志英[1] 耿松[1] 王勇[1] 苗驰[1] 李洋[2] 胡圣大[3] 金元哲[1] 刘乃丰[2] 

机构地区:[1]中国医科大学附属第四医院心内科,辽宁沈阳110032 [2]东南大学附属中大医院心内科,江苏南京210009 [3]苏州大学附属第一医院心内科,江苏苏州215006

出  处:《现代医学》2016年第5期622-626,共5页Modern Medical Journal

摘  要:目的:基于大量冠心病(coronary artery disease,CAD)患者常见临床数据构建CAD预测模型。方法:从多个心脏病学中心随机收集5 937例行冠状动脉造影检查的患者,根据年龄、性别、胸痛、糖尿病、高血压、高脂血症及吸烟史等7个常见临床指标进行CAD预测模型构建。结果:3 924例患者(66.1%)有冠状动脉粥样硬化狭窄,2 013例患者无明显冠状动脉狭窄。所有的预测因子均与CAD显著相关。该模型能够比较准确地诊断CAD,其受试者工作曲线(receiver operating characteristic curve,ROC)曲线下面积(area under roc curve,AUC)为0.74,对CAD诊断的最佳截断值为0.668,敏感性和特异性分别为0.767和0.692。心绞痛的加入提高了预测模型的准确性。结论:从常规临床变量中开发的个体化CAD模型能够提供CAD相关预测依据。该模型或许能够提供CAD诊断决策支持帮助医生管理CAD病人。Objective: To construct a coronary artery disease( CAD) prediction model based on routine clinical data from a large amount of patients. Methods: This study included 5 937 consecutive patients who underwent coronary angiography for evaluation of CAD. A predictive model was constructed for diagnosis of CAD with the help of seven common risk factors such as age,sex,angina,diabetes,hypertension,hyperlipidaemia and smoking.Results: 3 924 patients( 66. 1%) had coronary artery stenosis,while 2 013 patients had no coronary artery stenosis. All potential predictors were significantly associated with the presence of CAD. This model gives a relative accurate prediction of CAD with the AUC of 0. 74. The optimal cut-off for prediction of CAD of this model was0. 668 with a sensitivity of 0. 767 and a specificity of 0. 692. Addition of angina to the prediction model improved the accurracy. Conclusion: Updated prediction model from routine clinical characters allows for accurate estimation of the pretest probability of coronary artery disease. This algorithm may be useful in making decisions that help physicians to administrating CAD patients.

关 键 词:动脉粥样硬化 诊断模型 风险因素 大数据 

分 类 号:R543.31[医药卫生—心血管疾病]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象