Method and device for analyzing fetal heart rate variation in parturition process based on multi-channel EHG signals

Abstract

The invention discloses a method and a device for analyzing fetal heart rate variation in a birth process based on multi-channel EHG signals. The method comprises the following steps: S1, monitoring EHG signals of N channels in an abdominal area of a puerpera in real time; s2, presetting an empirical weight omega i for the abdomen area, covered by each channel, of the puerpera; s3, calculating the root-mean-square RMS power Pi of each channel within the range of a set frequency band by taking a set time period as a calculation window, performing normalization processing on a power sequence # imgabs0 # after weighting the root-mean-square RMS power Pi of N channels, and obtaining a power sequence # imgabs2 #; S4, performing low-pass filtering processing on most of the power sequences to obtain a power sequence # imgabs0 # and a power sequence # imgabs1 #; obtaining a global uterus activity data sequence of the abdominal surface; s5, extracting uterine contraction features of the uterine activity data sequence; and S6, inputting the uterine contraction features into a pre-trained fetal monitoring model to judge the state of the fetus. According to the method, the weight is set for each channel, and the uterine contraction characteristics of the uterine activity data sequence are extracted, so that the state of the fetus is accurately judged.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more specifically, to a method and device for analyzing fetal heart rate variability during labor based on multi-channel EHG signals. Background Art

[0002] During the clinical process of delivery, doctors monitor uterine activity (UC) and fetal heart rate (FHR) in real time to determine the status of the fetus in the uterus and make clinical decisions. Specifically, after determining the risk of delivery for the mother, doctors focus on the information of the fetal FHR, such as baseline, variation, acceleration, deceleration and other characteristics. Among them, the deceleration characteristics of FHR under the influence of uterine contraction (UC) are the key clinical features, such as early deceleration, variable deceleration, late deceleration, prolonged deceleration, etc. It can provide risk tips about potential fetal hypoxia, acidosis, etc. So as to make clinical decisions early and reduce the risk of delivery. The most significant reference points of these deceleration characteristics are based on the UC process.

[0003] Uterine activity (UC) monitoring is one of the important measurement indicators for labor monitoring. Traditional uterine monitoring methods such as intrauterine pressure catheter (IUPC) can adequately monitor the amplitude and frequency of uterine contractions; however, it requires rupture of fetal membranes and is associated with rare but serious complications. Currently, its noninvasive alternative TOCO is the most widely used. However, external TOCO measurements have low accuracy, are dependent on the location of the probe, and can only reflect the overall changes in uterine pressure.

[0004] Uterine electromyography (EHG) is an innovative technology that measures changes in uterine biopotential by placing electrodes on the surface of the mother's abdomen and provides real-time maps. Compared with TOCO, EHG has lower requirements for the location of contact electrodes, can provide more accurate information on uterine activity, and can provide more local measurement information through multi-channel electrodes. These measurements are related to the electrophysiological root causes of uterine contractions, so EHG can provide more detailed diagnostic information.

[0005] At present, obstetrics mainly implements clinical fetal monitoring through CTG, which is a technology based on TOCO. TOCO itself can only reflect the overall mechanical changes of the uterine abdominal surface, has low sensitivity, and is easily affected by the placement of the TOCO probe, resulting in erroneous monitoring and affecting clinical diagnosis. Therefore, it is necessary to improve the existing technology. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for analyzing fetal heart rate variability during labor based on multi-channel EHG signals, so as to overcome the problems existing in the prior art.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] A method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals, comprising the following steps:

[0009] S1, real-time monitoring of EHG signals of N channels in the abdomen area of ​​the parturient, where N is a positive integer;

[0010] S2. Preset an empirical weight ω for the parturient abdomen area covered by each channel i , where i ranges from 1 to N;

[0011] S3, taking the set time period as a calculation window, calculate the root mean square RMS power P of each channel within the set frequency band. i , and then calculate the root mean square RMS power P of N channels i Weighted power series Among them, P i T P i The transpose of the power sequence After normalization, we get the power series

[0012] S4, performing low-pass filtering on most power sequences to obtain a global uterine activity data sequence on the abdominal surface;

[0013] S5, extracting uterine contraction features of the uterine activity data sequence;

[0014] S6. Inputting the uterine contraction characteristics into a pre-trained fetal monitoring model to determine the status of the fetus.

[0015] Furthermore, in step S1, N electrodes are arranged in the abdomen area of ​​the parturient to monitor N channels of EHG signals in real time.

[0016] Furthermore, in step S3, the root mean square RMS power P i The calculation formula is:

[0017]

[0018] N is the length of the window, and x is the EHG signal sampling point.

[0019] Furthermore, the step S4 also includes downsampling the uterine activity data sequence to a set frequency.

[0020] Furthermore, the step S5 specifically includes:

[0021] Set the time window of the uterine contraction baseline feature as the set time window, move the lowest and highest values ​​in the power sequence in the detection window with a fixed step length, and obtain the difference PV between the highest and lowest values. Calculate the mean of the 10% points of the lowest value as the uterine contraction baseline UC BASE ;

[0022] The threshold parameter TH1 of uterine contraction detection is set to be UCBASE+PV / 4, the amplitude of effective uterine contraction is greater than 2*TH1, and the time when the amplitude is continuously greater than TH1 is in the third time period;

[0023] Set the maximum value of effective uterine contraction to the uterine contraction apex UC PEAK UC, the moment when the rising edge of effective uterine contraction exceeds TH1 START UC, the moment when the falling edge of effective contraction is less than TH1 END ;

[0024] The fetal electrocardiogram signal FECG is extracted by using the differential data of two electrodes set on the abdomen, and the R wave of the fetal electrocardiogram signal FECG is identified, and the RR interval is calculated to obtain the FHR sequence;

[0025] The fourth set time period is used as the sliding average calculation window, the sliding period is set as the fifth time period, and the baseline of the FHR sequence is extracted to obtain the fetal heart rate baseline FHR. BASE ;

[0026] Using the fetal heart rate baseline as a reference, calculate the FHR variation parameter V FHR =FHR-FHR BASE ;

[0027] The variation parameter V FHR＞ The data point of the first set value is recorded as the pending acceleration data sequence point FHR acc , V FHR <-The data point of the first set value is recorded as the pending deceleration data sequence point FHR dec , respectively for the FHR of the given acceleration data sequence points acc and pending deceleration data sequence point FHR dec The sequence positions are counted, and the start and end positions of the continuous sequence positions exceeding the set time are recorded to obtain the fetal heart rate acceleration feature segment and deceleration feature segment respectively.

[0028] Furthermore, the training steps of the fetal monitoring model are:

[0029] Select the characteristic points of multiple uterine activity data sequences, the uterine contraction apex UC PEAK , the moment when the rising edge of effective uterine contraction exceeds TH1 is recorded as UC START , the moment UC when the falling edge of effective contraction is less than TH1 END, fetal heart rate baseline FHR BASE , fetal heart rate acceleration feature segment and deceleration feature segment and corresponding fetal status data as a data set;

[0030] Dividing the data set into a training set and a validation set of a certain proportion;

[0031] The training set is input into a neural network for training to obtain a fetal monitoring model, which is then verified using a verification set.

[0032] The present invention also provides a device according to the above-mentioned method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals, comprising:

[0033] A monitoring module, used for real-time monitoring of EHG signals of N channels in the abdominal area of ​​the parturient, where N is a positive integer;

[0034] The preset module is used to preset an empirical weight ω for the parturient abdomen area covered by each channel i , where i ranges from 1 to N;

[0035] The calculation module is used to calculate the root mean square RMS power P of each channel within the set frequency band, taking the set time period as a calculation window. i , and then calculate the root mean square RMS power P of N channels i Weighted power series Among them, P i T P i The transpose of the power sequence After normalization, we get the power series

[0036] A low-pass filtering module is used to perform low-pass filtering on most power sequences to obtain a global uterine activity data sequence on the abdominal surface;

[0037] An extraction module, used for extracting uterine contraction features of the uterine activity data sequence;

[0038] A judgment module, used for inputting the uterine contraction characteristics into a pre-trained fetal monitoring model to judge the state of the fetus;

[0039] The monitoring module, the preset module, the calculation module, the low-pass filtering module, the extraction module and the judgment module are connected in sequence.

[0040] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals are implemented as described above.

[0041] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals are implemented as described above.

[0042] Compared with the prior art, the advantages of the present invention are: the present invention uses multi-channel EHG signals to analyze fetal heart rate variability during labor, sets weights for each channel, extracts uterine contraction features of the uterine activity data sequence, and accurately determines the state of the fetus. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0045] Figure 2 This is a flow chart of the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals of the present application.

[0046] Figure 3 This is the EHG electrode distribution diagram in the embodiment of the present application.

[0047] Figure 4 It is the fetal heart rate baseline diagram in the embodiment of the present application.

[0048] Figure 5 This is a framework diagram of the device for analyzing fetal heart rate variability during labor based on multi-channel EHG signals of the present application.

[0049] Figure 6 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0051] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0053] See also Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0054] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0055] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc.

[0056] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0057] It should be noted that the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals provided in the embodiment of the present application is generally executed by the server 105. Accordingly, the delivery auxiliary doula device based on the progress of labor is generally set in the terminal devices 101, 102, and 103.

[0058] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0059] See also Figure 2 As shown, the present invention provides a method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals, characterized in that it includes the following steps:

[0060] Step S1, real-time monitoring of EHG signals of N channels in the abdominal area of ​​a parturient, wherein N is a positive integer.

[0061] In this embodiment, 16 electrodes are arranged in the abdomen area of ​​the parturient to monitor 16 channels of EHG signals in real time, with a sampling rate of 40 Hz. Figure 3 As shown, the electrodes are numbered 1, 2, 3, ..., 15, 16.

[0062] Step S2: preset an empirical weight ω for the parturient abdomen area covered by each channel i , where i ranges from 1 to N.

[0063] In this embodiment, the corresponding empirical weight vector of each electrode is W=[ω1,ω2,ω3,...ω 15 ,ω 16 ]. Among them, the weights of electrodes 6, 7, 10, and 11 at the center of the navel are recorded as 1; the weights of electrodes 5, 8, 9, and 12 are recorded as 0.95; and the weights of the remaining channels are recorded as 0.9.

[0064] Step S3: Calculate the RMS power P of each channel within the frequency band [0.3 Hz, 1 Hz] with a calculation window of 3 s. i =[p1,p2,p3,......p 15 ,p 16 ], and then calculate the root mean square power P of the 16 channels i Weighted power series Among them, Pi T P i In order to eliminate the influence of different channel numbers, the power sequence After normalization, we get the power series

[0065] In this embodiment, the root mean square RMS power P i The calculation formula is:

[0066]

[0067] N is the length of the window, and x is the EHG signal sampling point.

[0068] Step S4: Perform 0.1 Hz low-pass filtering on most power sequences to obtain a global uterine activity data sequence on the abdominal surface.

[0069] In this embodiment, the uterine activity data sequence is downsampled to 4 Hz.

[0070] Step S5: extracting the uterine contraction features of the uterine activity data sequence, the specific implementation method is:

[0071] The time window of the uterine contraction baseline characteristics was set to 3 minutes, and the lowest and highest values ​​in the power sequence in the detection window were moved with a step length of 1 minute. The difference PV between the highest and lowest values ​​was obtained, and the mean of the 10% points of the lowest value was calculated as the uterine contraction baseline UC. BASE .

[0072] The threshold parameter TH1 for uterine contraction detection is set to be UCBASE+PV / 4, the amplitude of effective uterine contraction is greater than 2*TH1, and the amplitude continues to be greater than TH1 for 25-180 seconds.

[0073] Set the maximum value of effective uterine contraction to the uterine contraction apex UC PEAK UC, the moment when the rising edge of effective uterine contraction exceeds TH1 START UC, the moment when the falling edge of effective contraction is less than TH1 END .

[0074] Using the differential data of the two electrodes 13 and 4 on the abdomen, the fetal ECG signal FECG is extracted, and the R wave of the fetal ECG signal FECG is identified, and the RR interval is calculated to obtain the FHR sequence. The sampling rate of the sequence is f FHR Recorded as 4Hz.

[0075] Take 10 minutes as the sliding average calculation window, set the sliding period to 10s, extract the baseline of the FHR sequence, and the window data has a total of WN=10*60*f FHR= 2400, calculate the mean of all FHR values, update it every 10s, and thus obtain the fetal heart rate baseline during the monitoring process.

[0076] See also Figure 3 As shown, the 10-minute mean calculation window moves 10*f every 10 seconds. FHR , that is, 40 data points, and then calculate the mean to get a FHR baseline value, and so on, to get the fetal heart rate baseline FHR BASE Since the update time step is 10s, there is a 10-fold difference between it and the FHR sampling rate, so the fetal heart rate baseline FHR is obtained. BASE Further interpolation is required to make its sampling rate consistent with the FHR sampling rate.

[0077] Using the fetal heart rate baseline as a reference, calculate the FHR variation parameter V FHR =FHR-FHR BASE ;

[0078] The variation parameter V FHR＞ The data point of 15 is recorded as the pending acceleration data sequence point FHR acc , V FHR The data point <-15 is recorded as the pending deceleration data sequence point FHR dec , respectively for the FHR of the given acceleration data sequence points acc and pending deceleration data sequence point FHR dec The sequence positions are counted, and the start and end positions of the continuous sequence positions exceeding 15s (i.e., 15s*fFHR=60 points) are recorded to obtain the fetal heart rate acceleration feature segment and deceleration feature segment respectively.

[0079] Step S6: input the uterine contraction characteristics into a pre-trained fetal monitoring model to determine the status of the fetus.

[0080] In this embodiment, the training steps of the fetal monitoring model are: selecting characteristic points of multiple uterine activity data sequences, uterine contraction apex UC PEAK , the moment when the rising edge of effective uterine contraction exceeds TH1 is recorded as UC START , the moment UC when the falling edge of effective contraction is less than TH1 END , fetal heart rate baseline FHR BASE , fetal heart rate acceleration feature segments and deceleration feature segments and the corresponding fetal status data as a data set, which can be the usually accumulated data, combined with the obstetric fetal monitoring guide experience data; the data set is divided into a training set and a validation set in a certain proportion; the training set is input into a neural network for training to obtain a fetal monitoring model, and the validation set is used for verification.

[0081] The present invention uses multi-channel EHG signals to analyze fetal heart rate variability during labor, sets weights for each channel, and extracts uterine contraction features from a uterine activity data sequence to accurately determine the state of the fetus.

[0082] Further references Figure 5 , as a response to the above Figure 2 The present application provides an embodiment of a fetal heart rate variability analysis device during labor based on a multi-channel EHG signal. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0083] A fetal heart rate variability analysis device during labor based on multi-channel EHG signals, comprising:

[0084] Monitoring module 1 is used to monitor N channels of EHG signals in the abdomen area of ​​the parturient in real time, where N is a positive integer.

[0085] Presetting module 2, used to preset an empirical weight ω for the parturient abdomen area covered by each channel i , where i ranges from 1 to N.

[0086] The calculation module 3 is used to calculate the root mean square RMS power P of each channel within the set frequency band, taking the set time period as a calculation window. i , and then calculate the root mean square RMS power P of N channels i Weighted power series Among them, P i T P i The transpose of the power sequence After normalization, we get the power series

[0087] The low-pass filtering module 4 is used to perform low-pass filtering on the majority power sequences to obtain a global uterine activity data sequence on the abdominal surface.

[0088] The extraction module 5 is used to extract the uterine contraction features of the uterine activity data sequence.

[0089] The judgment module 6 is used to input the uterine contraction characteristics into a pre-trained fetal monitoring model to judge the state of the fetus.

[0090] The monitoring module 1, the preset module 2, the calculation module 3, the low-pass filtering module 4, the extraction module 5 and the judgment module 6 are connected in sequence.

[0091] The present invention uses multi-channel EHG signals to analyze fetal heart rate variability during labor, sets weights for each channel, and extracts uterine contraction features from a uterine activity data sequence to accurately determine the state of the fetus.

[0092] To solve the above technical problems, the present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of the computer device in this embodiment.

[0093] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 6 with components 61-63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0094] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0095] The memory 61 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 6. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as the program code of the fetal heart rate variability analysis method during labor based on multi-channel EHG signals, etc. In addition, the memory 61 can also be used to temporarily store various types of data that have been output or are to be output.

[0096] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run the program code stored in the memory 61 or process data, such as running the program code of the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals.

[0097] The network interface 63 may include a wireless network interface or a wired network interface. The network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0098] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores a program for analyzing fetal heart rate variability during labor based on multi-channel EHG signals, and the program for analyzing fetal heart rate variability during labor based on multi-channel EHG signals can be executed by at least one processor, so that the at least one processor performs the steps of the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals as described above.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0100] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, the patent owner may make various variations or modifications within the scope of the appended claims. As long as they do not exceed the protection scope described in the claims of the present invention, they should be within the protection scope of the present invention.

Claims

1. A method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals, characterized in that: The following steps are involved: S1, real-time monitoring of EHG signals of N channels in the abdomen area of ​​the parturient, where N is a positive integer; S2. Preset an empirical weight ω for the parturient abdomen area covered by each channel i , where i ranges from 1 to N; S3, taking the set time period as a calculation window, calculate the root mean square RMS power P of each channel within the set frequency band. i , and then calculate the root mean square RMS power P of N channels i Weighted power series Among them, P i T P i The transpose of the power sequence After normalization, we get the power series S4, performing low-pass filtering on most power sequences to obtain a global uterine activity data sequence on the abdominal surface; S5, extracting uterine contraction features of the uterine activity data sequence; S6. Inputting the uterine contraction characteristics into a pre-trained fetal monitoring model to determine the status of the fetus.

2. The method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals according to claim 1, characterized in that: In the step S1, N electrodes are arranged in the abdomen of the parturient to monitor N channels of EHG signals in real time.

3. The method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals according to claim 2, characterized in that: In step S3, the root mean square RMS power P i The calculation formula is: N is the length of the window, and x is the EHG signal sampling point.

4. The method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals according to claim 1, characterized in that: The step S4 also includes downsampling the uterine activity data sequence to a set frequency.

5. The method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals according to claim 1, characterized in that: The step S5 specifically includes: Set the time window of the uterine contraction baseline feature as the set time window, move the lowest and highest values ​​in the power sequence in the detection window with a fixed step length, and obtain the difference PV between the highest and lowest values. Calculate the mean of the 10% points of the lowest value as the uterine contraction baseline UC BASE ; The threshold parameter TH1 of uterine contraction detection is set to be UCBASE+PV / 4, the amplitude of effective uterine contraction is greater than 2*TH1, and the time when the amplitude is continuously greater than TH1 is in the third time period; Set the maximum value of effective uterine contraction to the uterine contraction apex UC PEAK UC, the moment when the rising edge of effective uterine contraction exceeds TH1 START UC, the moment when the falling edge of effective contraction is less than TH1 END ; The fetal electrocardiogram signal FECG is extracted by using the differential data of two electrodes set on the abdomen, and the R wave of the fetal electrocardiogram signal FECG is identified, and the RR interval is calculated to obtain the FHR sequence; The fourth set time period is used as the sliding average calculation window, the sliding period is set as the fifth time period, and the baseline of the FHR sequence is extracted to obtain the fetal heart rate baseline FHR. BASE ; Using the fetal heart rate baseline as a reference, calculate the FHR variation parameter V FHR =FHR-FHR BASE ; The variation parameter V FHR >The data point of the first set value is recorded as the pending acceleration data sequence point FHR acc , V FHR <-The data point of the first set value is recorded as the pending deceleration data sequence point FHR dec , respectively for the FHR of the given acceleration data sequence points acc and pending deceleration data sequence point FHR dec The sequence positions are counted, and the start and end positions of the continuous sequence positions exceeding the set time are recorded to obtain the fetal heart rate acceleration feature segment and deceleration feature segment respectively.

6. The method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals according to claim 1, characterized in that: The training steps of the fetal monitoring model are: Select the characteristic points of multiple uterine activity data sequences, the uterine contraction apex UC PEAK , the moment when the rising edge of effective uterine contraction exceeds TH1 is recorded as UC START , the moment UC when the falling edge of effective contraction is less than TH1 END , fetal heart rate baseline FHR BASE , fetal heart rate acceleration feature segment and deceleration feature segment and corresponding fetal status data as a data set; Dividing the data set into a training set and a validation set of a certain proportion; The training set is input into a neural network for training to obtain a fetal monitoring model, which is then verified using a verification set.

7. A device for analyzing fetal heart rate variability during labor based on multi-channel EHG signals according to any one of claims 1 to 6, characterized in that: include: A monitoring module, used for real-time monitoring of EHG signals of N channels in the abdominal area of ​​the parturient, where N is a positive integer; The preset module is used to preset an empirical weight ω for the parturient abdomen area covered by each channel i , where i ranges from 1 to N; The calculation module is used to calculate the root mean square RMS power P of each channel within the set frequency band, taking the set time period as a calculation window. i , and then calculate the root mean square RMS power P of N channels i Weighted power series Among them, P i T P i The transpose of the power sequence After normalization, we get the power series A low-pass filtering module is used to perform low-pass filtering on most power sequences to obtain a global uterine activity data sequence on the abdominal surface; An extraction module, used for extracting uterine contraction features of the uterine activity data sequence; A judgment module, used for inputting the uterine contraction characteristics into a pre-trained fetal monitoring model to judge the state of the fetus; The monitoring module, the preset module, the calculation module, the low-pass filtering module, the extraction module and the judgment module are connected in sequence.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals as described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for analyzing fetal heart rate variability during labor based on multi-channel EHG signals as described in any one of claims 1 to 6.

Images