Fetal electrocardiosignal dynamic analysis and fetal state prediction method based on topographic map analysis

Abstract

The invention discloses a fetal electrocardiosignal dynamic analysis and fetal state prediction method based on topographic map analysis, which comprises the following steps: collecting clinical pregnant woman abdominal electric signals, obtaining fetal electrocardiosignals through preprocessing and signal separation technologies, and constructing a reference data set of signal dynamic analysis; the method comprises the following steps: designing a topographic map analysis algorithm suitable for fetal electrocardiosignals, constructing a signal state template, generating a time sequence change diagram of fetal electrocardiosignal states, and taking a state statistical parameter sequence with labels as a reference data set for fetal state prediction; constructing a decision tree model, and training a training data set of the state statistical parameter sequence to obtain a trained model; and inputting the test set of the state statistics parameter sequence into the decision tree model to predict the fetal state. According to the method, the limitation of the existing non-invasive fetal electrocardiograph monitoring in the aspects of interpretability, visualization and fetal state prediction is solved, and the readability, the interpretability and the fetal state prediction performance of a visualization result are remarkably optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of fetal heart monitoring, and relates to a method for analyzing the dynamics of a fetal electrocardiogram signal state and predicting a fetal adverse state, and specifically is a method for analyzing the dynamics of an electrocardiogram signal and predicting a state based on topographic map analysis. Background Art

[0002] Fetal heart rate monitoring technology is used to collect fetal heart rate changes and reflect the fetal heart state. It can be used to identify whether the fetus is in an adverse state such as hypoxia or asphyxia. At the same time, the fetal heart rate characteristics displayed by monitoring can assist in the early diagnosis of diseases such as fetal acidemia and hypoxic-ischemic encephalopathy. Therefore, the dynamic display of fetal ECG monitoring data can more intuitively reflect the fetal state, and the prediction of adverse conditions can assist in early medical intervention, reduce neonatal morbidity and mortality, and improve delivery outcomes.

[0003] In actual clinical applications, there are many limitations in fetal heart monitoring. First, the commonly used fetal heart monitoring method is cardiotocography (CTG), but it has the disadvantages of poor interpretation, lack of details of fetal heart rate variability, and unsuitability for long-term monitoring. Other monitoring methods are not widely used due to the high difficulty of operation, high price, and damage.

[0004] In order to overcome the limitations of the above methods and obtain a safer monitoring method, a fetal monitoring technology that has attracted much attention recently is non-invasive fetal electrocardiography (NI-FECG). This method collects mixed maternal and fetal ECG signals through electrodes placed on the abdomen of pregnant women, and then separates the electrical signals of fetal heart activity through signal processing and feature recognition methods. NI-FECG has the outstanding advantages of being non-destructive, non-invasive and non-ionizing radiation, but it has technical difficulties such as low signal-to-noise ratio and susceptibility to noise and interference from maternal ECG signals. In order to solve the limitations of NI-FECG, current research focuses on extending adult ECG signal processing methods to fetal ECG signal extraction and feature recognition, and has overcome some of the difficulties. However, most of the existing research methods are to optimize the signal processing results, and no reasonable optimization schemes have been proposed for the readability and visualization of the signal and the relationship between the signal and the delivery outcome. Summary of the invention

[0005] The purpose of the present invention is to propose a method for dynamic analysis of fetal ECG signals and prediction of fetal status based on topographic map analysis, so as to solve the limitations of existing non-invasive fetal ECG monitoring in terms of result interpretation, visualization and fetal status prediction indicators, improve the display mode of fetal ECG signals, and improve the accuracy and reliability of prediction of adverse fetal conditions.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0007] 1. A method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographical analysis, such as Figure 1 As shown, the following steps are included:

[0008] S1, place the electrodes of the NI-FECG device on the abdomen of pregnant women to collect real abdominal mixed electrical signals and collect the delivery outcomes of pregnant women. The collected abdominal electrical signals are preprocessed and separated to obtain fetal ECG signals, and the abdominal electrical signal data are labeled according to the delivery outcome classification. The abdominal fetal ECG signals containing the labeled information are constructed as a benchmark data set for dynamic analysis of fetal ECG signals.

[0009] S2, design a topographical analysis algorithm suitable for dynamic analysis of fetal ECG signals, construct a state template of fetal ECG signals, generate a time series change diagram of fetal ECG signal states, and calculate state statistical parameters. The state statistical parameter sequence corresponds to the annotated data collected by S1, and the sequence is annotated in the same way to construct a benchmark data set for fetal state prediction.

[0010] S3, constructing a decision tree model, training the training data of the statistical parameters of the topographic map state with the fetal state annotation collected in S2, and obtaining the trained model parameters.

[0011] S4, extracting the test data of the statistical parameter sequence of the topographic map state with the fetal state annotation collected by S2 and inputting it into the decision tree model, and using the parameters obtained by S3 to predict the fetal state.

[0012] 2. According to the method of fetal electrocardiogram dynamics analysis and fetal status prediction based on topographic map analysis in claim 1, it is characterized in that, in S1, the same NI-FECG device and electrode sheet are used to collect abdominal electrical signals of pregnant women of different gestational weeks, and the signal data covers a variety of abdominal electrical signal samples of pregnant women of different gestational weeks and different physical conditions.

[0013] 3. According to the method of fetal electrocardiogram signal dynamic analysis and fetal status prediction based on topographic map analysis in claim 1, it is characterized in that, in S1, after the various types of abdominal electrical signals collected are preprocessed and separated to obtain fetal electrocardiogram signals, the data are classified and labeled as adverse delivery outcomes and good delivery outcomes based on the degree of neonatal hypoxia and acidosis recorded in the actual delivery outcomes when performing data labeling.

[0014] 4. According to the method of fetal electrocardiogram signal dynamic analysis and fetal state prediction based on topographic map analysis as described in claim 1, it is characterized in that in S2, the topographic map analysis is realized based on the characteristics of the multi-lead abdominal electrodes themselves and the time variation characteristics of the fetal electrocardiogram signals, and is an extended application of the microstate analysis of the electroencephalogram signals on the abdominal fetal electrical signals with the same characteristics.

[0015] 5. A method for fetal ECG signal dynamics analysis and fetal state prediction based on topographic map analysis according to claim 4, characterized in that the topographic map analysis includes state segmentation, fetal ECG data state fitting and state statistical parameter calculation;

[0016] Among them, state segmentation is used to analyze the energy distribution of fetal ECG signals and generate template topography; fetal ECG data state fitting is used to match the template topography with the ECG signal; state statistical parameter calculation can obtain the statistical characteristics of the matching between each template topography and the signal, which can potentially characterize a specific state mechanism.

[0017] 6. The method for fetal electrocardiogram signal dynamics analysis and fetal state prediction based on topographic map analysis according to claim 5 is characterized in that the state segmentation part analyzes the fetal electrocardiogram signal energy distribution and generates a template topographic map, which comprises:

[0018] The instantaneous distribution potential topography of the fetal electrocardiogram signal is calculated to obtain the local maximum topography curve, and the clustering technology is used to determine the optimal number of clusters to obtain the template topography.

[0019] 7. The method for dynamic analysis of fetal ECG signals and prediction of fetal status based on topographical map analysis according to claim 5, characterized in that the process of matching the template topographical map with the ECG signal by fetal ECG data state fitting comprises:

[0020] The topological structure of the fetal ECG signal at each time point is calculated in the time domain, and the similarity is calculated with the template topographic map. The template topographic map with high similarity matches the signal at that time point.

[0021] 8. A method for fetal electrocardiogram signal dynamics analysis and fetal state prediction based on topographic map analysis according to claim 5, characterized in that the state statistical parameter calculation obtains the statistical characteristics of each template topographic map matching with the signal, and the process for potentially characterizing a specific state mechanism includes:

[0022] The statistical distribution characteristics of each template topography in the signal were calculated, including duration, incidence, coverage and transfer rate, and these statistical parameters were used to predict the fetal status in S3 and S4.

[0023] 9. According to the method of fetal electrocardiogram signal dynamics analysis and fetal state prediction based on topographic map analysis in claim 1, it is characterized in that, in S3, a binary classification decision tree model is constructed, and the annotated state statistical parameter sequence collected by S2 is divided into a training set and a test set, and the training set is used for model training in S3.

[0024] 10. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 1, characterized in that in S4, the process of testing the performance of the model comprises:

[0025] The test data set divided by S3 was input into the model trained by S3 to predict the fetal status, and the prediction accuracy, sensitivity, precision, specificity, and F1 score of the performance indicators were calculated, and the ROC curve was drawn.

[0026] The beneficial effects of the present invention are as follows:

[0027] In the method for dynamic analysis of fetal ECG signals and prediction of fetal status based on topographical analysis of the present invention, mixed electrical signals of the abdomen of various pregnant women are first collected, and fetal ECG signals are obtained through preprocessing and signal separation, and fetal ECG data containing specific classifications are labeled according to the delivery outcome as a benchmark data set for dynamic analysis of fetal ECG signals; a topographical analysis algorithm suitable for fetal ECG signals is designed, a state template of fetal ECG signals is constructed, a time series change diagram of fetal ECG signal states is generated, and a state statistical parameter sequence with annotations is obtained, which is used as a benchmark data set for fetal state prediction; a decision tree model is constructed, and a training data set of the collected state statistical parameter sequence is trained to obtain a trained model; the test set of the collected state statistical parameter sequence is input into the decision tree model to predict the fetal state. The present invention uses topographical analysis and decision tree models suitable for fetal ECG signals to deal with the limitations of non-invasive fetal ECG monitoring in terms of result interpretation, visualization and fetal state prediction indicators. Compared with the existing methods, the visualization of monitoring results has been significantly improved, which is clearer and easier to understand, and the interpretability has been increased, and the fetal state prediction performance has been significantly optimized. The present invention establishes a new benchmark data set based on a specific fetal status category and fetal ECG data set, providing a data set from other angles for predicting fetal status, including a statistical description of the dynamic characteristics of fetal ECG signals, linking the changes in fetal ECG signals with fetal status, and providing a new angle for predicting fetal status. Therefore, the present invention can solve the limitations of existing non-invasive fetal ECG monitoring in terms of result interpretation, visualization, and fetal status prediction indicators, and improve the readability of fetal ECG monitoring results, the comprehensiveness of fetal status prediction indicators, and the accuracy of prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the implementation of the present invention or the existing technical solutions, the following is a brief introduction to the drawings required for describing the prior art.

[0029] Figure 1 A method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis is shown in FIG.

[0030] Figure 2 This is a diagram of a method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis in an example of the invention. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0032] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0033] like Figure 2 As shown, the embodiment of the present invention discloses a method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis, comprising the following specific steps:

[0034] S101: Place the 4-conductor electrode of the NI-FECG device on the abdomen of pregnant women to collect mixed abdominal electrical signals and collect the delivery outcomes of pregnant women. A total of 100 cases of abdominal electrical data were collected. The collected abdominal electrical signals were preprocessed and separated to obtain fetal ECG signals. The abdominal electrical signal data were labeled according to the delivery outcome classification, and the abdominal fetal ECG signals containing the labeled information were constructed as a benchmark data set for dynamic analysis of fetal ECG signals.

[0035] S102: Design a topographical analysis algorithm suitable for dynamic analysis of fetal ECG signals, construct a state template of fetal ECG signals, generate a time series change diagram of fetal ECG signal states, and calculate state statistical parameters. The state statistical parameter sequence corresponds to the annotated data collected in S101, and the sequence is annotated in the same way to construct a benchmark data set for fetal state prediction.

[0036] S103: Construct a decision tree model, train the training data of the statistical parameters of the topographic map state with the fetal state annotation collected in S102, and obtain the trained model parameters.

[0037] S104: Extract the test data of the statistical parameter sequence of the topographic map state with the fetal state annotation collected in S102 and input it into the decision tree model, and use the parameters obtained in S103 to predict the fetal state.

[0038] As a preferred embodiment of the present invention, in step S101, the process of data collection is as follows:

[0039] aaa: The same NI-FECG device and electrode sheet were used to collect 4-lead abdominal electrical signals from pregnant women of different gestational weeks. The signal data covered a variety of abdominal electrical signal samples from pregnant women of different gestational weeks and different physical conditions over 35 weeks.

[0040] bbb: Collect data related to delivery outcomes, including umbilical artery blood gas pH, whole blood base excess, lactate, oxygen partial pressure, carbon dioxide partial pressure, and Apgar score;

[0041] ccc: pre-process and separate various collected abdominal electrical signals to obtain fetal ECG signals;

[0042] ddd: When labeling data, the fetal ECG data were classified and labeled as 0 for poor delivery outcomes and 1 for good delivery outcomes based on the degree of neonatal hypoxia and acidosis recorded in the actual delivery outcomes.

[0043] In step S102, the topographic analysis is realized based on the characteristics of the multi-lead abdominal electrodes and the time-varying characteristics of the fetal ECG signal, which is an extended application of the microstate analysis of the EEG signal on the abdominal fetal electrical signal with the same characteristics. The topographic analysis includes state segmentation, fetal ECG data state fitting, and state statistical parameter calculation, wherein the state segmentation is used to analyze the energy distribution of the fetal ECG signal and generate a template topographic map; the fetal ECG data state fitting is used to match the template topographic map with the ECG signal; the state statistical parameter calculation can obtain the statistical characteristics of the matching of each template topographic map with the signal, which can potentially characterize a specific state mechanism.

[0044] Furthermore, the state segmentation part of step S102 includes the following specific steps:

[0045] aaa: Calculate the instantaneous distribution potential topography of the fetal ECG signal;

[0046] bbb: get the local maximum relief curve;

[0047] ccc: K-means clustering technique is applied to determine the optimal number of clusters as 10, and the template topographic map is obtained.

[0048] Furthermore, the fetal ECG data state fitting part of step S102 includes the following specific steps:

[0049] aaa: Calculate the topological structure of the fetal ECG signal at each time point in the time domain;

[0050] bbb: calculate the dissimilarity of the global topographic map with the template topographic map;

[0051] ccc: A dissimilarity of 0 means that the template topographic map completely matches the topographic map distribution at that moment, and a dissimilarity of 2 means that the template topographic map and the topographic map distribution at that moment have opposite polarities but the same structure. A topographic map time series change graph is constructed based on the matching results.

[0052] Furthermore, the state statistical parameters of step S102 calculate the statistical distribution characteristics of each template topography in the signal, including duration, incidence, coverage and transfer rate, and construct a state statistical parameter sequence for predicting the fetal state.

[0053] In the step S103, a binary classification decision tree model is constructed, and the annotated state statistical parameter sequence collected in S102 is divided into a training set and a test set according to an 8:2 ratio, and the training set is used for model training in S103.

[0054] In step S104, the process of testing the model performance includes:

[0055] aaa: Input the test data set divided by S103 into the model trained by S103 to predict the fetal status;

[0056] bbb: calculate the prediction accuracy, sensitivity, precision, specificity, and F1 score of the performance indicators;

[0057] ccc: draw ROC curve.

[0058] The above description of the disclosed examples enables professionals and technicians in the field to use this invention. It is obvious to professionals and technicians in the field that multiple modifications to these embodiments are obvious, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features disclosed herein. Those skilled in the art can also make various equivalent deformations or substitutions without violating the spirit of the present invention, and these equivalent deformations or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis, comprising the following steps: S1, place the electrodes of the NI-FECG device on the abdomen of the pregnant woman to collect real abdominal mixed electrical signals, and collect the delivery outcomes of the pregnant woman; obtain the fetal ECG signals through preprocessing and signal separation of the collected abdominal electrical signals, annotate the abdominal electrical signal data according to the delivery outcome classification, and construct the abdominal fetal ECG signals containing the annotated information as a benchmark data set for dynamic analysis of fetal ECG signals; S2, designing a topographical analysis algorithm suitable for dynamic analysis of fetal ECG signals, constructing a state template of fetal ECG signals, generating a time series change diagram of fetal ECG signal states, and calculating state statistical parameters; the state statistical parameter sequence corresponds to the annotated data collected by S1, and the sequence is annotated in the same way to construct a benchmark data set for fetal state prediction; S3, constructing a decision tree model, training the training data of the statistical parameters of the topographic map state with the fetal state annotation collected by S2, and obtaining the trained model parameters; S4, extracting the test data of the statistical parameter sequence of the topographic map state with the fetal state annotation collected by S2 and inputting it into the decision tree model, and using the parameters obtained by S3 to predict the fetal state.

2. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 1, characterized in that: In S1, the same NI-FECG device and electrodes were used to collect abdominal electrical signals from pregnant women at different gestational weeks. The signal data covered a variety of abdominal electrical signal samples from pregnant women at different gestational weeks and in different physical conditions.

3. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 1, characterized in that: In S1, after the various types of abdominal electrical signals collected were preprocessed and separated to obtain the fetal ECG signals, the data were classified and labeled as adverse delivery outcomes and good delivery outcomes based on the degree of neonatal hypoxia and acidosis recorded in the actual delivery outcomes.

4. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 1, characterized in that: In S2, topographic analysis is achieved based on the characteristics of the multi-lead abdominal electrodes and the temporal variation characteristics of the fetal ECG signals. It is an extended application of the microstate analysis of EEG signals on abdominal fetal electrical signals with the same characteristics.

5. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 4, characterized in that: Topographic analysis includes state segmentation, fetal ECG data state fitting, and state statistical parameter calculation; Among them, state segmentation is used to analyze the energy distribution of fetal ECG signals and generate template topography; fetal ECG data state fitting is used to match the template topography with the ECG signal; state statistical parameter calculation can obtain the statistical characteristics of the matching between each template topography and the signal, which can potentially characterize a specific state mechanism.

6. The method for fetal electrocardiogram signal dynamics analysis and fetal status prediction based on topographic map analysis according to claim 5, characterized in that: The state segmentation part analyzes the energy distribution of the fetal ECG signal and generates a template topographic map, which includes: The instantaneous distribution potential topography of the fetal electrocardiogram signal is calculated to obtain the local maximum topography curve, and the clustering technology is used to determine the optimal number of clusters to obtain the template topography.

7. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 5, characterized in that: The process of matching the template topography with the ECG signal by fetal ECG data state fitting includes: The topological structure of the fetal ECG signal at each time point is calculated in the time domain, and the similarity is calculated with the template topographic map. The template topographic map with high similarity matches the signal at that time point.

8. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 5, characterized in that: The state statistical parameters are calculated to obtain the statistical characteristics of each template topography and signal matching, which are used to potentially characterize a specific state mechanism. The process includes: The statistical distribution characteristics of each template topography in the signal were calculated, including duration, incidence, coverage and transfer rate, and these statistical parameters were used to predict the fetal status in S3 and S4.

9. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographic map analysis according to claim 1, characterized in that: In S3, a binary classification decision tree model is constructed, and the annotated state statistical parameter sequence collected by S2 is divided into a training set and a test set. The training set is used for model training in S3.

10. The method for dynamic analysis of fetal electrocardiogram signals and prediction of fetal status based on topographical analysis according to claim 1, characterized in that: In S4, the process of testing model performance includes: The test data set divided by S3 was input into the model trained by S3 to predict the fetal status, and the prediction accuracy, sensitivity, precision, specificity, and F1 score of the performance indicators were calculated, and the ROC curve was drawn.

Images