基于可穿戴设备量化分析急性心衰患者夜间呼吸模式的探索性研究  

Exploratory study on quantitative analysis of nocturnal breathing patterns in patients with acute heart failure based on wearable devices

作　　者：李梦伟 亢玉[2] 寇宇晴 赵双琳 张秀 邱丽叡 颜伟 喻鹏铭[4] 张庆[2] 张政波[7] LI Mengwei;KANG Yu;KOU Yuqing;ZHAO Shuanglin;ZHANG Xiu;QIU Lirui;YAN Wei;YU Pengming;ZHANG Qing;ZHANG Zhengbo(Medical School of Chinese PLA,Beijing 100853,P.R.China;Department of Cardiology,West China Hospital of Sichuan University,Chengdu 610041,P.R.China;Department of Medical Engineering,the 72nd Group Army Hospital of CPLA,Huzhou,Zhejiang 313000,P.R.China;Rehabilitation Medical Center,West China Hospital of Sichuan University,Chengdu 610041,P.R.China;School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876,P.R.China;Department of Hyperbaric Oxygen,the First Medical Center,Chinese PLA General Hospital,Beijing 100853,P.R.China;Center for Artificial Intelligence in Medicine,Chinese PLA General Hospital,Beijing 100853,P.R.China)

机构地区：[1]中国人民解放军医学院,北京100853 [2]四川大学华西医院心脏内科,成都610041 [3]中国人民解放军陆军第七十二集团军医院医学工程科,浙江湖州313000 [4]四川大学华西医院康复医学中心,成都610041 [5]北京邮电大学人工智能学院,北京100876 [6]中国人民解放军总医院第一医学中心高压氧科,北京100853 [7]中国人民解放军总医院医学人工智能研究中心,北京100853

出　　处：《生物医学工程学杂志》2023年第6期1108-1116,共9页Journal of Biomedical Engineering

基　　金：国家自然科学基金面上项目(62171471);保健专项科研课题面上项目(22BJZ42)。

摘　　要：急性心力衰竭(AHF)患者常伴呼吸困难,对患者的呼吸模式进行监测和量化分析可为病情和预后评估提供参考信息。本文纳入39例AHF患者和24例健康受试者,采用可穿戴设备收集其夜间胸腹呼吸信号,并量化分析两组人群夜间呼吸模式的差异。与健康组相比,AHF组的呼吸率(BR)均值更高[(21.03±3.84)次/分vs.(15.95±3.08)次/分,P<0.001],相对浅快呼吸指数变异系数更大[70.96%(54.34%~104.28)%vs.58.48%(45.34%~65.95)%,P=0.005],腹呼吸贡献比变异系数更大[(22.52±7.14)%vs.(17.10±6.83)%,P=0.004],呼吸率样本熵更小(0.67±0.37 vs.1.01±0.29,P<0.001);此外,吸气(TI)和呼气(TE)时间均值更短、变异系数更大,劳累呼吸指数变异系数更大,庞加莱图SD1、SD2更大,以上指标的两组间差异均有统计学意义。使用Logistic回归校准发现TI均值降低是AHF的危险因素。BR均值区分两组人群的能力最强,曲线下面积(AUC)为0.846。结果表明呼吸周期、幅度、协调性和非线性参数等能够有效量化AHF患者的异常呼吸模式,其中TI均值降低是AHF的危险因素,呼吸率均值区分两组人群的能力最强。以上结果有望为心衰患者病情评估提供新的信息。Patients with acute heart failure(AHF)often experience dyspnea,and monitoring and quantifying their breathing patterns can provide reference information for disease and prognosis assessment.In this study,39 AHF patients and 24 healthy subjects were included.Nighttime chest-abdominal respiratory signals were collected using wearable devices,and the differences in nocturnal breathing patterns between the two groups were quantitatively analyzed.Compared with the healthy group,the AHF group showed a higher mean breathing rate(BR_mean)[(21.03±3.84)beat/min vs.(15.95±3.08)beat/min,P<0.001],and larger R_RSBI_cv[70.96%(54.34%–104.28)%vs.58.48%(45.34%–65.95)%,P=0.005],greater AB_ratio_cv[(22.52±7.14)%vs.(17.10±6.83)%,P=0.004],and smaller SampEn(0.67±0.37 vs.1.01±0.29,P<0.001).Additionally,the mean inspiratory time(TI_mean)and expiration time(TE_mean)were shorter,TI_cv and TE_cv were greater.Furthermore,the LBI_cv was greater,while SD1 and SD2 on the Poincare plot were larger in the AHF group,all of which showed statistically significant differences.Logistic regression calibration revealed that the TI_mean reduction was a risk factor for AHF.The BR_mean demonstrated the strongest ability to distinguish between the two groups,with an area under the curve(AUC)of 0.846.Parameters such as breathing period,amplitude,coordination,and nonlinear parameters effectively quantify abnormal breathing patterns in AHF patients.Specifically,the reduction in TI_mean serves as a risk factor for AHF,while the BR_mean distinguishes between the two groups.These findings have the potential to provide new information for the assessment of AHF patients.

关 键 词：急性心力衰竭 呼吸模式量化 可穿戴设备 

分 类 号：R541.6[医药卫生—心血管疾病] TP368.33[医药卫生—内科学]