CN1117331C - 非侵入诊断心血管及相关疾病的方法和仪器 - Google Patents

非侵入诊断心血管及相关疾病的方法和仪器 Download PDF

Info

Publication number
CN1117331C
CN1117331C CN99805707A CN99805707A CN1117331C CN 1117331 C CN1117331 C CN 1117331C CN 99805707 A CN99805707 A CN 99805707A CN 99805707 A CN99805707 A CN 99805707A CN 1117331 C CN1117331 C CN 1117331C
Authority
CN
China
Prior art keywords
signal
neural network
pulse
angiosthenia
cardiovascular
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN99805707A
Other languages
English (en)
Other versions
CN1299486A (zh
Inventor
G·K·Y·科
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SARRUS BIOMEDICAL Ltd
Original Assignee
SARRUS BIOMEDICAL Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by SARRUS BIOMEDICAL Ltd filed Critical SARRUS BIOMEDICAL Ltd
Publication of CN1299486A publication Critical patent/CN1299486A/zh
Application granted granted Critical
Publication of CN1117331C publication Critical patent/CN1117331C/zh
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B7/00Instruments for auscultation
    • A61B7/02Stethoscopes
    • A61B7/04Electric stethoscopes
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024Detecting, measuring or recording pulse rate or heart rate
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/41Detecting, measuring or recording for evaluating the immune or lymphatic systems
    • A61B5/411Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7253Details of waveform analysis characterised by using transforms
    • A61B5/726Details of waveform analysis characterised by using transforms using Wavelet transforms
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235Details of waveform analysis
    • A61B5/7264Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7225Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S128/00Surgery
    • Y10S128/03Heart-lung
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S128/00Surgery
    • Y10S128/92Computer assisted medical diagnostics
    • Y10S128/925Neural network

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Physiology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Acoustics & Sound (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Cardiology (AREA)
  • Vascular Medicine (AREA)
  • Immunology (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

非侵入诊断心血管和相关疾病的仪器和方法。该系统在动脉压脉冲的波形轮廓的动力学与相关病症状态之间建立对应关系。系统包括输入模块、轮廓信号接收器和处理模块。输入模块使用压力传感器获取动脉脉冲的非侵入测量结果。轮廓信号接收器对动脉压脉冲信号进行放大、数字化和归一化。在处理模块中,使归一化的动脉压脉冲轮廓经受子波分析,后者将动脉血压轮廓的时间序列的动力学变换成多分辨率子波系数或标记。处理模块包括神经网络,后者训练成使得嵌入在系数中的变换动脉压轮廓的诊断特征与疾病症状相联系。经学习阶段后,该系统能诊断出患者中已知心血管症症状。

Description

非侵入诊断心血管及相关疾病的方法和仪器
发明领域
本发明涉及心血管疾病及相关异常性的非侵入诊断。本发明尤其涉及通过测量和解释动脉压脉冲轮廓来诊断心血管疾病的方法和仪器。
发明背景
诊断心血管和相关疾病的方法可分为侵入诊断和非侵入诊断两类。侵入心血管诊断法是涉及渗入皮肤或体孔的那些方法。该类方法包括插入导管和施加放射性的药剂至体内。非浸入心血管诊断法并不涉及渗入皮肤或体孔。该类方法包括作体检/心电图以及各种形式的图像检查。
侵入心血管诊断法已获得广泛应用,因它们在诊断心血管病方面习惯上比非侵入心血管诊断法更为可靠。然后,非侵入心血管诊断法是可取的,因为和侵入心血管诊断法相比,的确它们通常操作起来便宜,且对病人较少危险。
一种特别有效的非侵入心血管诊断术涉及用一个的手指把脉搏。传统的中医执业医生以及包括希腊、东印度、阿拉伯和不列颠在内的其他文明国家的许多医生已成功地使用这种技术好几个世纪。在很多这些国家中,那里昂贵的诊断工具可能并不轻易得到,而把脉搏则为首先,有时甚至是仅有的心血管诊断工具。这种工具对诊断其他疾病也是有效的,因许多疾病症状具有相伴的心血管表征。
把桡骨神经(radial)脉搏作为诊断包括心血管病在内的疾病的方法,是基于以下发现,即脉搏的形状或轮廓包含有关病人生理状态的重要诊断信息。当脉搏是在心脏中心地产生时,该脉搏就向循环系统或血管的所有部分传播,并在其后向中心反射回来,就象一个波被池塘边缘反向回来一样。反射的大小和时序或者反射事件的轮廓关键地取决于供给身体中不同器官系统的血管的状态。这样人们可以想象,在中心产生的脉搏犹似一访问的试验脉冲,其反射包含有涉及血管和其所供给诸末端器官的重要诊断信息、正如在M.F.Okouke,R.Kelly和A.Avolio所著《脉搏》(The Arterial pulse,philadelphia:Lea & Febiger,1992)一书所述,该反射波连同与心脏瓣膜闭合相关的事件对动脉压脉冲轮廓的形成起着决定性的作用。
然而,把脉搏作为诊断心血管和相关疾病的方法并未得到广泛的接受。这可能归诸以下事实,即该技术并不产生定量的结果。是故,可靠的诊断只能由对该技术有经验的执业医生获得。
提供心脏收缩和舒张血压定量值的血压计或脉压计作为诊断心血管健康的方法得到了广泛的接受。然而,心脏血管收缩压和舒张压的值对表征患者的心血管健康虽然是重要的,但心脏收缩压和舒张压值并不包括存在于动脉压脉冲轮廓内的许多重要诊断信息。是故,作为诊断心血管和相关疾病手段的脉压计,其应用是受到限止的。
对改进由脉压计所提供诊断心血管疾病法的系统已在开发。例如,授予Akay等人美国专利5,638,823就讲述一非侵入地探测冠状动脉疾病的系统。该系统在代表患者的舒张心声的声波信号上进行子波变换。以变换的开始四个时刻包括在输入至神经网络的特征矢量中,神经网络基于包含在特征矢量中的信息诊断出冠状动脉疾病的存在。
然而,由Akay等讲授的系统在若干方面是不足的。首先,由于该系统分析与流入患者在动脉血液的声学骚动相关,故系统只能探测一种疾病的存在,即冠状动脉狭窄。其次,该系统要求患者作血管扩张药剂处理以改善舍张心声的信噪比。所以该系统用这样一种药剂对患者过敏反应方面的可用性而受到限止。第三,许多临床参数,诸如患者的性别、年龄、体重、血压以及家庭医史等必须包括在特征矢量内。结果误诊的可能性取决于输入诸临床参数的正确度。最后,该系统对通过舍张心声污染(经由诸如环境、呼吸和胃的噪声一类声音)引起的误诊断高度敏感。
授予Kaspari的美国专利5,533,511讲述一非侵入测量血压用的方法和仪器,该法涉及通过置一压电传感器于动脉而从患者血压的波形获得血压脉冲。于是将传感器的输出脉冲过滤、放大和数字化。把时序特征(诸如脉冲幅度、上升时间、及宽)和频率特征(诸如富里哀或拉伯拉拉斯变换值、相位关系以及频率分布)经由数字化脉冲提取出来。最后神经网络基于所提取的特征与采用溯源至多数患者的血压而获取的历史性数据之间的比较来决定患者的实际血压。
然而,由Kaspari讲述的方法只限于供临床用的血压脉冲的估计,且由于Kaspari法的本性而使它并不适用于心血管疾病的诊断。再者,按照Kaspari讲述的方法,必须使用侵入内部的动脉的导入管以获取绝对血压的参考数据。诸如Kaspari所要求的侵入步骤并不为所有患者所接受,并对某些患者甚至还可能具有危险性。
人类心率易变性是在技术上另一感兴趣的领域。人类心率的易变性受控于交感和付交感活动之间的平衡(Malik M.,Camn A.J.编,《心率易变性(HeartRate Variahility)》,Armonk,(Y.Y.:Futme Puhlishing,1995)。该控制或失败可通过分析由心跳间间隔组成的长程相关性(long range correlation)或时间序列的刻度指数(scaling exponents of the time-series)加以探测(Peng CK等人,Chaos.5:82-27,1995)。该法在临床上是重要的,并已在预测充血性心衰竭病患者的生存(Kalon KL et al.,;circulation 96:842-848,1997)以及预测有肌梗塞之后其后的心室搏动过速(Makikallio TH et al.,AmericanJournal of Cardiolgy 80:779-7783,1999)方面获得成功。然而,该技术的应用需要不寻常的长期测量以获取一典型地包含有8000次心跳的时间序列。
因此,一直需要一种快速、正确而又非侵入地诊断心血管和相关疾病方法。较佳地,这种方法同样也适于分析人类心率的易变性。
发明概要
在本发明中,提供一快速和正确地诊断心血管以及相关疾病(诸如动脉硬化和普通心脏恶化)的方法。该诊断可不经渗入皮肤或体孔而获得,给患者带来的不适最少。另外,该诊断的速度和精度并不诊断者的技巧或知识的限制。
按照本发明,该方法包括以下步骤:接收代表动脉压脉冲轮廓的信号:从该信号提取频率定位信息和时间定位信息;把该提取的信息作为输入提供给神经网络,该神经网络已用多个训练组合加以训练,每一训练组合使动脉压脉冲轮廓与已知心血管或相关疾病相关;以及从神经网络产生出疾病鉴定输出。
按照本发明,该装置包含有:(a)接收代表动脉压脉冲轮廓的信号输入的装置;(b)与输入装置相耦合的信息提取装置,用以从所述信号提取频率定位信息和时间定位信息,和输出代表一部分所提取信息的定位信息输出信号的装置;以及(c)用多个训练组合加以训练的神经网络,每一训练组合使动脉压脉冲轮廓与已知心血管或相关疾病相关联,所述神经网络包括产生疾病鉴定输出信号的装置,疾病鉴定输出信号代表包含在诸训练组合内的每一已知心血管或相关疾病的发生概率。
附图简述
现将参考附图,它们作为例子表示本发明的较佳实施例,其中
图1是一方框图,表示按照本发明的非侵入诊断心血管疾病的系统;
图2是表示图1中该系统输入模块的更为详细的方框图;
图3是表示图1中该系统处理模块和输出模块的更为详细的方框图;
图4(a)是表示受验者在正常呼吸下的归一化动脉压脉冲轮廓图;
图4(b)是表示受验者在Valsalvs手法下的归一化动脉压脉冲轮廓图;
图4(c)是表示受验者保持其呼吸的归一化动脉压脉冲轮廓图;
图5(a)以图解形式表示图4(a)中归一化动脉压脉冲轮廓信号的分解;
图5(b)以图解形式表示图4(b)中归一化动脉压脉冲轮廓信号的分解;
图5(c)以图解形式表示图4(c)中归一化动脉压脉冲轮廓信号的分解;
图6(a)表示图1系统用的第一种神经网络;
图6(b)表示图1系统用的第二种神经网络;
图7(a)表示在正常条件下和Valsalve操作法下从受验者A得到的动脉压轮廓;
图7(b)表示在正常条件和Valsalve操作法下从受验者B得到的动脉压轮廓;
图8(a)表示通过应用子波变换从图7(a)动脉压轮廓导出的标记(Signature)的按比例心脏循环图(scale-cardiac cycle plot);
图8(b)表示通过应用子波变换从图7(b)动脉压脉冲轮廓导出的标记的按比例周期图;
图9(a)表示从受查者A在正常条件和血管紧缩条件期间所得的动脉压轮廓;
图9(b)表示从受查者B在正常条件和血管紧缩条件期间所得的动脉压轮廓;
图10(a)表示通过应用子波变换从图9(a)动脉压轮廓导出的标记的按比例心脏循环图;
图10(b)表示通过应用子波变换从图9(b)动脉压轮廓导出的标记的按比例心脏循环图。
较佳实施例的描述
首先参照图1进行,该图以方框图表示按照本发明用以诊断心血管和相关疾病的非侵入诊断系统10原理模块。该诊断系统10包括输入系统11、处理模块12和输出模块13。处理模块12包括中央处理单元(CPU)14和存储器模块配置15。
输入模块11输入来自通常由P表示的一患者或受查者的血压脉冲轮廓。正如图2所示,该输入模块11包括压力传感器20和轮廓信号接收器21,后者与压力传感器20的输出相耦合。轮廓信号接收器21包括信号放大器和滤波器级22以及模拟至数字(A/D)转换器23。A/D转换器23耦合至信号放大器滤波器22级的输出。
在本发明的另一实施例中,备有通常由标号20(a)所指示的一个或更多个额外的传感器。将会明白,诊断性能可通过增加尺寸,即增加压力轮廓的数目来加以改进,因此提供2个或更多个传感器20a是有利的。
较佳地,压力传感器20是非侵入型的。通过固定一层0.5mm硅酮膜来构建非侵入压力传感器20,该膜用以陷获小体积的空气于诸如Motorola公司提供的MPX10D一类压-阻压力敏感器之上。然后借助于带有VelcroTM型装置的弹性带固定之。压力传感器20探测到流经患者动脉中血液的动脉压轮廓,随后输出代表动脉压轮廓的模拟信号至信号接收器21。于是把此动脉压轮廓信号经放大器和滤波器级22加以放大和滤波,并输出至轮廓信号接收器21中的模拟至数字转换器23。模拟数字转换器23将压力轮廓信号输出转换成一系列数字输出信号。数字输出信号提供数字化的“抽点打印”(snapshots),后者定义代表患者P的动脉压脉冲的压力脉冲信号矢量24。
将来自输入模块11的脉搏信号矢量24输出至处理模块12(图1)以供处理分析。正如图3所示,处理模拟12由以下诸处理级构成:心脏循环周期提取器级30,时序和幅度归一化级32,子波变换级34,以及神经网络级36。处理模块12也包括训练级35,用以训练神经网络36。训练级35的操作描述如下。将轮廓信号接收器21以及心脏循环周期提取器30,时序和幅度归一化级32,子波变换34和神经网络36诸级串联起来。来自轮廓信号接收器21的脉搏信号矢量24依次通过心脏循环周期提取器级30,时序和幅度归一化级32,子波变换级34以及神经网络36。正如将要描述的那样,这些单元合作产生疾病鉴定输出信号,后者是由从患者P得到的原始动脉压脉冲轮廓导出的。
由于动脉脉搏并不与子波变换级34或神经网络36同步,故脉搏信号矢量首先被心脏循环周期提取器30接收。心脏信号提取器对于熟悉该技术的人而言是众所周知的。心脏循环周期提取器30为患者每一心脏循环周期探测出一完整的动脉压脉冲轮廓信号。这样,来自心脏循环周期提取器30的输出为一压力轮廓信号矢量31,后者代表患者动脉动脉压脉冲轮廓的一个完整周期。
由于动脉压脉冲轮廓每个循环周期的持续时间和幅度将随患者而异,故将来自心脏循环周期提取器30的压力轮廓信号矢量31用时间和幅度归化级32加以归一化。时间和幅度归一化级32对所提取的压力轮廓矢量31的每一周期的持续时间进行归一化,产生归一化的压力脉冲轮廓矢量40,如图4(a)至4(c)所示。时间和幅度归一化级32如此归一化所提取的压力轮廓矢量31中每一周期的持续时间,以致于归一化的压力脉冲轮廓信号40包括固定的取样点数目。同样将所提取的压力轮廓信号40的每一周期的幅度归一化至每一周期的峰峰值。这样一种时间和幅度归一化级32的实施在本领域技术人员的理解范围以内。
再次回到图3,按照本发明另一实施例也可备有一预处理级310。该预处理级310提供额外的处理步骤,后者可被施加于非侵入的压力轮廓。在本实施例中,该预处理级310提供高通滤波和/时间求导功能。由预处理级310完成的预处理步骤提供许多优点。首先,过滤或计算时间导数使与动脉压脉冲轮廓相关的时间变化得到加强。另外,求导或过滤的信号部分地包含下一流动周期的信息。将会明白,当神经网络36可直接使用合适的归一化的诸峰和谷的比值时,从而就可绕过子波变换级34。
参照经预处理过的动脉压脉冲轮廓信号的图4(a)至4(c)。图4(a)表示得自受查者在正常呼吸条件下三个分别以41a、41b和41c示出的典型归一化动脉压脉冲轮廓信号41。图4(b)表示得受查者在施加著名的Valsalve操作法期间的三个分别以42a、42b和42c示出的典型归一化动脉压脉冲轮廓信号42,其中测量取自以下条件,即受查者处在试图对着闭合的声门呼气而被过度用力的境地。这种条件模拟其中存在心脏输出和脉搏压力降低(这起因于胸内压力急剧增加和静脉回流的降低)和交感神经紧张度增加的失常状态。图4(c)表示得自受查者保持其呼吸在呼气末尾的三个分别以43a、43b和43c示出典型归一化动脉压脉冲轮廓信号43这种操作产生类似于Valsalve操作法的效果,但程度较低。
为了从动脉压脉冲轮廓中探测和诊断出血管或相关的病征,宁可对时间和幅度归一化模块32(图3)的归一化动脉压脉冲轮廓输出矢量进行更为详细的表征,但用的参数量尽可能少。为此任务,传统的傅里叶变换是不适合的。将会明白,传统傅里叶变换对由少数固定成分,例如,正弦和余弦函数组成的待表征信号使用起来相当好。因为傅里叶变换中正弦和余弦基本函数以频率定位,所以如果待表征的信号包括有任何突变,则当变换到频率领域时,信号将向外扩展到整个频率轴。此外,动脉压脉冲轮廓40(图4)将包括诸如瓣膜闭合和波反射一类瞬变事件。因而动脉压脉冲轮廓的傅里叶基本函数分析将使先而突发的瞬变定位困难。
因此,在其较佳实施例中,按照本发明的非侵入诊断系统10使用子波变换来处理归一化的脉搏轮廓信号40(图4)。子波变换借助图3所示子波变换级34加以实施和进行。子波变换包括在G.strang和T.Hguyen所著《子波和滤波器组合》(Wavelets and Filter Bank)(Welleslay-Cambridge Press,Wellesley,MA 1966出版)一书中的已知变换,且将处于该技术中那些熟练人员的理解范围以内。和傅里叶变换不同,子波变换的基本函数局部在空间和频率或尺度两者中。结果当许多函数被变换至子波领域时将是稀疏的。另外,子波变换具有可能基本函数的无穷组合,且每一个均不是不同的长度,而并不限于只用正弦和余弦函数。因此使用子波变换即可分离信号的不连续性,又可获得详细的频率分析。
当进行波形分析时,每个基本函数均具有其自身的优、缺点。本发明在这个方面,选择Daubechies子波作为优选的基本函数,用以表征动脉压脉冲轮廓信号。Daubechies子波尤其适合于分析具有尖锐特征的信号。在较佳实施例中,采用第4阶Daubechies子波以进行不连续的变换,也即对来自时间幅度归一化级21(图3)中归一化过的动脉压脉冲轮廓信号40(图4)进行分解。子波变换级34分解每一归一化过的动脉压脉冲轮廓信号40成相应的近似值a2和详细的函数d1和d2。近似值a2和详细函数d1d2提供一系列子波系数,后者正如下面将要叙述的那样,用来鉴定患者心血管系统的特征。正如图5(a)所示,将取自正常呼吸期间的归一化过的动脉压脉冲轮廓信号41变换成近似值信号44(a2),第一和第二详细函数44(d1)和44(d2)。似类地,将取自Valsalve操作法期间归一化过的动脉压脉冲轮廓信号42变换成如图5(b)所示的近似值信号45(a2),第一和第二详细函数45(d1)和45(d2)。类似地,将取自患者保持其呼吸时归一化过的动脉压脉冲轮廓信号43变换成如图5(c)所示的近似值信号46(a2),第一和第二详细函数46(d1)和46(d2)。
在较佳实施例中,第4阶Daubechies子波变换通过重复地施加第4阶Daubechies子波系数的变换矩阵于归一化的动脉压脉冲轮廓信号40而从数学上加以实施。
将来自子波变换级34的输出信号,也即子波系数提供给神经网络级36的输入。在本发明的这方面,神经网络36的主要功能乃是基于由子波变换级34为归一化动脉压脉冲轮廓信号40产生的系数来表征心血管或相关疾病。仿真神经网络在1966 PWS出版社出版的由M17,Hagan,H.B.Demnth,M.Beale所著《神经网络设计》(Neural Networh Design中所描述,对该技术领域的熟练人员而言是众所周知的。在本系统的这一方面,该神经网络级35包括一神经网络50,它由输入层53,输出层54以及一系列隐藏层56构成,如图6(a)所示。输入层52会有一系列处理元件53,也即相应表示为53a,53b,53c…53n的单元或端点。相似地,输出层54含有一系列分别以55a,55b,55c…55n加以表示的处理元件55.隐藏层56同样含一系列处理元件57。各个不同层的处理元件借助加权的可调连加以连接。将神经网络50的处理能力存储在这些端点间的加权上。该端点间的加权通过用多个训练组合训练神经网络50得到。正图3所示,该训练级35含有求和元件37和一组训练目标参数38。求和元件37为神经网络36产生一均方误差和输出。求和元件37包括一有名的反馈元件,并具有耦合于神经网络36输出的第一输入和用以接收预定训练目标38的第二输入。将来自求和元件37的输出(也即均方误差和)通过由CPU控制器14启动的开关39选择性地耦合于神经网络36。为了训练神经网络36,将一来自子波变换级34的输入矢量,也即一组子波系数施加至神经网络36.求和器37在来自神经网络36的输出和相应于患者心血管系统相关特征的训练目标38之间产生一均方误差和,并将该输出施加于神经网络36。重复进行神经网络的训练,直至达到预定的误差目标。
采用神经网络36代替常规计算机的优点在于,神经网络36能从训练组合,即从子波变换34获得的子波系数进行学习。因此,当完成训练时,该神经网络36就能支适当地响应并不包括在训练组合中的输入矢量。
正如该技术领域中熟练的人员将会明白的那样,许多有已知类型的神经网络是可用的,而每种神经网络类型的通用性则将于输入数据而变化。在本发明的这一方面,该神经网络级36宁可包括如图6(a)所示的多层知觉(也即背层传播)神经网络50,或者如图6(b)所示的放射基本函数网络60。多层知觉神经网络50含有一个或多个隐藏层56a和56b。在多层知觉神经网络50中,隐藏层56包括有S形激活函数,而输出层54则含有线性激活函数。在较佳实施例,多层知觉神经网络50用一反向传播的学习算法进行训练。
图6(b)示出一桡骨神经基本功能神经网络60.它由输入层62,输出层64和单个隐藏层66构成。隐藏层66中的处理元件67包括有高斯激活函数。输出层64用的处理元件包括有线性激活函数。输出层64用的处理元件包括有线性激活函数。对于神经网络50和60,将具有恒定态1的偏置单元连至所有的隐藏和输出端点。
反向传播网络50(图6a)和桡骨神经基本功能网络60(图60)两者的输入矢量均包括由子波变换级34产生近似值a2和详细函数d1,d2(图5a至5c)的系数。由于一级详细函数d1极大多数含有一噪声,也即其信息与来自周期至周期的心脏事件无关,故在输入矢量中的详细函数d1的系数并使用于神经网络50和60的输入层52或62。相应地对于二级分解,该输入矢量包括来自近似值函数a2和第二详细函数d2的指定系数组合。对于三级分解,该输入矢量包括来自近似值函数a3和第二详细函数d2和d3的指定系数组合。一般讲,对经由子波变换级34(图3)的“n”级分解,该输入矢量将包括来自近似值函数an和详细函数dn,dn-1…d1的指定系数组合。
在神经网络级36(图3)中的输出层54(或64)产生一输出矢量,它包括范围从0-1的一系列输出。输出层54(或64)中端点的数目相应于能经由系统10加以诊断的异常征状的数目。在神经网络36的训练期间,对输出层54中的二进制输出进行编码,俾使每一输出矢量将只含有一个非零成分,也即对数1,它相应于经由子波变换级34产生的系数加以引出的一特定异常。因此,输出矢量的大小,因而输出层54的大小,随待探测的异常数目而增加。将会明白,系统10并不受制于这一特定的编码方案。可使用其他的编码方案,而神经网络级36(图3)的主要功能在于使输入矢量的训练组合与编码在输出矢量组合中的特定异常相关联。
通过从许多不同受查者不同条件下获取的脉搏读数来对神经网络36进行训练。对于每一种条件,只有一部分轮廓数据矢量被用于网络训练。例如,在一组来自多个受查者的大约50-1000个动脉压脉冲轮廓读数中,轮廓的大约80%被用于神经网络训练,而留下的20%则用于网络性能的确认。正如图3所示,使用均方误差和元件37来监控以80%的动脉压脉冲轮廓信号去训练神经网络36的进行。当达到一特定的误差目标时(这将取决于训练组合的大小)就用留下的20%轮廓数据矢量去试验神经网络36,并通过强制输出矢量经受一竞争性变换,后者给予最大成分为1,其余为0。将会明白,这种试验格式允许让神经网络36的能力评估从并非训练组合部分的动脉压脉冲轮廓矢量中对诸种异常作出正确的诊断。
实验结果
采用按本发明的系统10,并参照图4(a)~4(c)和图5(a)~5(c)来分析来自受查者在三种条件下的数据组合。第一数据组合(诸例子示于图4(a)和5(a))包括发射的脉搏读数,后者得自三受查者在正常呼吸,也即静坐期间的左臂。第二数据组合(图4(b)和图5(b))包括从同样的三受查者在经受Valsalve操作法条件下,也即让受查者试各对着闭合的声门呼气而用力过度期间得到的发射脉搏读数。取自这些条件下的脉搏读数模拟以下诸异常,即出现心脏输出和脉搏压力降低(起因于胸内压力的急剧增加和静脉回流的下降),交感神经紧张度增加,动脉血液中二氧化碳分压增加、氧分压和PH值下降。第三数据组合(图4(c)和图5(c))包括从三同一受查保持其呼吸在吸气末尾条件下得到的发射脉搏读数。这一操作产生程度较小的、类似于Valsalve操作法的效果,其心脏输出变化不大,但平均动脉压力则随呼吸保持进则而增加。
按照本发明的方法,将得自上述不一同条件下的脉搏读数首先归一化成如图4(a)-4(c)所示。然后参照图5(a)-5(c)让归一化的动脉压脉冲轮廓41-43经受离散子波变换以产生如上所述相应的子波系数组合44-46。在对变化级34采用4级Daubechies子波之后就用二级分解来为每一受查者在三种条件下产生相应的子波系数数据组合。将子波系数数据组合分成训练组合(也即80%)和试验组合(也即20%)。将同一试验组合用作为后面传播型神经网络50和具有单个隐藏的桡骨神经基本功能网络60的输入矢量。每种条件由二进制输出矢量加以表示:对正常条件为(1,0,0),对Valsalve操作法为(0,1,0),而对呼吸保持则为(0,0,1)。
发现两种神经网络50和60在为于5000次训练期内均达到所希望的误差目标。当将试验组合(20%原始数据组合不被用训练)用于评估系统10的性能时,对反向传播50和桡骨神经基本功能60两种神经网络均达到在三种条件下大约95%的正确分类率。相似的结果得自用5级分解的子波系数。
下面参照图7-10。图7(a)表示对受查者以标号101a指示的一正常高通滤波过的动脉压脉冲轮廓和当受查者经受Valsalve操作法时的动脉压脉冲轮廓102a,而图7(b)则表示对受查者以标号101b指示的一正常高通滤波过的动脉压脉冲轮廓和当受查者经受Valsalve操作法时的动脉压脉冲轮廓102b。Valsalve操作法导致对着闭合的声门强制呼气,后者使胸内压力增加,并阻碍静脉回流。这一状态转而产生带有短期心脏收缩喷射的重搏(也即二次搏动)脉搏。这样一种条件产生出一种类似于如受查者经受心衰竭、血容积过小的休克或者暂时停搏(temponade)一类征状的动脉压脉冲轮廓。
正如图7(a)和7(b)所示,各自对应受查者A和B的正常动脉压脉冲轮廓101a,101b均表征为:心收缩肩103a,103b,紧跟着称为介于300-400msec之间的重搏凹口106a,106b,其归一化心脏循环周期为900msec。相反,Valsalves氏操作产生的动脉压脉冲轮廓102a和102b则显示出相应的心收缩肩104a和104b以及迟后的凹口105a和105b。正如图7(a)和7(b)所示,分离二次搏动或重搏107A,107B的相应凹口105a,105b两者均被延迟。正如上述,相应于嵌入正常动脉压脉冲轮廓101和Valsalve操作法所得动脉压脉冲轮廓102之不变特征的标记110得以产生。分别示于图8(a)和8(b)中对受查者A和B的110a和110b通过以下产生,即施加连续的子波(也即4阶Daubechies)于相应的正常动脉压脉冲轮廓101和VAlsalves氏操作所得动脉压脉冲轮廓102,并从正常动脉压脉冲轮廓101的子波系数减去Valsalves氏动脉压脉冲轮廓102的子波系数。正如图8(a)和(b)所示,标记110作为按比例心脏循环周期加以显示。对图8(a)中的受查者,标记710包括亮区111a、112a、113a和暗区114a、115a、116a。同样对受查者,标记b包括亮区111b、112b、113b、114b、115b、116b。亮区111-113代表围绕收缩肩103,104(图7(a)和7(b))之动脉压脉冲轮廓中正的差额。另一方面暗区114-117代表正常动脉压脉冲轮廓101之重搏凹口106区域中负的差额。
下面参照图9(a)和9(b),它们分别表示受查者和正常的左臂动脉压脉冲轮廓121a、121b和受查者经受外部血管收缩时的动脉压脉冲轮廓122a、112b。通过让受查者的左手短期暴露于0℃的冷水而把血管收缩条件引入与压力传感器20相连(图2)的受查者的手臂。正职图9(a)和9(b)所示,血管收缩导致心脏收缩波部分123a、123b的放大或增加(相对于重搏波部分)。当归一化至一个心脏循环周期的正常动脉压脉冲轮廓121a、121b的心脏收缩波部分124a、124b相比较时,血管收缩同样导致动脉压脉冲轮廓122a、122b之心脏收缩波部分的持续期增加。在图9(a)和9(b)中,正常动脉压脉冲轮廓121之相应的心脏收缩肩由标号125a和125b加以指示,而重搏凹口则由标号125a和126b加以指示。对于血管收缩的动脉压脉冲轮廓122,相应的心脏收缩肩由标号127a和127b指示,而重搏凹口由标号128a和128b指示,如图9(a)和9(b)所示。血管收缩条件产生一相似于以下条件的动脉压脉冲轮廓,即受查者如若经受严重的局部反射性血管收缩,后者能从患有诸如Raymand氏症业类的四肽血管病患者中观察到。
参照图10(a)和10(b),它们表示对血管收缩动脉压脉冲轮廓122所导致的标记。对受查者的标记由图10(a)所示的130a加以指示。标记130a表征为:分别以133a、133b、133c表示的(在图10(a)中显示为暗区)的负差额带子波系数133,以及分别以135a、135b(在图10(a)显示为亮区)表示的一系列正差额子波系数135。类似地,对受查者的标记130b则表征为:分别以134a、134b、134c、134d…(在图10(b)中为暗区)表示的负差额带子波系数134,以及分别以136a、136b(图10(b)中显示为亮区)表示的一系列正差额子波系数136.暗区133、134代表各自正常动脉压脉冲轮廓121a、121b(图9(a)和9(b))中重搏凹口126的负差额。在另一方面,亮区则代表在各自正常动脉压脉冲轮廓121a、121b(图9(a)和9(b))中围绕心收缩肩217(应为127-译者注)的正差额。
正如上述,对每种标记101a,101b(图7(a)和7(b))以及121a,121b(图9(a)和9(b))的子波系数均被分成训练组合和试验组合,用以训练和试验神经网络36。主训练和试验阶段完成时,系统11(应为10-译者)就能对受查者X提供基于该患者脉搏读数的诊断。
关于心率易变性的分析
按照另一方面,系统10包括用以分析人类心率易变性的处理模块。参照图3,系统10包括一心跳之间间隔测量级312以及子波变换和刻度指数处理级314.较佳地,子波变换级314按《平均子波系数》(Average WaveletCoefficient CAWC,见Simonsen I & Hansen A,Physical Review E58:2779-2789,1998)法的子波算法进行。在按照本发明的系统10中子波分析的框架以内业已发现,借助利用平均子波系数(AWC)法可使时间测量沽少一个数量级,从而在短得多的时间框架内利用心跳间隔测量312和刻度指数处理互助314达到对心率易变性的评估。
将会明白,存在对心率易性的许多有效应用。例如,可用它来评价运动的效果,因为对于正常人群和心肌梗塞后的病人两者,已知运动使交感神经和付交感神经控制之间的平衡得以改善。可将心率易变性的子波分析应用于这一重要领域。
可以其它特定的形式实施本发明而不违背其精神或基本特征。因此认为,目前讲座的实施例乃是说明性的而非限制性的,本发明的范畴由所附权利要求书指明,而非前面的叙述,因而所有在与权利要求等效的主意和范围以内发生的变化均被指定为包括在其中。

Claims (13)

1.一种用以诊断心血管病相关症状的系统,其特征在于所述系统包括:
接收代表动脉压脉冲轮廓的信号的输入装置;
与所述输入装置耦合的信息提取装置,用以从信号中提取频率定位信息和时间定位信息并包括产生代表一部分所提取信息的定位信息输出信号的装置;以及
用多个训练组合进行训练的神经网络,每个训练组合使动脉压脉冲轮廓与已知的心血管或相关疾病相联系,所述神经网络包括接收所述定位信息输出信号的装置和产生疾病鉴定输出信号的装置,疾病鉴定输出信号代表所提取信息与由所述训练组合导出的心血管相关症状之间的相关性。
2.如权利要求1所述的系统,其特征在于,所述的接收装置选择性地与只接收所述定位信息输出信号的所述信息提取装置相耦合。
3.如权利要求1所述的系统,其特征在于,所述信息提取装置包括对所述接收信号进行多分辨率分解的信号分解装置。
4.如权利要求3所述的系统,其特征在于,所述信号分解装置包括子波变换装置。
5.如权利要求1所要求系统,其特征在于所述信号分解装置包括Daubechies子波变换装置。
6.如权利要求1所述的系统,其特征在于所述接收装置包括模拟-数字转换器,用以产生动脉压脉冲的数字化表示,所述模拟-数字转换器包括接收动脉压脉冲传感器的输出信号的输入端口,其中,所述信息提取装置包括与所述模拟数字转换器耦合的离散子波变换装置,用以通过对接收信号的多分辨率分解从所述接收信号中提取近似值和详细函数数据,与离散子波变换装置耦合的矢量产生装置,用于产生包括所提取近似值和详细数字的矢量,作为定位信息输出信号。
7.按照权利要求1所述的系统,其特征在于,所述神经网络包括多层知觉神经网络,所述神经网络通过反向传播学习进行训练。
8.按照权利要求1所述的系统,其特征在于所述多层知觉神经网络包括含有S形激活功能的隐藏层和含有线性激活功能的输出层。
9.按照权利要求1所述的系统,其特征在于所述神经网络包括桡骨神经(动脉)基本功能神经网络。
10.按照权利要求1所述的系统,其特征在于所述桡骨神经基本功能神经网络包括含有线性激活功能的输出层和含有高斯激活功能的隐藏层。
11.按照权利要求1所述的系统,其特征在于所述信号提取装置包括预处理模块,后者包括对信号进行滤波的滤波器。
12.按照权利要求1所述的系统,其特征在于所述信号提取装置包括预处理模块,用以对信号进行时间求导功能。
13.按照权利要求1所述的系统,其特征在于进一步包括用以决定心率易变性的刻度指数模块。
CN99805707A 1998-05-01 1999-04-30 非侵入诊断心血管及相关疾病的方法和仪器 Expired - Fee Related CN1117331C (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US09/071,348 US6135966A (en) 1998-05-01 1998-05-01 Method and apparatus for non-invasive diagnosis of cardiovascular and related disorders
US09/071,348 1998-05-01

Publications (2)

Publication Number Publication Date
CN1299486A CN1299486A (zh) 2001-06-13
CN1117331C true CN1117331C (zh) 2003-08-06

Family

ID=22100750

Family Applications (1)

Application Number Title Priority Date Filing Date
CN99805707A Expired - Fee Related CN1117331C (zh) 1998-05-01 1999-04-30 非侵入诊断心血管及相关疾病的方法和仪器

Country Status (6)

Country Link
US (1) US6135966A (zh)
EP (1) EP1075678A1 (zh)
CN (1) CN1117331C (zh)
AU (1) AU3695799A (zh)
CA (1) CA2330572A1 (zh)
WO (1) WO1999057647A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102549588A (zh) * 2009-08-10 2012-07-04 糖尿病工具瑞典股份公司 用于产生状态指示的装置和方法
CN101785666B (zh) * 2008-11-21 2014-02-12 普尔松医疗系统公司 用于确定生理参数的仪器及方法

Families Citing this family (122)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU7845900A (en) 1999-09-29 2001-04-30 Siemens Corporate Research, Inc. Multi-modal cardiac diagnostic decision support system and method
US6600949B1 (en) * 1999-11-10 2003-07-29 Pacesetter, Inc. Method for monitoring heart failure via respiratory patterns
US6589188B1 (en) 2000-05-05 2003-07-08 Pacesetter, Inc. Method for monitoring heart failure via respiratory patterns
US7149576B1 (en) * 2000-07-10 2006-12-12 Cardiodynamics International Corporation Apparatus and method for defibrillation of a living subject
DE10043266A1 (de) * 2000-08-28 2002-03-14 Getemed Medizin Und Informatio Verfahren und Vorrichtung zur kontinuierlichen, nichtinvasiven Bestimmung des Blutdrucks
US6741885B1 (en) 2000-12-07 2004-05-25 Pacesetter, Inc. Implantable cardiac device for managing the progression of heart disease and method
US7035679B2 (en) * 2001-06-22 2006-04-25 Cardiodigital Limited Wavelet-based analysis of pulse oximetry signals
FR2827405B1 (fr) * 2001-07-10 2004-01-16 Univ Paris 7 Denis Diderot Procede d'analyse d'un evenement tel qu'une intervention chirurgicale sur un vaisseau sanguin
US20030093301A1 (en) * 2001-11-13 2003-05-15 Hypertension Diagnostics, Inc. Centralized clinical data management system process for analysis and billing
KR100462182B1 (ko) * 2002-04-15 2004-12-16 삼성전자주식회사 Ppg 기반의 심박 검출 장치 및 방법
US20030208451A1 (en) * 2002-05-03 2003-11-06 Jim-Shih Liaw Artificial neural systems with dynamic synapses
WO2004075746A2 (en) 2003-02-27 2004-09-10 Cardiodigital Limited Method and system for analysing and processing ph0t0plethysmogram signals using wavelet transform
US7455643B1 (en) 2003-07-07 2008-11-25 Nellcor Puritan Bennett Ireland Continuous non-invasive blood pressure measurement apparatus and methods providing automatic recalibration
US7596535B2 (en) 2003-09-29 2009-09-29 Biotronik Gmbh & Co. Kg Apparatus for the classification of physiological events
US7300405B2 (en) * 2003-10-22 2007-11-27 3M Innovative Properties Company Analysis of auscultatory sounds using single value decomposition
US20060025931A1 (en) * 2004-07-30 2006-02-02 Richard Rosen Method and apparatus for real time predictive modeling for chronically ill patients
EP1814438B8 (en) * 2004-11-08 2009-04-01 Koninklijke Philips Electronics N.V. Safe identification and association of wireless sensors
US20060167385A1 (en) * 2005-01-24 2006-07-27 3M Innovative Properties Company Analysis of auscultatory sounds using voice recognition
US7520860B2 (en) * 2005-04-13 2009-04-21 Marie G. Johnson Detection of coronary artery disease using an electronic stethoscope
US8308646B2 (en) * 2005-04-18 2012-11-13 Mayo Foundation For Medical Education And Research Trainable diagnostic system and method of use
US8145463B2 (en) * 2005-09-15 2012-03-27 Schlumberger Technology Corporation Gas reservoir evaluation and assessment tool method and apparatus and program storage device
US8920343B2 (en) 2006-03-23 2014-12-30 Michael Edward Sabatino Apparatus for acquiring and processing of physiological auditory signals
US7751873B2 (en) * 2006-11-08 2010-07-06 Biotronik Crm Patent Ag Wavelet based feature extraction and dimension reduction for the classification of human cardiac electrogram depolarization waveforms
US8244509B2 (en) * 2007-08-01 2012-08-14 Schlumberger Technology Corporation Method for managing production from a hydrocarbon producing reservoir in real-time
US20090324033A1 (en) * 2008-06-30 2009-12-31 Nellcor Puritan Bennett Ireland Signal Processing Systems and Methods for Determining Slope Using an Origin Point
US8077297B2 (en) 2008-06-30 2011-12-13 Nellcor Puritan Bennett Ireland Methods and systems for discriminating bands in scalograms
US8295567B2 (en) 2008-06-30 2012-10-23 Nellcor Puritan Bennett Ireland Systems and methods for ridge selection in scalograms of signals
US8398556B2 (en) 2008-06-30 2013-03-19 Covidien Lp Systems and methods for non-invasive continuous blood pressure determination
US8660799B2 (en) 2008-06-30 2014-02-25 Nellcor Puritan Bennett Ireland Processing and detecting baseline changes in signals
US8827917B2 (en) 2008-06-30 2014-09-09 Nelleor Puritan Bennett Ireland Systems and methods for artifact detection in signals
US7944551B2 (en) 2008-06-30 2011-05-17 Nellcor Puritan Bennett Ireland Systems and methods for a wavelet transform viewer
US20090326402A1 (en) * 2008-06-30 2009-12-31 Nellcor Puritan Bennett Ireland Systems and methods for determining effort
US8370080B2 (en) * 2008-07-15 2013-02-05 Nellcor Puritan Bennett Ireland Methods and systems for determining whether to trigger an alarm
US8385675B2 (en) * 2008-07-15 2013-02-26 Nellcor Puritan Bennett Ireland Systems and methods for filtering a signal using a continuous wavelet transform
US8761855B2 (en) 2008-07-15 2014-06-24 Nellcor Puritan Bennett Ireland Systems and methods for determining oxygen saturation
US20100016692A1 (en) * 2008-07-15 2010-01-21 Nellcor Puritan Bennett Ireland Systems and methods for computing a physiological parameter using continuous wavelet transforms
US20100016676A1 (en) * 2008-07-15 2010-01-21 Nellcor Puritan Bennett Ireland Systems And Methods For Adaptively Filtering Signals
US8506498B2 (en) 2008-07-15 2013-08-13 Nellcor Puritan Bennett Ireland Systems and methods using induced perturbation to determine physiological parameters
US8660625B2 (en) * 2008-07-15 2014-02-25 Covidien Lp Signal processing systems and methods for analyzing multiparameter spaces to determine physiological states
US8082110B2 (en) 2008-07-15 2011-12-20 Nellcor Puritan Bennett Ireland Low perfusion signal processing systems and methods
US8285352B2 (en) 2008-07-15 2012-10-09 Nellcor Puritan Bennett Llc Systems and methods for identifying pulse rates
US8679027B2 (en) 2008-07-15 2014-03-25 Nellcor Puritan Bennett Ireland Systems and methods for pulse processing
US8226568B2 (en) * 2008-07-15 2012-07-24 Nellcor Puritan Bennett Llc Signal processing systems and methods using basis functions and wavelet transforms
US8358213B2 (en) 2008-07-15 2013-01-22 Covidien Lp Systems and methods for evaluating a physiological condition using a wavelet transform and identifying a band within a generated scalogram
US9687161B2 (en) 2008-09-30 2017-06-27 Nellcor Puritan Bennett Ireland Systems and methods for maintaining blood pressure monitor calibration
US9301697B2 (en) 2008-09-30 2016-04-05 Nellcor Puritan Bennett Ireland Systems and methods for recalibrating a non-invasive blood pressure monitor
US9314168B2 (en) 2008-09-30 2016-04-19 Nellcor Puritan Bennett Ireland Detecting sleep events using localized blood pressure changes
US8532751B2 (en) 2008-09-30 2013-09-10 Covidien Lp Laser self-mixing sensors for biological sensing
US8410951B2 (en) * 2008-09-30 2013-04-02 Covidien Lp Detecting a signal quality decrease in a measurement system
US8696585B2 (en) * 2008-09-30 2014-04-15 Nellcor Puritan Bennett Ireland Detecting a probe-off event in a measurement system
US9155493B2 (en) 2008-10-03 2015-10-13 Nellcor Puritan Bennett Ireland Methods and apparatus for calibrating respiratory effort from photoplethysmograph signals
US20100087714A1 (en) * 2008-10-03 2010-04-08 Nellcor Puritan Bennett Ireland Reducing cross-talk in a measurement system
US9011347B2 (en) 2008-10-03 2015-04-21 Nellcor Puritan Bennett Ireland Methods and apparatus for determining breathing effort characteristics measures
WO2010053845A1 (en) 2008-11-05 2010-05-14 Nellcor Puritan Bennett Llc System and method for facilitating observation of monitored physiologic data
FR2939928B1 (fr) * 2008-12-15 2012-08-03 Snecma Standardisation de donnees utilisees pour la surveillance d'un moteur d'aeronef
US8216136B2 (en) 2009-03-05 2012-07-10 Nellcor Puritan Bennett Llc Systems and methods for monitoring heart rate and blood pressure correlation
US20100298728A1 (en) * 2009-05-20 2010-11-25 Nellcor Puritan Bennett Ireland Signal Processing Techniques For Determining Signal Quality Using A Wavelet Transform Ratio Surface
US8364225B2 (en) * 2009-05-20 2013-01-29 Nellcor Puritan Bennett Ireland Estimating transform values using signal estimates
US8444570B2 (en) * 2009-06-09 2013-05-21 Nellcor Puritan Bennett Ireland Signal processing techniques for aiding the interpretation of respiration signals
US20100324827A1 (en) * 2009-06-18 2010-12-23 Nellcor Puritan Bennett Ireland Fluid Responsiveness Measure
US20100331716A1 (en) * 2009-06-26 2010-12-30 Nellcor Puritan Bennett Ireland Methods and apparatus for measuring respiratory function using an effort signal
US8290730B2 (en) 2009-06-30 2012-10-16 Nellcor Puritan Bennett Ireland Systems and methods for assessing measurements in physiological monitoring devices
US9198582B2 (en) 2009-06-30 2015-12-01 Nellcor Puritan Bennett Ireland Determining a characteristic physiological parameter
US20100331715A1 (en) * 2009-06-30 2010-12-30 Nellcor Puritan Bennett Ireland Systems and methods for detecting effort events
US8636667B2 (en) 2009-07-06 2014-01-28 Nellcor Puritan Bennett Ireland Systems and methods for processing physiological signals in wavelet space
US20110021892A1 (en) * 2009-07-23 2011-01-27 Nellcor Puritan Bennett Ireland Systems and methods for respiration monitoring
US8594759B2 (en) * 2009-07-30 2013-11-26 Nellcor Puritan Bennett Ireland Systems and methods for resolving the continuous wavelet transform of a signal
US8346333B2 (en) * 2009-07-30 2013-01-01 Nellcor Puritan Bennett Ireland Systems and methods for estimating values of a continuous wavelet transform
US8478376B2 (en) * 2009-07-30 2013-07-02 Nellcor Puritan Bennett Ireland Systems and methods for determining physiological information using selective transform data
US8628477B2 (en) 2009-07-31 2014-01-14 Nellcor Puritan Bennett Ireland Systems and methods for non-invasive determination of blood pressure
US8755854B2 (en) 2009-07-31 2014-06-17 Nellcor Puritan Bennett Ireland Methods and apparatus for producing and using lightly filtered photoplethysmograph signals
US9220440B2 (en) 2009-09-21 2015-12-29 Nellcor Puritan Bennett Ireland Determining a characteristic respiration rate
US8855749B2 (en) 2009-09-24 2014-10-07 Covidien Lp Determination of a physiological parameter
US8923945B2 (en) 2009-09-24 2014-12-30 Covidien Lp Determination of a physiological parameter
US8400149B2 (en) * 2009-09-25 2013-03-19 Nellcor Puritan Bennett Ireland Systems and methods for gating an imaging device
US9066660B2 (en) 2009-09-29 2015-06-30 Nellcor Puritan Bennett Ireland Systems and methods for high-pass filtering a photoplethysmograph signal
US20110077484A1 (en) * 2009-09-30 2011-03-31 Nellcor Puritan Bennett Ireland Systems And Methods For Identifying Non-Corrupted Signal Segments For Use In Determining Physiological Parameters
US8463347B2 (en) 2009-09-30 2013-06-11 Nellcor Puritan Bennett Ireland Systems and methods for normalizing a plethysmograph signal for improved feature analysis
US20110098933A1 (en) * 2009-10-26 2011-04-28 Nellcor Puritan Bennett Ireland Systems And Methods For Processing Oximetry Signals Using Least Median Squares Techniques
US9451887B2 (en) 2010-03-31 2016-09-27 Nellcor Puritan Bennett Ireland Systems and methods for measuring electromechanical delay of the heart
US9320430B2 (en) 2010-03-31 2016-04-26 Reichert, Inc. Ophthalmic diagnostic instrument and method
US8898037B2 (en) 2010-04-28 2014-11-25 Nellcor Puritan Bennett Ireland Systems and methods for signal monitoring using Lissajous figures
US9050043B2 (en) 2010-05-04 2015-06-09 Nellcor Puritan Bennett Ireland Systems and methods for wavelet transform scale-dependent multiple-archetyping
US8834378B2 (en) 2010-07-30 2014-09-16 Nellcor Puritan Bennett Ireland Systems and methods for determining respiratory effort
US8825428B2 (en) 2010-11-30 2014-09-02 Neilcor Puritan Bennett Ireland Methods and systems for recalibrating a blood pressure monitor with memory
US9357934B2 (en) 2010-12-01 2016-06-07 Nellcor Puritan Bennett Ireland Systems and methods for physiological event marking
US9259160B2 (en) 2010-12-01 2016-02-16 Nellcor Puritan Bennett Ireland Systems and methods for determining when to measure a physiological parameter
TW201224822A (en) * 2010-12-06 2012-06-16 Ind Tech Res Inst Computerize health management method and health management electronic device
EP2462871A1 (en) * 2010-12-13 2012-06-13 Acarix A/S System, stethoscope and method for indicating risk of coronary artery disease
US9072433B2 (en) 2011-02-18 2015-07-07 Covidien Lp Method and apparatus for noninvasive blood pressure measurement using pulse oximetry
US8721557B2 (en) 2011-02-18 2014-05-13 Covidien Lp Pattern of cuff inflation and deflation for non-invasive blood pressure measurement
US9113830B2 (en) 2011-05-31 2015-08-25 Nellcor Puritan Bennett Ireland Systems and methods for detecting and monitoring arrhythmias using the PPG
CN103747724B (zh) * 2011-07-05 2016-06-22 皇家飞利浦有限公司 用于确定感兴趣动脉在变化的压力下开放/闭合切换时刻的方法、设备和系统
US9597022B2 (en) 2011-09-09 2017-03-21 Nellcor Puritan Bennett Ireland Venous oxygen saturation systems and methods
US9402554B2 (en) 2011-09-23 2016-08-02 Nellcor Puritan Bennett Ireland Systems and methods for determining respiration information from a photoplethysmograph
US9675274B2 (en) 2011-09-23 2017-06-13 Nellcor Puritan Bennett Ireland Systems and methods for determining respiration information from a photoplethysmograph
US9693709B2 (en) 2011-09-23 2017-07-04 Nellcot Puritan Bennett Ireland Systems and methods for determining respiration information from a photoplethysmograph
US8880576B2 (en) 2011-09-23 2014-11-04 Nellcor Puritan Bennett Ireland Systems and methods for determining respiration information from a photoplethysmograph
US9119597B2 (en) 2011-09-23 2015-09-01 Nellcor Puritan Bennett Ireland Systems and methods for determining respiration information from a photoplethysmograph
US8870783B2 (en) 2011-11-30 2014-10-28 Covidien Lp Pulse rate determination using Gaussian kernel smoothing of multiple inter-fiducial pulse periods
US8755871B2 (en) 2011-11-30 2014-06-17 Covidien Lp Systems and methods for detecting arrhythmia from a physiological signal
US9693736B2 (en) 2011-11-30 2017-07-04 Nellcor Puritan Bennett Ireland Systems and methods for determining respiration information using historical distribution
US9060695B2 (en) 2011-11-30 2015-06-23 Covidien Lp Systems and methods for determining differential pulse transit time from the phase difference of two analog plethysmographs
US9247896B2 (en) 2012-01-04 2016-02-02 Nellcor Puritan Bennett Ireland Systems and methods for determining respiration information using phase locked loop
US9179876B2 (en) 2012-04-30 2015-11-10 Nellcor Puritan Bennett Ireland Systems and methods for identifying portions of a physiological signal usable for determining physiological information
US9241670B2 (en) 2012-09-11 2016-01-26 Covidien Lp Methods and systems for conditioning physiological information using a normalization technique
US9560978B2 (en) 2013-02-05 2017-02-07 Covidien Lp Systems and methods for determining respiration information from a physiological signal using amplitude demodulation
US9687159B2 (en) 2013-02-27 2017-06-27 Covidien Lp Systems and methods for determining physiological information by identifying fiducial points in a physiological signal
US9554712B2 (en) 2013-02-27 2017-01-31 Covidien Lp Systems and methods for generating an artificial photoplethysmograph signal
US9974468B2 (en) 2013-03-15 2018-05-22 Covidien Lp Systems and methods for identifying a medically monitored patient
US10226188B2 (en) 2013-08-23 2019-03-12 Covidien Lp Systems and methods for monitoring blood pressure
US10022068B2 (en) 2013-10-28 2018-07-17 Covidien Lp Systems and methods for detecting held breath events
US9848820B2 (en) 2014-01-07 2017-12-26 Covidien Lp Apnea analysis system and method
US9955894B2 (en) 2014-01-28 2018-05-01 Covidien Lp Non-stationary feature relationship parameters for awareness monitoring
WO2015127281A1 (en) 2014-02-20 2015-08-27 Covidien Lp Systems and methods for filtering autocorrelation peaks and detecting harmonics
CN107205671A (zh) * 2014-08-22 2017-09-26 普尔斯地质构造有限责任公司 至少部分基于脉搏波形的自动诊断
JP7187493B2 (ja) * 2017-03-02 2022-12-12 アトコア メディカル ピーティーワイ リミテッド 非侵襲的な上腕血圧測定
US11284827B2 (en) 2017-10-21 2022-03-29 Ausculsciences, Inc. Medical decision support system
US11471090B2 (en) * 2018-06-04 2022-10-18 Analytics For Life Inc. Method and system to assess pulmonary hypertension using phase space tomography and machine learning
CN109528196B (zh) * 2018-11-14 2022-07-01 北京工业大学 一种肝静脉压力梯度无创性评估方法
CN112233750B (zh) * 2020-10-20 2024-02-02 吾征智能技术(北京)有限公司 一种基于咯血性状及疾病的信息匹配系统
CN113449636B (zh) * 2021-06-28 2024-03-12 苏州美糯爱医疗科技有限公司 一种基于人工智能的主动脉瓣狭窄严重程度自动分类方法

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4289141A (en) * 1976-08-19 1981-09-15 Cormier Cardiac Systems, Inc. Method and apparatus for extracting systolic valvular events from heart sounds
US4899758A (en) * 1986-01-31 1990-02-13 Regents Of The University Of Minnesota Method and apparatus for monitoring and diagnosing hypertension and congestive heart failure
US5054493A (en) * 1986-01-31 1991-10-08 Regents Of The University Of Minnesota Method for diagnosing, monitoring and treating hypertension
US5092343A (en) * 1988-02-17 1992-03-03 Wayne State University Waveform analysis apparatus and method using neural network techniques
US5740270A (en) * 1988-04-08 1998-04-14 Neuromedical Systems, Inc. Automated cytological specimen classification system and method
US5265011A (en) * 1989-04-03 1993-11-23 Eastern Medical Testing Services, Inc. Method for ascertaining the pressure pulse and related parameters in the ascending aorta from the contour of the pressure pulse in the peripheral arteries
US5339818A (en) * 1989-09-20 1994-08-23 University Of Utah Research Foundation Method for determining blood pressure utilizing a neural network
US5402521A (en) * 1990-02-28 1995-03-28 Chiyoda Corporation Method for recognition of abnormal conditions using neural networks
US5276612A (en) * 1990-09-21 1994-01-04 New England Medical Center Hospitals, Inc. Risk management system for use with cardiac patients
US5211177A (en) * 1990-12-28 1993-05-18 Regents Of The University Of Minnesota Vascular impedance measurement instrument
US5280792A (en) * 1991-09-20 1994-01-25 The University Of Sydney Method and system for automatically classifying intracardiac electrograms
US5703965A (en) * 1992-06-05 1997-12-30 The Regents Of The University Of California Image compression/decompression based on mathematical transform, reduction/expansion, and image sharpening
US5542421A (en) * 1992-07-31 1996-08-06 Frederick Erdman Association Method and apparatus for cardiovascular diagnosis
DE69416475T2 (de) * 1993-04-02 1999-07-22 Nagano, Ken, Nagano, Nagano Elektronisches instrument zur blutdruck-messung
US5390679A (en) * 1993-06-03 1995-02-21 Eli Lilly And Company Continuous cardiac output derived from the arterial pressure waveform using pattern recognition
US5444796A (en) * 1993-10-18 1995-08-22 Bayer Corporation Method for unsupervised neural network classification with back propagation
US5400795A (en) * 1993-10-22 1995-03-28 Telectronics Pacing Systems, Inc. Method of classifying heart rhythms by analyzing several morphology defining metrics derived for a patient's QRS complex
US5533511A (en) * 1994-01-05 1996-07-09 Vital Insite, Incorporated Apparatus and method for noninvasive blood pressure measurement
US5503156A (en) * 1994-03-11 1996-04-02 Millar Instruments, Inc. Noninvasive pulse transducer for simultaneously measuring pulse pressure and velocity
US5638823A (en) * 1995-08-28 1997-06-17 Rutgers University System and method for noninvasive detection of arterial stenosis
NL1001309C2 (nl) * 1995-09-28 1997-04-03 Tno Werkwijze en inrichting voor de bepaling van brachiale arteriedrukgolf op basis van nietinvasief gemeten vingerbloeddrukgolf.
US5799100A (en) * 1996-06-03 1998-08-25 University Of South Florida Computer-assisted method and apparatus for analysis of x-ray images using wavelet transforms
US5839438A (en) * 1996-09-10 1998-11-24 Neuralmed, Inc. Computer-based neural network system and method for medical diagnosis and interpretation
US5778881A (en) * 1996-12-04 1998-07-14 Medtronic, Inc. Method and apparatus for discriminating P and R waves
US5848193A (en) * 1997-04-07 1998-12-08 The United States Of America As Represented By The Secretary Of The Navy Wavelet projection transform features applied to real time pattern recognition

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101785666B (zh) * 2008-11-21 2014-02-12 普尔松医疗系统公司 用于确定生理参数的仪器及方法
CN102549588A (zh) * 2009-08-10 2012-07-04 糖尿病工具瑞典股份公司 用于产生状态指示的装置和方法

Also Published As

Publication number Publication date
WO1999057647A1 (en) 1999-11-11
CN1299486A (zh) 2001-06-13
EP1075678A1 (en) 2001-02-14
US6135966A (en) 2000-10-24
AU3695799A (en) 1999-11-23
CA2330572A1 (en) 1999-11-11

Similar Documents

Publication Publication Date Title
CN1117331C (zh) 非侵入诊断心血管及相关疾病的方法和仪器
US11478215B2 (en) System and method for infrasonic cardiac monitoring
JP7261811B2 (ja) 訓練された予測モデルに基づく血圧降下の非侵襲的決定のためのシステム及び方法
Roy et al. Improving photoplethysmographic measurements under motion artifacts using artificial neural network for personal healthcare
CN114376564B (zh) 一种基于心冲击信号的睡眠分期方法、系统、装置及介质
CN101801263B (zh) 监测生理状况和检测异常
Vakulenko Indicators and main capabilities of the Oranta-AO information system used in the analysis of arterial pulsations recorded during blood pressure measurement In: DV Vakulenko, LO Vakulenko (eds.) Arterial oscillography: New capabilities of the blood pressure monitor with the Oranta-AO information system
Vakulenko Comparative analysis of the reaction vessels of the left and right shoulder to increasing compression during blood pressure measurement according to the morphological analysis of arterial pulsations using the Oranta-AO information system In: DV Vakulenko, LO Vakulenko (eds.) Arterial oscillography: New capabilities of the blood pressure monitor with the Oranta-AO information system
CN111714088B (zh) 基于中医原理的人体特征指标检测方法和系统
CN112274120B (zh) 一种基于单路脉搏波的无创动脉硬化检测方法、装置
CN118333107B (zh) 基于扩散模型的ppg生成ecg跨模态生成方法
Cao et al. Guard your heart silently: Continuous electrocardiogram waveform monitoring with wrist-worn motion sensor
WO2023129752A1 (en) Assessment of hemodynamics parameters
CN116049674A (zh) 一种基于生成对抗网络的有创血压波形估计的方法及系统
Moran et al. Deep transfer learning for chronic obstructive pulmonary disease detection utilizing electrocardiogram signals
Liu et al. Semantic segmentation of qrs complex in single channel ecg with bidirectional lstm networks
CN114145725B (zh) 一种基于无创连续血压测量的ppg采样率估算方法
Nikolaev et al. Structural architectural solutions for an intelligence system of cardiological screening of diabetes patients
Vieira Multimodal deep learning for heart sound and electrocardiogram classification
Alexandridi et al. Hardware design for the computation of heart rate variability
RU2442529C1 (ru) Способ диагностирования сердечно-сосудистой системы
Antikainen Time Series Analytics for Decision Support in Chronic Diseases: Clinical case studies
Jacobson Analysis and classification of physiological signals using wavelet transforms
Wu et al. Self-Supervised Learning for Biomedical Signal Processing: A Systematic Review on ECG and PPG Signals
Alexandridi et al. An integrated system for the diagnosis of cardiac pathology through the analysis of heartbeat interval variability

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
C19 Lapse of patent right due to non-payment of the annual fee
CF01 Termination of patent right due to non-payment of annual fee
REG Reference to a national code

Ref country code: HK

Ref legal event code: GR

Ref document number: 1061326

Country of ref document: HK