冠心病气阴两虚证临床预测模型的构建与验证  

Construction and Verification of Clinical Prediction Model for Qi-Yin Deficiency Syndrome of Coronary Heart Disease

作　　者：陈浩然 王远红[2] 王伟蔚 王科军[1] CHEN Haoran;WANG Yuanhong;WANG Weiwei;WANG Kejun(School of Traditional Chinese Medicine,Binzhou Medical University,Yantai Shandong 264003,China;First Affiliated Hospital,Heilongjiang University of Chinese Medicine,Harbin Heilongjiang 150000,China;Dongying Hospital Affiliated to Shandong University of Traditional Chinese Medicine,Dongying Shandong 257000,China)

机构地区：[1]滨州医学院中医学院,山东烟台264003 [2]黑龙江中医药大学附属第一医院,黑龙江哈尔滨150000 [3]山东中医药大学附属东营医院,山东东营257000

出　　处：《中医药导报》2024年第12期67-72,共6页Guiding Journal of Traditional Chinese Medicine and Pharmacy

基　　金：国家自然科学基金面上项目(81873312);黑龙江省自然科学基金联合引导项目(JJ2022LH1048)。

摘　　要：目的:构建和验证冠心病气阴两虚证临床预测模型,以期辅助临床辨证,为冠心病气阴两虚证的辨证诊疗提供参考。方法:回顾性收集2022年1月至2024年1月于山东中医药大学附属东营医院就诊的176例冠心病患者的临床资料,通过LASSO-多因素Logistic回归的方式构建模型,并通过绘制受试者工作特征曲线(ROC)、校正曲线和临床决策曲线(DCA)对模型进行评价。结果:经过LASSO-多因素Logistic回归分析,年龄、糖尿病、左室射血分数和空腹血糖为纳入模型中的特征,高龄、糖尿病和高空腹血糖是患者被诊断为气阴两虚证的危险因素,高左室射血分数是患者被诊断为气阴两虚证的保护性因素。训练组中模型的曲线下面积(AUC)为0.829[95%CI(0.755,0.903)],验证组中模型的AUC为0.775[95%CI(0.631,0.918)],校正曲线显示模型的预测曲线与实际观测曲线较为接近,DCA显示模型在小于0.8的决策阈值下能够为患者提供临床收益。结论:本研究构建的冠心病气阴两虚证临床预测模型效能较好,能够为冠心病气阴两虚证的辨证诊疗提供一定程度的参考价值。Objective:To construct and validate a clinical prediction model for Qi-Yin deficiency syndrome in coronary heart disease,aiming to assist in clinical syndrome differentiation and provide a reference for the diagnosis and treatment of Qi-Yin deficiency syndrome in coronary heart disease.Methods:A retrospective collection of clinical data from 176 coronary heart disease patients who visited Dongying Hospital Affiliated to Shandong University of Traditional Chinese Medicine from January 2022 to January 2024 was conducted.The model was constructed using the Lasso-Multifactorial Logistic Regression method and evaluated by plotting the receiver operating characteristic curve(ROC),calibration curve,and decision curve analysis dynamic(DCA).Results:The Lasso-Multifactorial Logistic Regression analysis identified age,diabetes,left ventricular ejection fraction,and fasting blood glucose as characteristics included in the model.Advanced age,diabetes,and high fasting blood glucose were risk factors for the diagnosis of Qi-Yin deficiency syndrome,while a high left ventricular ejection fraction was a protective factor.The area under the curve(AUC) of the model in the training group was 0.829 [95% CI(0.755,0.903)],and the AUC in the validation group was 0.775 [95% CI(0.631,0.918)].The calibration curve showed that the model's predictive curve was close to the actual observed curve,and the DCA indicated that the model could provide clinical benefits to patients at a decision threshold below 0.8.Conclusion:The clinical prediction model for Qi-Yin deficiency syndrome in coronary heart disease constructed in this study has good performance,and can provide a certain reference for the syndrome differentiation and treatment of Qi-Yin deficiency syndrome in coronary heart disease.

关 键 词：冠心病 气阴两虚证 列线图 临床预测模型 

分 类 号：R241.8[医药卫生—中医诊断学]