WO2014169595A1 - Procédé et système d'analyse d'arythmies - Google Patents

Procédé et système d'analyse d'arythmies Download PDF

Info

Publication number
WO2014169595A1
WO2014169595A1 PCT/CN2013/085178 CN2013085178W WO2014169595A1 WO 2014169595 A1 WO2014169595 A1 WO 2014169595A1 CN 2013085178 W CN2013085178 W CN 2013085178W WO 2014169595 A1 WO2014169595 A1 WO 2014169595A1
Authority
WO
WIPO (PCT)
Prior art keywords
parameter
arrhythmia analysis
waveform parameter
analysis result
abnormal
Prior art date
Application number
PCT/CN2013/085178
Other languages
English (en)
Chinese (zh)
Inventor
尹鹏
李尔松
邹海涛
Original Assignee
深圳市科曼医疗设备有限公司
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 深圳市科曼医疗设备有限公司 filed Critical 深圳市科曼医疗设备有限公司
Publication of WO2014169595A1 publication Critical patent/WO2014169595A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/364—Detecting abnormal ECG interval, e.g. extrasystoles, ectopic heartbeats
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT 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

Definitions

  • the present invention relates to the field of medical devices, and in particular to an arrhythmia analysis method and system.
  • the waveform analysis method is based on the characteristic waveforms in the ECG signal (such as an electrocardiogram).
  • the characteristic waveform of the ECG signal refers to some indicative peaks and troughs in the ECG signal, such as P, Q, R, S, T. Waves, etc., where P waves represent atrial depolarization, QRS complexes represent ventricular depolarization, and T waves represent ventricular repolarization.
  • Waveform analysis first obtains characteristic waveform parameters, such as the amplitude, time length, rise/fall time, and waveform interval of the characteristic waveform. These characteristic waveform parameters are pre-cured in the arrhythmia analysis instrument according to clinical experience.
  • the obtained characteristic waveform parameters are compared with the fixed judgment threshold.
  • the arrhythmia analysis result can be determined, such as morning room, early morning two-law, and atrial fibrillation.
  • the template matching method mainly calculates the average RR interval and the R wave average shape in the ECG signal of the subject as a template, and compares the RR interval and the R wave shape of each heartbeat of the subject with the template, if both If the difference is beyond a certain range, it is considered that an arrhythmia has occurred.
  • the waveform analysis method uses the empirical threshold value of the cured characteristic waveform parameters as a basis for judging. Although it is universal, it is suitable for people with special ages and special physiques, especially for neonatal electrocardiogram detection. The signal is weak, the QRS wave time limit is short, and the newborn crying has a large interference to the ECG detection, so it is easy to get the wrong arrhythmia analysis result.
  • the template analysis method can only make effective judgments when the R wave shape of the subject is greatly different from the template, and the arrhythmia waveform with insignificant difference cannot be effectively judged.
  • Embodiments of the present invention provide an arrhythmia analysis method, including:
  • the embodiment of the invention further provides an arrhythmia analysis system, which comprises:
  • An abnormal feature waveform parameter obtaining module configured to acquire an abnormal feature waveform parameter in the sample of the ECG signal of the detected object
  • the arrhythmia analysis module is configured to calculate an arrhythmia analysis result by using a support vector machine algorithm according to the abnormal feature waveform parameter;
  • An analysis result input/output module configured to output and display the arrhythmia analysis result, wherein the analysis result input/output module is further configured to determine whether a correction parameter of the arrhythmia analysis result is received, and if yes, the analysis result input /output module is also used to output display correction results;
  • the algorithm modifying module is configured to modify the support vector machine algorithm according to the modified parameter and the abnormal feature waveform parameter.
  • the support vector machine algorithm is used to calculate the arrhythmia analysis result according to the abnormal feature waveform parameter, which can meet the accuracy requirement of the arrhythmia analysis of the general population ECG signal detection sample.
  • the support vector machine algorithm is modified according to the input correction result, thereby realizing the self-learning function of the ECG signal detection sample, and similar detection is detected again.
  • the correct correction result can be outputted at the time of the sample, thereby reducing the false positive rate and the missed rate of the arrhythmia analysis.
  • FIG. 1 is a schematic flow chart of an arrhythmia analysis method provided by an embodiment
  • FIG. 2 is a schematic flow chart showing an implementation process of step S11 in an arrhythmia analysis method provided by the embodiment shown in FIG. 1;
  • step S12 in an arrhythmia analysis method provided by the embodiment shown in FIG. 1;
  • FIG. 4 is a schematic flowchart of an implementation process of modifying a support vector machine in step S14 in an arrhythmia analysis method provided by the embodiment shown in FIG. 1;
  • FIG. 5 is a schematic structural diagram of an arrhythmia analysis system according to an embodiment
  • FIG. 6 is a schematic structural diagram of an abnormal feature waveform parameter obtaining module provided in the embodiment shown in FIG. 5;
  • FIG. 7 is a schematic structural diagram of an arrhythmia analysis module provided by the embodiment shown in FIG. 5;
  • FIG. 8 is a schematic structural diagram of an algorithm modification module provided by the embodiment shown in FIG. 5.
  • an arrhythmia analysis method is provided, the flow of which includes:
  • step S11 may be, but is not limited to, performing the following steps:
  • Step S112 extracting characteristic waveform parameters in the sample of the ECG signal of the detected object.
  • the characteristic waveform of the ECG signal refers to some bands with indicative meanings in the ECG signal, such as P wave, QRS complex wave, T wave and so on. Characteristic waveform parameters, including the amplitude, length of time, rise/fall time, and waveform interval of the characteristic waveform.
  • Step S114 comparing the characteristic waveform parameter with a preset parameter threshold, and determining whether the parameter threshold needs to be corrected according to the frequency of the characteristic waveform parameter exceeding the parameter threshold.
  • the extracted characteristic waveform parameters are compared with preset parameter thresholds to determine whether the characteristic waveform parameters exceed a preset parameter threshold.
  • the parameter threshold is preset to the average value of the characteristic waveform parameter according to a medical general normal standard.
  • the QRS wave width is normally 60-100 ms, and the preset QRS wave width threshold may be 80 ms.
  • the preset QRS wave width threshold may be 80 ms.
  • the frequency of the characteristic waveform parameter exceeding the preset parameter threshold is defined, which may be determined according to factors such as the population distribution of the detected person.
  • Step S116 if yes, correcting the parameter threshold, and using the characteristic waveform parameter exceeding the corrected parameter threshold as the abnormal characteristic waveform parameter;
  • Step S118 if no, the characteristic waveform parameter exceeding the preset parameter threshold is used as the abnormal feature waveform parameter.
  • correction of the parameter threshold should not exceed the general normal standard of medicine.
  • the QRS wave is used as an example.
  • the preset QRS width threshold can be 80ms. When the QRS wave in the waveform of the ECG signal is detected, If 80% exceeds the preset threshold, the QRS wave width threshold can be corrected to 100ms. If the parameter threshold is not corrected, the characteristic waveform parameter exceeding the preset parameter threshold is used as the abnormal characteristic waveform parameter. If the parameter threshold is corrected, the characteristic waveform parameter exceeding the corrected parameter threshold is used as the abnormal characteristic waveform. parameter. After the detected object is detected, the characteristic waveform parameter threshold will be restored to the preset parameter threshold.
  • the parameter threshold is not a fixed value solidified inside the machine, but can be corrected according to the specific detection situation, and the misjudgment caused by the fixed parameter threshold is reduced, Missing the situation.
  • the support vector machine algorithm is used to calculate the arrhythmia analysis result
  • the Machine (SVM) algorithm defines three tuples: the input space I of the problem, the space T of the problem solving mechanism, and the solution space O of the problem.
  • the input space I input of the problem is an abnormal characteristic waveform parameter, such as waveform amplitude, waveform time length, waveform interval, etc.
  • the solution space O of the problem is the arrhythmia analysis result, such as room early, second law, triple law, room Trembling.
  • the SVM algorithm can be viewed as a function of input space I to solution space O.
  • step S12 may include:
  • Step S122 input an abnormal feature waveform parameter.
  • the abnormal feature waveform parameter acquired at step S11 is transmitted as an input to the input space I of the SVM algorithm.
  • step S124 the abnormal characteristic waveform parameter is taken as an input, and the arrhythmia analysis result is calculated according to the transfer function of the support vector machine.
  • the transfer function of the algorithm is constructed in the solution mechanism space T of the SVM algorithm, and the input is an abnormal feature waveform parameter, and the final output is the arrhythmia analysis result.
  • the transfer function of the algorithm consists of multi-layer transfer sub-functions. Each input of each layer transfer sub-function has its corresponding input weight factor. The input and input weight factors act as the output of the layer transfer sub-function. Pass the subfunction to the lower layer.
  • step S126 the arrhythmia analysis result is output.
  • the arrhythmia analysis result calculated by the transfer function is outputted by the problem solving space O, and when implemented, may, but is not limited to, display the arrhythmia analysis result through the human-machine interface.
  • the arrhythmia analysis result given by the machine using the arrhythmia analysis method may deviate from the arrhythmia analysis result obtained by the doctor according to the patient's ECG waveform, the doctor may according to the actual clinical situation.
  • the result obtained by the machine is corrected.
  • the correction is implemented by the human-computer interaction interface on the machine.
  • the doctor can choose to correct the arrhythmia analysis result in the interface.
  • the correction parameter given by the doctor in the interface can be Not limited to the final arrhythmia analysis results, such as room early, two law.
  • the machine When the machine receives the correction result, it corrects the support vector machine algorithm and outputs the display correction result.
  • step S14 modifying the support vector machine algorithm specifically includes:
  • Step S142 acquiring a correction parameter and an abnormal feature waveform parameter.
  • Obtaining the correction parameters and the anomaly characteristic waveform parameters is the input space I that determines the problem of the SVM algorithm and the solution space O of the problem.
  • Step S144 adjusting an input weighting factor of the support vector machine transfer function according to the modified parameter and the abnormal feature waveform parameter.
  • the input weighting factors of the transfer function of each layer of the transfer function in the problem solving mechanism space T are adjusted, so that In the case of the current input space I input, the problem can be solved by the problem solving mechanism space T.
  • Modifying the support vector machine algorithm can be regarded as the "self-learning" process of the SVM algorithm. Before and after the arrhythmia analysis machine is shipped from the factory and in subsequent practical applications, a large number of ECG signal detection samples of various ages can be “learned”, which greatly improves the accuracy of arrhythmia analysis and reduces the false positive rate and missed rate.
  • Step S146 the input weighting factor of the adjusted support vector machine transfer function is saved.
  • the input weight factor of the adjusted support vector machine transfer function is saved.
  • the SVM algorithm transfer function adopts the adjusted input weight factor.
  • the arrhythmia analysis method provided by the embodiment uses the support vector machine algorithm to calculate the arrhythmia analysis result, which can meet the accuracy requirement of the arrhythmia analysis of the general population ECG detection sample, when encountering a special population
  • the support vector machine algorithm is modified according to the input correction result, thereby realizing the self-learning function of the ECG signal detection sample, and the output can be correctly output when the similar detection sample is detected again. The result of the correction, thereby reducing the false positive rate and the missed rate of the arrhythmia analysis.
  • an arrhythmia analysis system 20 is provided in accordance with one embodiment of the present invention.
  • An arrhythmia analysis system 20 provided by the embodiment includes an abnormal feature waveform parameter acquisition module 21, an arrhythmia analysis module 22, an algorithm modification module 23, and an analysis result input/output module 24.
  • the abnormal characteristic waveform parameter obtaining module 21 is configured to acquire an abnormal characteristic waveform parameter in the sample of the ECG signal of the detected object. For the working principle, refer to step S11 of the embodiment in FIG. 1 .
  • the arrhythmia analysis module 22 is configured to calculate an arrhythmia analysis result by using a support vector machine algorithm according to the abnormal feature waveform parameter.
  • the analysis result input/output module 24 is configured to output a display arrhythmia analysis result. For the working principle of the above module, refer to step S12 of the embodiment in FIG. 1 .
  • the analysis result input/output module 24 is further configured to determine whether the correction parameter of the arrhythmia analysis result is received, and if so, the display correction result is output.
  • the algorithm modification module 23 is configured to modify the support vector machine algorithm according to the modified parameter and the abnormal feature waveform parameter. For the working principle of the above module, refer to steps S13 and S14 of the embodiment in FIG. 1 .
  • FIG. 6 is a schematic structural diagram of an abnormal feature waveform parameter acquiring module 21 in an arrhythmia analysis system according to an embodiment of the embodiment of FIG.
  • the abnormal feature waveform parameter acquisition module 21 in this embodiment includes a feature waveform parameter extraction unit 211, a parameter threshold comparison correction unit 212, and an abnormal feature waveform parameter storage unit 213.
  • the feature waveform parameter extraction unit 211 is configured to extract feature waveform parameters in the sample of the ECG signal of the subject.
  • the parameter threshold comparison correction unit 212 is configured to compare the characteristic waveform parameter with a preset parameter threshold, determine whether the parameter threshold needs to be corrected according to the frequency of the characteristic waveform parameter exceeding the parameter threshold, and when the parameter threshold needs to be corrected, Correct the parameter threshold.
  • FIG. 7 a schematic structural diagram of the arrhythmia analysis module 22 in the arrhythmia analysis system provided in the embodiment of FIG.
  • the arrhythmia analysis module 22 includes:
  • the abnormal characteristic waveform parameter input unit 221 is configured to input an abnormal characteristic waveform parameter.
  • the transfer function analysis unit 222 is configured to input the abnormal feature waveform parameter as an input, and calculate an arrhythmia analysis result according to the transfer function of the support vector machine.
  • the arrhythmia analysis result transmission unit 223 is configured to transmit the arrhythmia analysis result to the analysis result input/output module 24 for the analysis result input/output module 24 to display the arrhythmia analysis result.
  • FIG. 9 a schematic structural diagram of an algorithm modification module 23 in an arrhythmia analysis system provided in the embodiment of FIG.
  • the algorithm modification module 23 includes:
  • the correction information acquisition unit 231 is configured to acquire a correction result and an abnormal feature waveform parameter.
  • the transfer function modification unit 232 is configured to adjust an input weighting factor of the support vector machine transfer function according to the correction result and the abnormal feature waveform parameter.
  • the transfer function holding unit 233 is configured to save the input weight factor of the adjusted transfer function.
  • the arrhythmia analysis system provided in this embodiment implements the arrhythmia analysis method in Embodiment 1, and the working principle thereof is not described in detail.

Abstract

La présente invention concerne un procédé et un système d'analyse d'arythmies. Le procédé comprend : l'acquisition d'un paramètre de forme d'onde caractéristique d'une anomalie dans un échantillon de signal d'électrocardiographe d'un sujet (S11); l'utilisation, sur la base du paramètre de forme d'onde caractéristique d'une anomalie, d'un algorithme d'une machine à vecteurs de support pour calculer et émettre un résultat d'analyse d'arythmies (S12); la détermination du fait qu'un paramètre de correction pour le résultat d'analyse d'arythmies est reçu ou non (S13) et, si oui, la modification de l'algorithme d'une machine à vecteurs de support sur la base du paramètre de correction et du paramètre de forme d'onde caractéristique d'une anomalie et l'émission du résultat corrigé (S14). Le procédé permet un "autoapprentissage" à partir de l'échantillon de signal d'électrocardiographe, et réduit le taux de faux positifs et le taux de faux négatifs d'une analyse d'arythmies.
PCT/CN2013/085178 2013-04-18 2013-10-14 Procédé et système d'analyse d'arythmies WO2014169595A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201310136210.9A CN103251405B (zh) 2013-04-18 2013-04-18 心律失常分析系统
CN201310136210.9 2013-04-18

Publications (1)

Publication Number Publication Date
WO2014169595A1 true WO2014169595A1 (fr) 2014-10-23

Family

ID=48955885

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/085178 WO2014169595A1 (fr) 2013-04-18 2013-10-14 Procédé et système d'analyse d'arythmies

Country Status (2)

Country Link
CN (1) CN103251405B (fr)
WO (1) WO2014169595A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110751131A (zh) * 2019-11-16 2020-02-04 李汭傧 一种心律失常检测装置
US10687728B2 (en) 2016-12-22 2020-06-23 Cardiac Pacemakers, Inc. Learning techniques for cardiac arrhythmia detection

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103251405B (zh) * 2013-04-18 2015-04-08 深圳市科曼医疗设备有限公司 心律失常分析系统
TWI522958B (zh) * 2014-06-11 2016-02-21 國立成功大學 生理訊號分析方法及其系統與內儲生理訊號分析程式之電腦程式產品
CN104573403B (zh) * 2015-02-05 2019-03-08 上海越光医疗科技有限公司 一种检测事件处理方法
CN105411567B (zh) * 2015-12-15 2018-04-24 北京世纪今科医疗器械有限公司 一种心电图数据分析方法及系统
CN105912879B (zh) * 2016-06-03 2021-04-13 广州馨瑞艾特科技有限公司 一种胎心率曲线修正方法及其装置
CN107944372B (zh) * 2017-11-17 2020-04-07 珠海市多泰吉智能技术有限公司 一种信号有效性识别的方法和设备以及计算机存储介质
US11596343B2 (en) * 2018-01-18 2023-03-07 Shenzhen Mindray Biomedical Electronics Co., Ltd. Method for analyzing arrhythmia in real time, electrocardiogram monitoring device and storage medium
CN110226928B (zh) * 2018-03-06 2022-07-01 深圳市理邦精密仪器股份有限公司 房颤伴室早和房颤伴差传的识别方法和装置
CN109091139B (zh) * 2018-07-13 2021-04-30 希蓝科技（北京）有限公司 一种修正阵发性心律失常事件的方法及装置
CN109637610A (zh) * 2018-11-19 2019-04-16 深圳市理邦精密仪器股份有限公司 心电报告的配置方法、终端设备及介质
TW202021528A (zh) 2018-12-05 2020-06-16 宏碁股份有限公司 基於光電容積描記圖訊號取得心律不整資訊的方法及檢測心律不整的裝置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1951320A (zh) * 2006-11-16 2007-04-25 上海交通大学 基于超完备特征的异常心电识别方法
WO2008007236A2 (fr) * 2006-06-07 2008-01-17 Koninklijke Philips Electronics N.V. Détection de fibrillation auriculaire
US20110224526A1 (en) * 2008-04-15 2011-09-15 Universidad Carlos Iii De Madrid System and method for reconstructing and viewing cardiac electrical activation
CN102274020A (zh) * 2011-06-30 2011-12-14 东北大学 一种低功耗的动态心电监护仪及其控制方法
CN102961129A (zh) * 2012-10-26 2013-03-13 上海交通大学无锡研究院 一种远程医疗的异常心电张量分析方法
CN103251405A (zh) * 2013-04-18 2013-08-21 深圳市科曼医疗设备有限公司 心律失常分析方法和系统

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101546556B (zh) * 2008-03-28 2011-03-23 展讯通信（上海）有限公司 用于音频内容识别的分类系统
CN102129069B (zh) * 2010-12-17 2012-05-09 浙江大学 基于多fpga的波束形成器输出数据带宽控制装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008007236A2 (fr) * 2006-06-07 2008-01-17 Koninklijke Philips Electronics N.V. Détection de fibrillation auriculaire
CN1951320A (zh) * 2006-11-16 2007-04-25 上海交通大学 基于超完备特征的异常心电识别方法
US20110224526A1 (en) * 2008-04-15 2011-09-15 Universidad Carlos Iii De Madrid System and method for reconstructing and viewing cardiac electrical activation
CN102274020A (zh) * 2011-06-30 2011-12-14 东北大学 一种低功耗的动态心电监护仪及其控制方法
CN102961129A (zh) * 2012-10-26 2013-03-13 上海交通大学无锡研究院 一种远程医疗的异常心电张量分析方法
CN103251405A (zh) * 2013-04-18 2013-08-21 深圳市科曼医疗设备有限公司 心律失常分析方法和系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10687728B2 (en) 2016-12-22 2020-06-23 Cardiac Pacemakers, Inc. Learning techniques for cardiac arrhythmia detection
CN110751131A (zh) * 2019-11-16 2020-02-04 李汭傧 一种心律失常检测装置

Also Published As

Publication number Publication date
CN103251405A (zh) 2013-08-21
CN103251405B (zh) 2015-04-08

Similar Documents

Publication Publication Date Title
WO2014169595A1 (fr) Procédé et système d'analyse d'arythmies
CN104173043B (zh) 一种适合于移动平台的心电数据分析方法
Okada A digital filter for the QRS complex detection
Gomez-Clapers et al. A fast and easy-to-use ECG acquisition and heart rate monitoring system using a wireless steering wheel
WO2016195366A1 (fr) Dispositif de prédiction d'arythmie ventriculaire et procédé associé
Chang et al. High-precision real-time premature ventricular contraction (PVC) detection system based on wavelet transform
CN104188683A (zh) 一种可显示、储存与传输心电信号的多功能智慧听诊器
US20210085190A1 (en) Motion sensor-based physiological parameter optimization method and monitoring device
Hegazy et al. The value of Holter monitoring in the assessment of pediatric patients
Lu et al. A portable ECG monitor with low power consumption and small size based on AD8232 chip
Yi et al. Derivation of respiration from ECG measured without subject's awareness using wavelet transform
CN109793532B (zh) 讯号同步处理装置、听诊器、输出系统与病征诊断系统
CN204181639U (zh) 一种可显示、储存与传输心电信号的多功能智慧听诊器
WO2013172569A1 (fr) Défibrillateur à synchronisation automatique comprenant des fonctions permettant de mesurer et d'éliminer un artéfact de mouvement
US11576617B2 (en) Detecting artifacts in a signal
CN104434310A (zh) 监护设备及其参数性能改进方法、系统
Liu et al. Design of a novel portable ECG monitor for heart health
Marhoon et al. A new real-time resource-efficient algorithm for ECG denoising, feature extraction and classification-based wearable sensor network
CN106137183A (zh) 一种基于心电传感器的心电监护供电控制系统
ITMI20140312U1 (it) Dispositivo per lo studio e la diagnosi dei disturbi neurodegenerativi
CN204745287U (zh) 一种基于心率变异性的催眠治疗抑郁症效果评价系统
WO2023092516A1 (fr) Système de compensation de signal électrophysiologique et procédé de compensation
Lejkowski et al. The measurement system for analyzing heart sounds with ECG reference signal
Feng et al. The design of low power portable ECG monitor
WO2019066283A1 (fr) Appareil et procédé de mesure de l'activité des cellules cérébrales dans la circulation de sang artificiel

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13882514

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 22.03.2016)

122 Ep: pct application non-entry in european phase

Ref document number: 13882514

Country of ref document: EP

Kind code of ref document: A1