WO2019100564A1 - 检测报告数据生成方法 - Google Patents

检测报告数据生成方法 Download PDF

Info

Publication number
WO2019100564A1
WO2019100564A1 PCT/CN2018/072358 CN2018072358W WO2019100564A1 WO 2019100564 A1 WO2019100564 A1 WO 2019100564A1 CN 2018072358 W CN2018072358 W CN 2018072358W WO 2019100564 A1 WO2019100564 A1 WO 2019100564A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
segment
event
report
position information
Prior art date
Application number
PCT/CN2018/072358
Other languages
English (en)
French (fr)
Inventor
臧凯丰
卢海涛
赵鹏飞
姜艳
王宝泉
曹君
Original Assignee
乐普（北京）医疗器械股份有限公司
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 乐普（北京）医疗器械股份有限公司 filed Critical 乐普（北京）医疗器械股份有限公司
Priority to EP18881963.5A priority Critical patent/EP3693973A4/en
Priority to US16/755,113 priority patent/US11452476B2/en
Publication of WO2019100564A1 publication Critical patent/WO2019100564A1/zh

Links

Images

Classifications

    • 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
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, 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
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02405—Determining heart rate variability
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, 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
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/0245—Detecting, measuring or recording pulse rate or heart rate by using sensing means generating electric signals, i.e. ECG signals
    • 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]
    • 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
    • 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
    • A61B5/369—Electroencephalography [EEG]
    • A61B5/372—Analysis of electroencephalograms
    • 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
    • A61B5/7221—Determining signal validity, reliability or quality
    • 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
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
    • A61B5/743—Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots
    • 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
    • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof

Definitions

  • the present invention relates to the field of data analysis and processing technologies, and in particular, to a method for generating test report data.
  • ECG monitoring is an important measure for the observation and diagnosis of cardiovascular patients. It can monitor the presence or absence of arrhythmia and frequency of heart beats in real time, and take timely and effective measures according to ECG activities.
  • the output of ECG monitoring is usually achieved by generating an ECG diagnostic report.
  • ECG monitoring especially dynamic ECG monitoring, has a very large amount of data. How to obtain the typical data values required in these data and the most typical data segment output ECG waveform that can most clearly reflect different ECG events, it appears that Particularly important.
  • the object of the present invention is to provide a method for generating test report data, which can automatically identify a typical sample segment of a representative event type from a heartbeat analysis data in combination with a signal quality assessment, and generate a test report by combining event type information and the like. data.
  • the present invention provides a method for generating test report data, including:
  • the ECG event data has one or more event type information
  • the ECG event data is filtered according to the signal quality evaluation parameter, and the report conclusion data and the report item data are obtained;
  • the segment interception parameter includes start position information and intercept width information
  • the report item data, the report graph data, and the report conclusion data are output.
  • the intercepting the pre-selected sample segments according to the segment intercepting parameter to obtain a typical data segment is specifically:
  • the determining the segment intercepting parameter specifically includes:
  • the first preset displacement parameter is forwarded according to the position information of the event heartbeat, and the starting position information is obtained;
  • the second preset displacement parameter is forwarded according to the position information of the event heartbeat to obtain the starting position information.
  • determining the location information of the event heartbeat in the preselected sample segment, and determining the segment interception parameter specifically includes:
  • the event type information is specific event type information
  • calculating an interference-free signal ratio of each data segment in the pre-selected sample segment according to the quality evaluation parameter and determining the event heart according to the interference-free signal ratio Position information of the beat, and determining the intercept width information and the starting position information according to the segment intercepting rule corresponding to the specific event type information.
  • the intercepting the pre-selected sample segments according to the segment intercepting parameter to obtain a typical data segment is specifically:
  • the data segment corresponding to the least heartbeat count is determined as the typical data segment.
  • the method for generating test report data performs quality assessment on each heart rhythm event by calculating noise interference data, selects an event segment with the highest data quality, and simultaneously analyzes the number of event types included in the segment, and preferentially selects the most A representative segment, that is, a segment containing only a single heart rhythm event, preferably the starting position of the segment, as far as possible to ensure that the event heartbeat is located in the middle of the selected segment.
  • a representative segment that is, a segment containing only a single heart rhythm event, preferably the starting position of the segment, as far as possible to ensure that the event heartbeat is located in the middle of the selected segment.
  • FIG. 1 is a schematic diagram of a method for generating test report data according to an embodiment of the present invention.
  • the method for generating test report data provided by the embodiment of the present invention provides a comprehensive and accurate method for generating ECG test report data.
  • FIG. 1 is a schematic diagram of a method for generating test report data according to an embodiment of the present invention.
  • the detection report data generating method of the present invention mainly includes the following steps:
  • Step 110 Acquire event type information of an electrocardiogram event corresponding to the electrocardiogram event data.
  • the ECG monitoring device converts the electrical signal into a digital signal output, which may be a single-lead or multi-lead time series data, and stores the original data through the data storage transmission device, and can pass WIFI, Bluetooth, USB , 3G/4G/5G mobile communication network, Internet of Things and other means of transmission.
  • the original data received by transmission needs to be resampled and converted into a preset standard data format by the data format, thereby solving the lead, sampling frequency and transmission data format used by different ECG devices.
  • Difference, and the data of the converted standard data format after conversion is removed by digital signal filtering to remove high frequency, low frequency noise interference and baseline drift, get heartbeat data, and interfere with heartbeat data, and the heartbeat data is based on
  • the interference recognition result and the time rule are combined according to the lead parameters of the heart beat data to generate heart beat analysis data.
  • the heartbeat analysis data is then generated based on the heartbeat classification information and the electrocardiogram basic rule reference data to generate ECG event data.
  • ECG event data has corresponding event types, such as supraventricular premature beats, atrial escape, ventricular premature beats, ventricular escape, and so on.
  • event types such as supraventricular premature beats, atrial escape, ventricular premature beats, ventricular escape, and so on.
  • event type information we can set event type information to characterize these event types. Therefore, the ECG event data has one or more event type information.
  • Step 120 Filter the ECG event data according to the signal quality evaluation parameter, and obtain report conclusion data and report item data;
  • the report conclusion data and the report item data include data calculated by the heart rate parameter, and the like, and include, for example, calculating an average heart rate, and maximum and minimum heart rate.
  • the maximum and minimum heart rate the fixed-length segment is used as the statistical unit, and the whole process scan and statistical comparison are performed one by one.
  • the length of the clip is generally 8-10 seconds, and can be freely set as needed.
  • the heart rate the statistical calculation method for different heart beat types is adopted for the main body of sinus rhythm and the ectopic heart rhythm.
  • the maximum and minimum heart rate for the sinus rhythm of the main body of the electrocardiogram, only calculate the sinus classification of heart beat; for the ectopic heart rhythm of the atrial flutter atrial fibrillation, only the atrial flutter atrial fibrillation; Other ectopic heartbeats of atrial fibrillation accounted for the ectopic heart rhythm of the subject, and all types of heart beats were involved in the calculation except for the artifacts.
  • Step 130 Perform quality assessment on the event segment included in the ECG event data according to the signal quality evaluation parameter, and determine the pre-selected sample segment by the quality assessment result;
  • the quality evaluation is performed according to the signal quality evaluation parameter, and the event fragment with the highest quality of the data signal is selected.
  • the signal quality evaluation parameters are based on the heartbeat data analysis, and are characterized by the noise level of the QRS complex between the RR intervals. Specifically, it can be calculated by the power of the QRS complex and the average power of the noise signal.
  • Step 140 determining location information of the event heartbeat in the preselected sample segment, and determining the segment interception parameter
  • the segment interception parameter is specifically a start position information and a clipping width information required for confirming a typical data segment. This is also related to the starting position of the event heartbeat.
  • the start position information and the intercept width information can be determined according to the type of the electrocardiogram event.
  • the heart rate data of the first heartbeat in the preselected sample segment may be determined first, and then the corresponding home position information is determined according to the heart rate data of the first heartbeat. For example, when the heart rate data is greater than the upper limit of the preset threshold, the first preset displacement parameter is forwarded according to the position information of the event heartbeat to obtain the starting position information; when the heart rate data is less than the lower limit of the preset threshold, the position information according to the event heartbeat is obtained. The second preset displacement parameter is moved forward to obtain the starting position information.
  • the interference-free signal proportion of each data segment in the pre-selected sample segment is first calculated according to the quality evaluation parameter, and the position information of the event heartbeat is determined according to the ratio of the interference-free signal, and The truncation width information and the starting position information are determined according to the segment intercepting rule corresponding to the specific event type information.
  • sample segment may be corresponding to only one heart cycle, or may correspond to multiple heart cycles.
  • ECG events for non-special rules and ECG events with special rules can be divided into two cases.
  • the termination position information intercepted by the selected sample segment can be obtained based on the position information of the initial position information and the event heartbeat.
  • the starting position of the segment is 0.3 second from the first heartbeat distance.
  • the starting position of the segment is 0.37 seconds away from the first heartbeat distance.
  • the special rule electrocardiogram event mentioned in the present invention may specifically include three types of events: a ventricular tachycardia event, a ventricular tachycardia event, and a long RR interval event whose time length is greater than a preset time threshold; the preset time threshold is preferably 8 seconds.
  • a preset time threshold is preferably 8 seconds.
  • two or more segments can be intercepted. The first segment is extended by 3 heartbeats, and the second segment is extended by 2 heartbeats.
  • the starting position of each segment can be processed in the manner described above for non-special rules.
  • the threshold when processing a special rule ECG event, in addition to determining that the highest-selected sample segment is the typical data segment according to the proportion of the interference-free signal, the threshold may be set, and for the sample segment that reaches the set threshold, Perform screening to select a typical data segment containing the least number of other event categories, and the specific method includes: determining whether the proportion of the interference-free signal reaches a ratio threshold (preferably determining the threshold in the range of 60%-95%); The data segment that meets or exceeds the threshold is subjected to event type singularity screening, and the data segment with the least heartbeat count among the remaining event type information except the target event type information is determined as a typical data segment.
  • a ratio threshold preferably determining the threshold in the range of 60%-95%
  • the purpose of the singularity screening here is to obtain as many sample fragments as possible reflecting the events corresponding to the fragments, that is, try not to have other events.
  • sample fragments with the least corresponding heart beat count obtained by the above steps are still plural, it is determined that the selected sample fragments with the highest proportion of non-interfering signals among the plurality of selected sample fragments are the report sample fragments. If the number of segments is still not unique, the first one is selected as the final preference.
  • Step 150 Perform interception processing on the pre-selected sample segments according to the segment intercepting parameters to obtain a typical data segment
  • the pre-selected sample segment is intercepted according to the initial position information determined by the previous step, the intercept width information, and the position information of the event heartbeat, so that the position of the event heartbeat is in the middle of the selected sample segment obtained, that is, typical data is obtained. Fragment.
  • Step 160 generating report graphic data based on typical data segments.
  • Step 170 Output report item data, report graphic data, and report conclusion data.
  • the report item data, the report graph data, and the report conclusion data may be output according to a preset data output format.
  • the method for generating test report data performs quality assessment on each heart rhythm event by calculating noise interference data, selects an event segment with the highest data quality, and simultaneously analyzes the number of event types included in the segment, and preferentially selects the most A representative segment, that is, a segment containing only a single heart rhythm event, by reasonably locating the starting position of the segment, tries to ensure that the event heartbeat is located in the middle of the selected segment, and that a particular rule is preferably set for the segment of the particular ECG event.
  • the test report data is generated by combining the selected typical data segments, event type information, and the like.
  • the steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both.
  • the software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Cardiology (AREA)
  • Physics & Mathematics (AREA)
  • Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Physiology (AREA)
  • Signal Processing (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Psychology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

一种检测报告数据生成方法，包括：获取心电图事件数据对应的心电图事件的事件类型信息(110)；心电图事件数据具有一个或多个事件类型信息；根据信号质量评价参数对心电图事件数据进行筛选，得到报告结论数据和报告表项数据(120)；根据信号质量评价参数对心电图事件数据包含的事件片段进行质量评估，根据质量评估结果确定预选样本片段(130)；确定预选样本片段中事件心搏的位置信息，并确定片段截取参数(140)；片段截取参数包括起始位置信息和截取宽度信息；根据片段截取参数对预选样本片段进行截取处理得到典型数据片段(150)；根据典型数据片段生成报告图形数据(160)；输出报告表项数据、报告图形数据和报告结论数据(170)。

Description

检测报告数据生成方法
本申请要求于2017年11月27日提交中国专利局、申请号为201711202991.1、发明名称为“检测报告数据生成方法”的中国专利申请的优先权。
技术领域
本发明涉及数据分析处理技术领域，尤其涉及一种检测报告数据生成方法。
背景技术
心电监测是心血管患者病情观察及诊疗的一项重要措施，可以实时监测有无心律失常、心脏搏动的频率等，并根据心电活动采取及时有效的措施。而心电监测的结果输出，通常是以生成心电诊断报告的方式来实现的。
然而，心电监测，尤其是动态心电监测，数据量非常大，如何在这些数据中获取到所需要的典型数据值和能够最明显反映不同心电图事件的最典型数据段输出心电图波形，就显得尤为重要。
发明内容
本发明的目的是提供一种检测报告数据生成方法，能够结合信号质量评估，自动从心搏分析数据中识别所需要的能代表事件类型的典型样本片段，并结合事件类型信息等，生成检测报告数据。
为实现上述目的，本发明提供了一种检测报告数据生成方法，包括：
获取心电图事件数据对应的心电图事件的事件类型信息；所述心电图 事件数据具有一个或多个事件类型信息；
根据信号质量评价参数对所述心电图事件数据进行筛选，得到报告结论数据和报告表项数据；
根据所述信号质量评价参数对所述心电图事件数据包含的事件片段进行质量评估，根据所述质量评估结果确定预选样本片段；
确定所述预选样本片段中事件心搏的位置信息，并确定片段截取参数；所述片段截取参数包括起始位置信息和截取宽度信息；
根据所述片段截取参数对所述预选样本片段进行截取处理得到典型数据片段；
根据所述典型数据片段生成报告图形数据；
输出所述报告表项数据、报告图形数据和报告结论数据。
优选的,所述根据所述片段截取参数对所述预选样本片段进行截取处理得到典型数据片段具体为：
根据所述起始位置信息、截取宽度信息和所述事件心搏的位置信息对所述预选样本片段进行截取，使得所述事件心搏的位置处于所述截取得到的典型数据片段的中部。
优选的,所述确定片段截取参数具体包括：
确定所述预选样本片段中的第一个心搏的心率数据；
当所述心率数据大于预设阈值上限时，根据事件心搏的位置信息前移第一预设位移参数，得到所述起始位置信息；
当所述心律数据小于预设阈值下限时，根据事件心搏的位置信息前移第二预设位移参数，得到所述起始位置信息。
进一步优选的,所述确定所述预选样本片段中事件心搏的位置信息，并确定片段截取参数具体包括：
当所述事件类型信息为特定事件类型信息时，根据所述质量评价参数计算所述预选样本片段中各数据片段的无干扰信号占比，并根据所述无干 扰信号占比确定所述事件心搏的位置信息，并根据所述特定事件类型信息对应的片段截取规则确定所述截取宽度信息和起始位置信息。
进一步优选的,所述根据所述片段截取参数对所述预选样本片段进行截取处理得到典型数据片段具体为：
确定所述无干扰信号的占比是否达到占比阈值；
对达到或高于所述占比阈值的多个数据片段进行事件类型单一性筛选；
将筛选得到的除目标事件类型信息外的其余事件类型信息中，对应心搏计数最少的数据片段确定为所述典型数据片段。
本发明实施例提供的检测报告数据生成方法，对每种心律事件，通过计算噪音干扰数据进行质量评估，选取数据质量最高的事件片段，同时分析片段中的包含的事件种类数量，优先选取最具代表性的片段，即仅含有单一心律事件的片段，优选片段的开始位置，尽量保证事件心搏位于所选取片段的中部。对于特定心电图事件的片段优选有特殊规则。
附图说明
图1为本发明实施例提供的检测报告数据生成方法的示意图。
具体实施方式
下面通过附图和实施例，对本发明的技术方案做进一步的详细描述。
本发明实施例提供的检测报告数据生成方法，提供了一种全面、准确的心电图检测报告数据的生成方式。
图1为本发明实施例提供的检测报告数据生成方法的示意图。如图1所示，本发明的检测报告数据生成方法主要包括如下步骤：
步骤110，获取心电图事件数据对应的心电图事件的事件类型信息；
具体的，心电监测设备将电信号转换为数字信号输出，具体可以是单 导联或多导联的时间序列数据，通过数据存储传输装置进行原始数据的存储，并可以通过WIFI、蓝牙，USB，3G/4G/5G移动通信网络，物联网等方式进行传输。
在心电信号质量评估之前，通过传输接收到的原始数据需要先进行重采样并通过数据格式转换为预设标准数据格式，由此可以解决不同心电图设备在使用的导联，采样频率和传输数据格式差异，并对转换后的预设标准数据格式的数据通过数字信号滤波去除高频，低频的噪音干扰和基线漂移，得到心搏数据，并对心搏数据进行干扰识别，并将心搏数据根据干扰识别结果和时间规则，依据心搏数据的导联参数进行合并，生成心搏分析数据。然后将心搏分析数据根据心搏分类信息和心电图基本规律参考数据生成心电图事件数据。
心电图事件数据具有相对应的事件类型，比如室上性早搏、房性逸搏、室性早搏、室性逸搏等等。我们可以设定事件类型信息来表征这些事件类型。因此心电图事件数据具有一个或多个事件类型信息。
步骤120，根据信号质量评价参数对心电图事件数据进行筛选，得到报告结论数据和报告表项数据；
具体的，报告结论数据和报告表项数据中包括对心率参数计算得到的数据等等，比如包括计算平均心率、及最大、最小心率等。在计算最大和最小心率时，以固定长度片段为统计单位，逐个心搏进行全程扫描和统计比较。片段的长度一般为8-10秒，也可以根据需要自由设定。计算心率时，针对窦性心律占主体和异位心律占主体采用不同的心搏类型统计计算方法。在计算最大最小心率时：针对窦性心律占主体的心电图，仅计算窦性分类心搏；针对房扑房颤类占主体的异位心律心电图，仅计算房扑房颤类心搏；针对非房扑房颤的其他异位心搏占主体的异位心律心电图，除伪差外所有类型心搏均参与计算。
步骤130，根据信号质量评价参数对心电图事件数据包含的事件片段 进行质量评估，质量评估结果确定预选样本片段；
具体的，对心电图事件数据，根据信号质量评价参数进行质量评估，选取数据信号质量最高的事件片段。
其中，信号质量评价参数基于心搏数据分析，由RR间期内相对于QRS波群的噪声水平来表征。具体可以通过根据QRS波群的功率和噪声信号的平均功率计算得到。
步骤140，确定预选样本片段中事件心搏的位置信息，并确定片段截取参数；
其中，片段截取参数具体是确认典型数据片段所需的起始位置信息和截取宽度信息。这与事件心搏的起始位置也是相关的。
起始位置信息和截取宽度信息可以根据心电图事件类型来确定。
当事件类型信息为一般事件类型信息时，可以先确定预选样本片段中的第一个心搏的心率数据，然后根据第一个心搏的心率数据来确定相应的起始位置信息。比如当心率数据大于预设阈值上限时，根据事件心搏的位置信息前移第一预设位移参数，得到起始位置信息；当心律数据小于预设阈值下限时，根据事件心搏的位置信息前移第二预设位移参数，得到起始位置信息。
而当事件类型信息为特定事件类型信息时，则要先根据质量评价参数计算预选样本片段中各数据片段的无干扰信号占比，并根据无干扰信号占比确定事件心搏的位置信息，并根据特定事件类型信息对应的片段截取规则确定截取宽度信息和起始位置信息。
在这里可以理解的，所说的样本片段，可以是仅对应一个心搏周期，也可以是对应多个心搏周期的。
下面以具体例子说明。
对于非特殊规则的心电图事件和特殊规则的心电图事件，可以分为两种情况处理。
第一种，针对非特殊规则心电图事件，只选取单个片段。因为事件心搏在预选样本片段中的位置是可知的，因此，根据起始位置信息和事件心搏的位置信息就可以得到中选样本片段截取的终止位置信息。
比如当片段第一个心搏心率大于等于100时，片段起始点位置距离第一个心搏距离为0.3秒。当片段第一个心搏心率小于等于45时，片段起始点位置距离第一个心搏距离为0.37秒。
第二种，针对特殊规则心电图事件，可以规定截取两个或多个片段。
本发明中所说的特殊规则心电图事件，可以具体包括3种事件：室速事件，室上速事件，时间长度大于预设时间阈值的长RR间期事件；预设时间阈值优选为8秒。对于此3种事件，可以截取两个或多个片段。第一个片段向前延3个心搏，第二个片段向后延2个心搏，每个片段的起始位置可以按上述非特殊规则的方式进行处理。
此外，在处理特殊规则心电图事件时，除了可以根据无干扰信号的占比确定占比最高的中选样本片段为典型数据片段之外，还可以设定阈值，对于达到设定阈值的样本片段，再进行筛选，选择包含其他事件种类数量最少的作为典型数据片段，具体方法包括：确定无干扰信号的占比是否达到占比阈值(优选的在60％-95％范围中确定阈值)；然后，对达到或高于占比阈值的数据片段进行事件类型单一性筛选，将筛选得到的除目标事件类型信息外的其余事件类型信息中，对应心搏计数最少的数据片段确定为典型数据片段。
这里单一性筛选的目的是得到尽可能单一的反映片段对应的事件的样本片段，即尽量不要存在其他事件。
如果通过上述步骤获得的对应心搏计数最少的样本片段依然为多个时，确定多个中选样本片段中无干扰信号占比最高的中选样本片段为报告样本片断。如片段数量仍不唯一，则选取其中的第一个作为最终优选。
步骤150，根据片段截取参数对预选样本片段进行截取处理得到典型 数据片段；
具体的，根据前步骤确定的起始位置信息、截取宽度信息和事件心搏的位置信息对预选样本片段进行截取，使得事件心搏的位置处于截取得到的中选样本片段的中部，即得到典型数据片段。
步骤160，根据典型数据片段生成报告图形数据。
步骤170，输出报告表项数据、报告图形数据和报告结论数据。
其中，可按照预设数据输出格式对报告表项数据、报告图形数据和报告结论数据进行输出。
本发明实施例提供的检测报告数据生成方法，对每种心律事件，通过计算噪音干扰数据进行质量评估，选取数据质量最高的事件片段，同时分析片段中的包含的事件种类数量，优先选取最具代表性的片段，即仅含有单一心律事件的片段，通过合理定位片段的开始位置，尽量保证事件心搏位于所选取片段的中部，并对于特定心电图事件的片段优选设置有特殊规则。最终结合选取得到的典型数据片段、事件类型信息等，生成检测报告数据。
专业人员应该还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
结合本文中所公开的实施例描述的方法或算法的步骤可以用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。
以上所述的具体实施方式，对本发明的目的、技术方案和有益效果进行了进一步详细说明，所应理解的是，以上所述仅为本发明的具体实施方式而已，并不用于限定本发明的保护范围，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (6)

  1. 一种检测报告数据生成方法，其特征在于，所述方法包括：
    获取心电图事件数据对应的心电图事件的事件类型信息；所述心电图事件数据具有一个或多个事件类型信息；
    根据信号质量评价参数对所述心电图事件数据进行筛选，得到报告结论数据和报告表项数据；
    根据所述信号质量评价参数对所述心电图事件数据包含的事件片段进行质量评估，根据所述质量评估结果确定预选样本片段；
    确定所述预选样本片段中事件心搏的位置信息，并确定片段截取参数；所述片段截取参数包括起始位置信息和截取宽度信息；
    根据所述片段截取参数对所述预选样本片段进行截取处理得到典型数据片段；
    根据所述典型数据片段生成报告图形数据；
    输出所述报告表项数据、报告图形数据和报告结论数据。
  2. 根据权利要求1所述的检测报告数据生成方法，其特征在于，所述根据所述片段截取参数对所述预选样本片段进行截取处理得到典型数据片段具体为：
    根据所述起始位置信息、截取宽度信息和所述事件心搏的位置信息对所述预选样本片段进行截取，使得所述事件心搏的位置处于所述截取得到的典型数据片段的中部。
  3. 根据权利要求2所述的检测报告数据生成方法，其特征在于，所述确定片段截取参数具体包括：
    确定所述预选样本片段中的第一个心搏的心率数据；
    当所述心率数据大于预设阈值上限时，根据事件心搏的位置信息前移第一预设位移参数，得到所述起始位置信息；
    当所述心律数据小于预设阈值下限时，根据事件心搏的位置信息前移 第二预设位移参数，得到所述起始位置信息。
  4. 根据权利要求2所述的检测报告数据生成方法，其特征在于，所述确定所述预选样本片段中事件心搏的位置信息，并确定片段截取参数具体包括：
    当所述事件类型信息为特定事件类型信息时，根据所述质量评价参数计算所述预选样本片段中各数据片段的无干扰信号占比，并根据所述无干扰信号占比确定所述事件心搏的位置信息，并根据所述特定事件类型信息对应的片段截取规则确定所述截取宽度信息和起始位置信息。
  5. 根据权利要求4所述的检测报告的生成方法，其特征在于，所述根据所述片段截取参数对所述预选样本片段进行截取处理得到典型数据片段具体为：
    所述起始位置信息和所述截取宽度信息对所述预选样本片段中各数据片段的无干扰信号占比为最高的数据片段进行截取，确定所述典型数据片段。
  6. 根据权利要求4所述的检测报告的生成方法，其特征在于，所述根据所述片段截取参数对所述预选样本片段进行截取处理得到典型数据片段具体为：
    确定所述无干扰信号的占比是否达到占比阈值；
    对达到或高于所述占比阈值的多个数据片段进行事件类型单一性筛选；
    将筛选得到的除目标事件类型信息外的其余事件类型信息中，对应心搏计数最少的数据片段确定为所述典型数据片段。
PCT/CN2018/072358 2017-11-27 2018-01-12 检测报告数据生成方法 WO2019100564A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP18881963.5A EP3693973A4 (en) 2017-11-27 2018-01-12 DETECTION REPORT DATA GENERATION PROCESS
US16/755,113 US11452476B2 (en) 2017-11-27 2018-01-12 Detection report data generation method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711202991.1 2017-11-27
CN201711202991.1A CN107945844B (zh) 2017-11-27 2017-11-27 检测报告数据生成方法

Publications (1)

Publication Number Publication Date
WO2019100564A1 true WO2019100564A1 (zh) 2019-05-31

Family

ID=61949062

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/072358 WO2019100564A1 (zh) 2017-11-27 2018-01-12 检测报告数据生成方法

Country Status (4)

Country Link
US (1) US11452476B2 (zh)
EP (1) EP3693973A4 (zh)
CN (1) CN107945844B (zh)
WO (1) WO2019100564A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108875575B (zh) * 2018-05-12 2021-05-11 鲁东大学 基于多通道信号融合深度神经网络自动心律失常分析方法
CN109745037B (zh) * 2019-02-14 2022-06-24 广州视源电子科技股份有限公司 一种图像处理方法、装置、设备和存储介质
CN113223650A (zh) * 2020-01-20 2021-08-06 深圳市理邦精密仪器股份有限公司 心电图报告的显示方法、心电图机及存储装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1393204A (zh) * 2001-06-26 2003-01-29 陈士良 心电频谱图测量仪
CN102138789A (zh) * 2011-01-24 2011-08-03 无锡微感科技有限公司 一种动态心电和运动记录与分析系统
CN102697492A (zh) * 2012-05-25 2012-10-03 长春华讯信息科技有限公司 一种实时心电信息分析系统及其分析方法
US20160188823A1 (en) * 2014-12-31 2016-06-30 General Electric Company System for providing electrocardiogram (ecg) analytics for electronic medical records (emr)

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6217525B1 (en) * 1998-04-30 2001-04-17 Medtronic Physio-Control Manufacturing Corp. Reduced lead set device and method for detecting acute cardiac ischemic conditions
US9492096B2 (en) * 2009-11-03 2016-11-15 Vivaquant Llc ECG sensing apparatuses, systems and methods
US8620418B1 (en) * 2013-01-04 2013-12-31 Infobionic, Inc. Systems and methods for processing and displaying patient electrocardiograph data
WO2014203114A2 (en) 2013-06-18 2014-12-24 Koninklijke Philips N.V. Ecg features for type ahead editing and automatic update for report interpretation
US10251576B2 (en) * 2013-09-25 2019-04-09 Bardy Diagnostics, Inc. System and method for ECG data classification for use in facilitating diagnosis of cardiac rhythm disorders with the aid of a digital computer
CN105232028A (zh) * 2015-09-29 2016-01-13 滕大志 一种用于监测心血管检测数据的方法和装置
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
WO2017182622A1 (en) 2016-04-21 2017-10-26 Koninklijke Philips N.V. Adaptive visualization of electrocardiogram
US10918295B2 (en) * 2016-05-19 2021-02-16 Btl Medical Technologies S.R.O. System and method for ECG signal processing
CN106264499B (zh) * 2016-08-26 2023-04-25 中山大学 一种量化心肺系统交互作用的分析方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1393204A (zh) * 2001-06-26 2003-01-29 陈士良 心电频谱图测量仪
CN102138789A (zh) * 2011-01-24 2011-08-03 无锡微感科技有限公司 一种动态心电和运动记录与分析系统
CN102697492A (zh) * 2012-05-25 2012-10-03 长春华讯信息科技有限公司 一种实时心电信息分析系统及其分析方法
US20160188823A1 (en) * 2014-12-31 2016-06-30 General Electric Company System for providing electrocardiogram (ecg) analytics for electronic medical records (emr)

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3693973A4 *

Also Published As

Publication number Publication date
EP3693973A4 (en) 2021-06-30
CN107945844A (zh) 2018-04-20
US20200253494A1 (en) 2020-08-13
US11452476B2 (en) 2022-09-27
CN107945844B (zh) 2021-07-16
EP3693973A1 (en) 2020-08-12

Similar Documents

Publication Publication Date Title
US20200138316A1 (en) Electrocardiogram signal detection
EP2704628B1 (en) Signal averaging
WO2019100563A1 (zh) 心电信号质量评估方法
US10973465B2 (en) Pacing signal processing method, system and electrocardiogram monitor
US20120071730A1 (en) Adaptive Processing of Ambulatory Electrocardiogram Signals
WO2016036805A1 (en) Electrocardiogram data analysis method and system for rapid diagnosis
US9050014B2 (en) System for cardiac arrhythmia detection and characterization
KR101366101B1 (ko) 개인별 ｅｃｇ 신호의 정상 신호 분류 시스템 및 방법
WO2019100564A1 (zh) 检测报告数据生成方法
CN113786200B (zh) 心电信号处理方法、装置、设备及可读介质
US11510605B2 (en) Instantaneous heartbeat reliability evaluation device, method, and program
Li et al. Probability density distribution of delta RR intervals: a novel method for the detection of atrial fibrillation
CN108937920B (zh) 一种心室纤颤信号检测方法、系统及心室纤颤检测装置
KR102342106B1 (ko) 인체상태 판단을 위한 비접촉식 생체신호 분석 시스템
US8457724B2 (en) System for heart performance characterization and abnormality detection
D'addio et al. Reproducibility of short-and long-term Poincare plot parameters compared with frequency-domain HRV indexes in congestive heart failure
TW201519862A (zh) 一種基於經驗模態分解法之心跳訊號檢測方法與檢測裝置
US10779769B2 (en) Method and system for evaluating a noise level of a biosignal
JPH0767843A (ja) 心電図信号のスペクトル分析方法および装置
CN114246569A (zh) 检测早搏类型的方法、装置及介质
KR101468057B1 (ko) 심전도 계측장치 및 심전도 모니터링 시스템
Dliou et al. Noised abnormal ECG signal analysis by combining EMD and Choi-Williams techniques
TWM530126U (zh) 基於擬合曲線之心跳訊號的檢測裝置
Stapelberg et al. A preprocessing tool for removing artifact from cardiac RR interval recordings using three‐dimensional spatial distribution mapping
TW201909840A (zh) 用於推測心房顫動之心跳訊號分析系統、方法及儲存該方法之機器可讀媒體

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: 18881963

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018881963

Country of ref document: EP

Effective date: 20200504

NENP Non-entry into the national phase

Ref country code: DE