摘要
背景心率变异性(heart rate variability,HRV)作为评估自主神经系统活性的重要指标,已被广泛用作心力衰竭患者预后的评估工具。NT-proBNP作为一种标志物,在心衰的诊断、风险分层及预后评估中发挥着至关重要的作用,但其检测依赖侵入性操作且难以动态监测。目的探讨可穿戴设备监测的HRV参数与NT-proBNP水平的相关性,并验证其作为无创风险分层工具的可行性。方法本研究利用可穿戴设备收集了2021年1月—2022年12月四川大学华西医院心内科的急性心衰患者入院、出院时的24 h心电数据,经过预处理后提取了HRV参数,以NT-proBNP≥3500 pmol/L为高风险截断值,采用Spearman相关分析探究HRV与NT-proBNP的关联性,评估逻辑回归、K最近邻(K-nearest neighbors,KNN)、支持向量机(support vector machine,SVM)、随机森林和XGBoost五种机器学习模型预测不良预后(NT-proBNP≥3500 pmol/L)的效能,并通过SHAP值量化特征贡献度。结果共纳入51例心衰患者,收集心电数据87份。HRV参数中,SDNN、SD2、VLF等10项指标与NT-proBNP呈显著负相关(r:-0.390~-0.371,P<0.001)。NT-proBNP水平≥3500 pmol/L的患者HRV参数SDNN[M(IQR):51.10(38.50~67.20)ms vs 77.95(54.45~95.50)ms,P<0.001]、SD2[M(IQR):68.30(52.90~93.90)ms vs 108.00(76.20~132.47)ms,P=0.003]、VLF[M(IQR):18.82(5.84~59.61)mHz vs 59.36(33.70~116.90)mHz,P=0.002]、ULF[M(IQR):6.30(1.99~18.02)mHz vs 18.60(10.05~34.09)mHz,P=0.001]均显著低于NT-proBNP<3500 pmol/L组,差异有统计学意义。机器学习模型中,Logistic回归分类性能最优(AUC=0.830,95%CI:0.760~0.890),SHAP分析显示SD2和LF/HF贡献度较高。结论可穿戴HRV参数与NT-proBNP水平显著相关,且能够通过机器学习模型有效区分NT-proBNP高低水平组,为心衰患者的无创动态监测及急性失代偿风险预测提供了新的参考。
Background Heart rate variability(HRV),an indicator of autonomic nervous system activity,is widely recognized for assessing heart failure prognosis.N-terminal pro-B-type natriuretic peptide(NT-proBNP)plays a crucial role in the diagnosis,risk stratification,and prognosis evaluation of heart failure,but its measurement relies on invasive procedures and lacks dynamic monitoring capabilities.Objective To explore the correlation between wearable HRV parameters and NT-proBNP levels and validate their feasibility as a non-invasive risk stratification tool.Methods The 24-hour wearable device physiological data and clinical indicators were collected from acute heart failure patients admitted to the Department of Cardiology,West China Hospital,Sichuan University,from January 2021 to December 2022.Post preprocessing,HRV parameters were extracted,and a threshold of 3500 pmol/L was established for NT-proBNP levels.Spearman correlation was used to analyze the association between HRV and NT proBNP,and the efficacy of five machine learning models including Logistic Regression,K-Nearest Neighbor(KNN),Support Vector Machine(SVM),Random Forest and XGBoost to predict poor prognosis(NT proBNP≥3500 pmol/L)was evaluated,and the characteristic contribution was quantified by the snap value.Results A total of 51 heart failure patients were included,with 87 electrocardiographic datasets collected.Among the HRV parameters,SDNN,SD2,VLF,and 7 other indexes showed significant negative correlations with NT-proBNP levels(r:-0.390 to-0.371,P<0.001).Patients with NT-proBNP≥3500 pmol/L had significantly lower HRV parameters,including SDNN(M[IQR]:51.10[38.50-67.20]ms vs 77.95[54.45-95.50]ms,P<0.001),SD2(M[IQR]:68.30[52.90-93.90]ms vs 108.00[76.20-132.47]ms,P=0.003),VLF(M[IQR]:18.82[5.84-59.61]mHz vs 59.36[33.70-116.90]mHz,P=0.002),ULF(M[IQR]:6.30[1.99-18.02]mHz vs 18.60[10.05-34.09]mHz,P=0.001).Among the machine learning models,Logistic Regression demonstrated the best classification performance(AUC=0.830,95%CI:0.760-0.890).SHAP analysis revealed that SD2 and LF/HF contributed the most to the model's classification.Conclusion Wearable HRV parameters are significantly correlated with NT-proBNP levels and can effectively differentiate high and low NT-proBNP groups using machine learning models,offering a new strategy for non-invasive dynamic monitoring and acute decompensation risk prediction in heart failure patients.
作者
时颖
张秀
夏万能
张越
张庆
张政波
SHI Ying;ZHANG Xiu;XIA Wanneng;ZHANG Yue;ZHANG Qing;ZHANG Zhengbo(Chinese PLA Medical School,Beijing 100853,China;Department of Cardiology,West China Hospital of Sichuan University,Chengdu 610041,Sichuan Province,China;Medical Innovation Research Department of PLA General Hospital,Beijing 100853,China)
出处
《解放军医学院学报》
2025年第3期256-261,F0003,共7页
Academic Journal of Chinese PLA Medical School
基金
国家自然科学基金项目(62171471)。
