Fetal heart analysis method, apparatus, device, and storage medium

Abstract

This invention discloses a fetal heart rate analysis method, apparatus, device, and storage medium. The method includes: acquiring fetal heart rate data and basic user information uploaded by a user; inputting the fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results. The preset fetal heart rate analysis model includes a position encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module; and distributing the fetal heart rate data, basic user information, and fetal heart rate analysis results to doctors at different levels based on the fetal heart rate analysis results. Because this invention inputs fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results, and the preset fetal heart rate analysis model includes a position encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module, this invention improves the accuracy of fetal heart rate analysis compared to existing technologies.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, device, and storage medium for fetal heart rate analysis. Background Technology

[0002] Fetal monitoring is a crucial means of ensuring fetal health. By monitoring indicators such as fetal heart rate and fetal movement, abnormalities can be detected promptly, allowing for appropriate measures to ensure the fetus's healthy growth. Currently, fetal monitoring is primarily conducted in hospitals, requiring specialized monitoring equipment and medical personnel. However, due to strained medical resources and a significant increase in high-risk pregnancies, especially those requiring daily fetal heart rate monitoring in late pregnancy, going to the hospital becomes extremely inconvenient.

[0003] Therefore, remote fetal heart rate monitoring has become an excellent solution. Remote fetal heart rate monitoring can improve the quality of life for pregnant women. Pregnant women can monitor fetal heart rate at home, eliminating the need for frequent hospital visits, thus reducing their burden and time costs. Simultaneously, remote fetal heart rate monitoring can enhance the pregnant woman's sense of security, allowing her to spend her pregnancy with greater peace of mind. Remote fetal heart rate monitoring can be achieved through smart devices; the pregnant woman only needs to wear a fetal heart rate monitor to monitor the fetus's heart rate and fetal movement in real time. Simultaneously, the monitoring data can be transmitted back to the cloud via the internet, and then distributed to doctors for remote analysis and feedback to the pregnant woman. The benefits of remote fetal heart rate monitoring not only lie in its convenience and speed, but also in its ability to effectively alleviate the problem of strained medical resources, balance medical resources across different regions and hospitals, and improve medical efficiency and quality. However, existing fetal heart rate analysis models have many shortcomings, including insufficient datasets and unsatisfactory model performance.

[0004] Therefore, there is an urgent need for a fetal heart rate analysis method that can improve the accuracy of fetal heart rate analysis and thus solve the technical problems of scarce hospital resources and low medical efficiency in the current fetal heart rate monitoring process. Summary of the Invention

[0005] The main objective of this invention is to provide a method, apparatus, device, and storage medium for fetal heart rate analysis, aiming to solve the technical problem of how to improve the accuracy of fetal heart rate analysis.

[0006] To achieve the above objectives, the present invention provides a fetal heart rate analysis method, the method comprising the following steps:

[0007] Obtain fetal heart rate data and basic user information uploaded by the user;

[0008] The fetal heart rate data and the user's basic information are input into a preset fetal heart rate analysis model to obtain the fetal heart rate analysis results. The preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module.

[0009] Based on the fetal heart rate analysis results, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis results are distributed to doctors at different levels.

[0010] Optionally, before the step of obtaining the fetal heart rate data and basic user information uploaded by the user, the method further includes:

[0011] Obtain the original fetal heart rate dataset and perform data preprocessing on the original fetal heart rate dataset to obtain the model training dataset;

[0012] A one-dimensional convolutional neural network model is constructed, and the one-dimensional convolutional neural network model is used as the initial fetal heart rate analysis model;

[0013] The initial fetal heart rate analysis model is improved to obtain a fetal heart rate analysis model to be trained;

[0014] The model training dataset is input into the fetal heart rate analysis model to be trained to obtain the preset fetal heart rate analysis model.

[0015] Optionally, the step of improving the initial fetal heart rate analysis model to obtain the fetal heart rate analysis model to be trained includes:

[0016] The initial fetal heart rate analysis model was improved into a deep residual model to obtain the first fetal heart rate analysis model.

[0017] A bidirectional gated cyclic unit is introduced into the first fetal heart rate analysis model to obtain a second fetal heart rate analysis model.

[0018] A multi-scale feature extraction module and a feature fusion module are introduced into the second fetal heart rate analysis model to obtain a third fetal heart rate analysis model.

[0019] A position encoding module is introduced into the third fetal heart rate analysis model to obtain a fourth fetal heart rate analysis model;

[0020] A channel attention mechanism is introduced into the fourth fetal heart rate analysis model to obtain the fetal heart rate analysis model to be trained.

[0021] Optionally, the step of obtaining the original fetal heart rate dataset and performing data preprocessing on the original fetal heart rate dataset to obtain the model training dataset includes:

[0022] Obtain the original fetal heart rate dataset and classify the original fetal heart rate dataset to obtain the classification results;

[0023] The original fetal heart rate dataset is labeled based on the classification results to obtain the labeled fetal heart rate dataset.

[0024] The labeled fetal heart data dataset was cleaned according to the fetal heart data screening criteria to obtain a cleaned fetal heart data dataset.

[0025] The cleaned fetal heart rate dataset is smoothed by moving average to obtain the model training dataset.

[0026] Optionally, the step of performing moving average smoothing on the cleaned fetal heart rate dataset to obtain the model training dataset includes:

[0027] The cleaned fetal heart rate dataset is smoothed by moving average according to a preset time window to obtain the processed fetal heart rate dataset.

[0028] The processed fetal heart rate dataset is subjected to data augmentation to obtain an augmented fetal heart rate dataset;

[0029] The enhanced fetal heart rate dataset is adjusted based on the number of each fetal heart rate data category in the enhanced fetal heart rate dataset to obtain the model training dataset.

[0030] Optionally, the step of distributing the fetal heart rate data, the user's basic information, and the fetal heart rate analysis results to doctors at different levels based on the fetal heart rate analysis results includes:

[0031] If the fetal heart rate analysis result is normal, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result will be sent to a doctor for fetal heart rate analysis review.

[0032] If the fetal heart rate analysis result is abnormal, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result will be distributed to two doctors at the level of associate chief physician or above for fetal heart rate analysis review.

[0033] Optionally, after the step of inputting the model training dataset into the fetal heart rate analysis model to be trained for model training and obtaining the preset fetal heart rate analysis model, the method further includes:

[0034] The preset fetal heart rate analysis model is evaluated using model evaluation metrics, which include: accuracy, precision, recall, and F1 score.

[0035] Furthermore, to achieve the above objectives, the present invention also proposes a fetal heart rate analysis device, the device comprising:

[0036] The data acquisition module is used to acquire fetal heart rate data and basic user information uploaded by the user.

[0037] The data analysis module is used to input the fetal heart data and the user's basic information into a preset fetal heart analysis model to obtain fetal heart analysis results. The preset fetal heart analysis model includes a position encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module.

[0038] The data distribution module is used to distribute the fetal heart data, the user's basic information, and the fetal heart analysis results to doctors of different levels based on the fetal heart analysis results.

[0039] Furthermore, to achieve the above objectives, the present invention also proposes a fetal heart rate analysis device, the device comprising: a memory, a processor, and a fetal heart rate analysis program stored in the memory and executable on the processor, the fetal heart rate analysis program being configured to implement the steps of the fetal heart rate analysis method as described above.

[0040] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a fetal heart rate analysis program, which, when executed by a processor, implements the steps of the fetal heart rate analysis method as described above.

[0041] This invention discloses a method for acquiring fetal heart rate data and basic user information uploaded by a user; inputting the fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results; the preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module; and distributing the fetal heart rate data, the basic user information, and the fetal heart rate analysis results to doctors at different levels based on the fetal heart rate analysis results. Because this invention inputs fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results, and the preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module, compared to existing technologies, this invention improves the accuracy of fetal heart rate analysis, thereby solving the technical problems of scarce hospital resources and low medical efficiency in existing fetal heart rate monitoring processes. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating the first embodiment of the fetal heart rate analysis method of the present invention;

[0043] Figure 2 This is a schematic diagram of the model architecture of the preset fetal heart rate analysis model in the fetal heart rate analysis method of the present invention;

[0044] Figure 3 This is a flowchart illustrating the second embodiment of the fetal heart rate analysis method of the present invention;

[0045] Figure 4This is a schematic diagram of a single residual block structure that makes up the depth residual model in the fetal heart rate analysis method of the present invention;

[0046] Figure 5 This is a schematic diagram of the structure of two feature extraction modules at different scales in the fetal heart rate analysis method of the present invention;

[0047] Figure 6 This is a schematic diagram of the channel attention structure in the fetal heart rate analysis method of the present invention;

[0048] Figure 7 This is a flowchart illustrating the third embodiment of the fetal heart rate analysis method of the present invention;

[0049] Figure 8 This is a structural block diagram of the first embodiment of the fetal heart rate analysis device of the present invention;

[0050] Figure 9 This is a schematic diagram of the structure of the fetal heart rate analysis device in the hardware operating environment involved in the embodiments of the present invention.

[0051] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0053] This invention provides a method for fetal heart rate analysis, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the fetal heart rate analysis method of the present invention.

[0054] In this embodiment, the fetal heart rate analysis method includes steps S10 to S30:

[0055] Step S10: Obtain the fetal heart rate data and basic user information uploaded by the user.

[0056] It should be noted that the executing entity in this embodiment can be a computer server device with data processing, network communication, and program execution functions applied in the fetal heart rate analysis scenario, such as a personal computer, laptop, mobile phone, smartwatch, etc., or an electronic device or fetal heart rate analysis device capable of realizing the above functions. The following uses a system including a fetal heart rate analysis device (hereinafter referred to as the system) as an example to illustrate this embodiment and the following embodiments.

[0057] It should be understood that fetal heart rate data is an important indicator reflecting the fetus's condition in utero, mainly including fetal heart rate and its changes. Basic user information may include the user's age, month of pregnancy, contact information, and home address.

[0058] It should be added that the above system can provide users with a convenient and accurate remote fetal heart rate analysis platform through a tight integration of the front-end and back-end. The front-end can use the Vue3 + Element-Plus framework to ensure a simple user interface and complete functionality. The back-end can use the Django 2 framework, combined with a preset fetal heart rate analysis model, to realize real-time analysis and result feedback of fetal heart rate monitoring data. The platform has role-based management, with different user roles having different transaction processing workflows, enabling users of different roles to efficiently upload data, review, and communicate on the system, ensuring that pregnant women can receive timely feedback on the fetal health status and reducing the burden of frequent trips to the hospital for high-risk pregnant women.

[0059] Understandably, the system offers login and registration for three user identities: pregnant woman (patient), doctor, and administrator (admin). When a pregnant woman logs in, she can upload fetal heart rate data and basic user information through the system interface. She can also view all her upload records and fetal heart rate analysis results, including upload date, uploaded data, and doctor's review results. Additionally, she can communicate with her assigned doctor to resolve any questions. When a doctor logs in, they can view a list of data awaiting review (including fetal heart rate data and basic user information), sorted by fetal heart rate normal / abnormal and submission time. After reviewing the data, the doctor fills in feedback and submits it. The system also supports fetal heart rate data visualization. If the review results are abnormal, the doctor can promptly remind the patient to schedule an in-person appointment. If there are abnormalities but the doctor cannot contact the pregnant woman immediately, they can directly communicate with the administrator for follow-up. Once the administrator logs into the system, they can view all fetal heart rate analysis data. If the doctor's review result is abnormal, the administrator can directly contact the pregnant woman by phone to remind her to go to the hospital for treatment in time. In addition, for data that is judged to be abnormal by the preset fetal heart rate analysis model, the administrator can directly remind the doctor to review it as soon as possible.

[0060] Step S20: Input the fetal heart rate data and the user's basic information into a preset fetal heart rate analysis model to obtain the fetal heart rate analysis results. The preset fetal heart rate analysis model includes a position encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module.

[0061] It should be noted that in this model study, a pre-designed fetal heart rate analysis model was developed by referring to relevant literature and based on the standard method used by doctors to assess fetal health using fetal heart rate (FHR). This is because doctors primarily focus on the following aspects when evaluating fetal health:

[0062] (1) Overall baseline of fetal heart rate: whether it is within the normal range, i.e., 110-160 beats / minute (bpm).

[0063] (2) Fetal heart rate baseline variation: whether it is moderate, and whether its small fluctuation range is between 6-25 bpm.

[0064] (3) Fetal heart rate acceleration: the quality and frequency of acceleration.

[0065] (4) Fetal heart rate deceleration: its existence and characteristics.

[0066] Based on the above considerations, the model was designed accordingly, for example, referring to... Figure 2 , Figure 2 This is a schematic diagram of the model architecture of the preset fetal heart rate analysis model in the fetal heart rate analysis method of the present invention. In the figure, Input represents the input data; Scale-1 feature extractor and Scale-2 feature extractor represent two feature extractors of different scales, i.e., multi-scale feature extraction modules; Positional Encoding represents the position encoding module; BiGRU represents a bidirectional gated recurrent unit; Layer Norm represents layer normalization; Linear represents a fully connected layer; Fusion represents the feature fusion module; Output represents the output data. In addition, the preset fetal heart rate analysis model also introduces a channel attention mechanism to enhance the model's ability to capture key information.

[0067] It should be noted that, considering that fetal heart rate data is a time series, the temporal relationship between its preceding and following time series may have a significant impact on model performance. Therefore, a position encoding module and a bidirectional gated recurrent unit (BiGRU) are introduced to process this temporal information.

[0068] It should be noted that the Scale-1 feature extractor and Scale-2 feature extractor are feature extractors of different scales, i.e., multi-scale feature extraction modules. They are designed to capture features of different scales, from a strong overall baseline (e.g., 20-minute scale) to medium-scale acceleration and deceleration (e.g., 30-second scale) to smaller-scale baseline variations (e.g., 1-second scale).

[0069] Step S30: Distribute the fetal heart rate data, the user's basic information, and the fetal heart rate analysis results to doctors at different levels based on the fetal heart rate analysis results.

[0070] It should be understood that the above fetal heart rate analysis results include both normal and abnormal cases.

[0071] In practice, if the fetal heart rate analysis result is normal, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result are sent to a doctor for review, with priority given to the doctor the pregnant woman is interested in; if the fetal heart rate analysis result is abnormal, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result are distributed to two doctors at the level of associate chief physician or above for review, with priority given to the doctor the pregnant woman is interested in.

[0072] This embodiment discloses the acquisition of fetal heart rate data and basic user information uploaded by the user; inputting the fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results. The preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module; and distributing the fetal heart rate data, the basic user information, and the fetal heart rate analysis results to doctors at different levels based on the fetal heart rate analysis results. Because this embodiment inputs fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results, and the preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module, compared to existing technologies, this embodiment improves the accuracy of fetal heart rate analysis, thereby solving the technical problems of scarce hospital resources and low medical efficiency in existing fetal heart rate monitoring processes.

[0073] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the fetal heart rate analysis method of the present invention.

[0074] Based on the first embodiment described above, in this embodiment, before step S10, steps S01 to S04 are further included:

[0075] Step S01: Obtain the original fetal heart rate dataset and perform data preprocessing on the original fetal heart rate dataset to obtain the model training dataset.

[0076] It should be understood that the above data preprocessing may include labeling the original fetal heart rate dataset and then cleaning the labeled original fetal heart rate dataset.

[0077] Step S02: Construct a one-dimensional convolutional neural network model and use the one-dimensional convolutional neural network model as the initial fetal heart rate analysis model.

[0078] Step S03: Improve the initial fetal heart rate analysis model to obtain the fetal heart rate analysis model to be trained.

[0079] In specific implementation, in order to improve the accuracy of fetal heart rate analysis, step S03 includes steps S031 to S035:

[0080] Step S031: Improve the initial fetal heart rate analysis model into a deep residual model to obtain the first fetal heart rate analysis model.

[0081] Step S032: Introduce a bidirectional gated loop unit into the first fetal heart rate analysis model to obtain a second fetal heart rate analysis model.

[0082] Step S033: Introduce a multi-scale feature extraction module and a feature fusion module into the second fetal heart rate analysis model to obtain a third fetal heart rate analysis model.

[0083] Step S034: Introduce a position encoding module into the third fetal heart rate analysis model to obtain a fourth fetal heart rate analysis model.

[0084] Step S035: Introduce a channel attention mechanism into the fourth fetal heart rate analysis model to obtain the fetal heart rate analysis model to be trained.

[0085] It should be noted that, in order to increase the model depth and provide better classification results when processing longer sequence data, the initial fetal heart rate analysis model (i.e., a one-dimensional convolutional neural network model) was improved to a deep residual model. For example, refer to... Figure 4 , Figure 4 This is a schematic diagram of a single residual block structure that makes up the deep residual model in the fetal heart rate analysis method of the present invention. In the figure, ResBlock represents a residual block; x is the input; Conv1D represents 1D convolution; Batch Normalization represents batch normalization; ReLU is the activation function; Projection is projection; Shortcut means directly passing the projected value to the output without intermediate processing, used to establish residual connections.

[0086] To capture features at varying scales, from a robust overall baseline (e.g., a 20-minute scale) to intermediate-scale accelerations and decelerations (e.g., a 30-second scale) and even smaller-scale baseline variations (e.g., a 1-second scale), a multi-scale feature extraction module and a feature fusion module are introduced. For example, referencing... Figure 5 , Figure 5 This diagram illustrates the structure of two feature extraction modules at different scales in the fetal heart rate analysis method of this invention. In the diagram, Scale-1 and Scale-2 represent two feature extraction structures at different scales; ResBlock represents the residual block; AvgPool represents the average pooling layer; and Channel Attention represents channel attention.

[0087] Furthermore, considering that fetal heart rate data is a time series, the temporal positional relationship between its preceding and following time series may have a significant impact on model performance. Therefore, a position encoding module and a bidirectional gated recurrent unit (BiGRU) are introduced to process this temporal information.

[0088] It should be noted that after multiple convolutions, the model's channel count can reach 512. To manage this redundant information and enhance the model's ability to capture key information, a channel attention mechanism is introduced, for example, referencing... Figure 6 , Figure 6 This is a schematic diagram of the channel attention structure in the fetal heart rate analysis method of the present invention. In the figure, Channel Attention represents channel attention; Input feature represents input feature; MaxPool represents max pooling layer; AvgPool represents average pooling layer; and SharedMLP represents multilayer shared perceptron.

[0089] Step S04: Input the model training dataset into the fetal heart rate analysis model to be trained to obtain the preset fetal heart rate analysis model.

[0090] In a specific implementation, the model training dataset can be input into the fetal heart rate analysis model to be trained for model training to obtain training results; then, the model parameters of the fetal heart rate analysis model to be trained can be optimized based on the training results to obtain a preset fetal heart rate analysis model.

[0091] Understandably, after the step of inputting the model training dataset into the fetal heart rate analysis model to be trained for model training and obtaining the preset fetal heart rate analysis model, the method further includes: evaluating the preset fetal heart rate analysis model using model evaluation metrics, including: accuracy, precision, recall, and F1 score.

[0092] In practical implementation, the performance of each model can be compared, including accuracy, precision, recall, and F1 score. For example, Table 1 shows a performance comparison of each model:

[0093] Table 1 Performance Comparison of Each Model

[0094] Model accuracy Accuracy Recall rate F1 score Initial fetal heart rate analysis model 86.34 86.51 85.12 85.81 First fetal heart rate analysis model 88.99 90.21 88.98 89.59 Second fetal heart rate analysis model 91.60 91.49 90.61 91.05 Third fetal heart rate analysis model 92.35 92.19 90.42 91.30 Fourth fetal heart rate analysis model 93.05 93.52 92.44 92.98 Preset fetal heart rate analysis model 95.67 94.58 96.93 95.74

[0095] The data in the performance comparison table of each model shows the gradual improvement in the performance of each model, proving the effectiveness of the gradual improvement of the model architecture in this embodiment.

[0096] This embodiment discloses the following steps: acquiring a raw fetal heart rate dataset; preprocessing the raw fetal heart rate dataset to obtain a model training dataset; constructing a one-dimensional convolutional neural network model and using this one-dimensional convolutional neural network model as the initial fetal heart rate analysis model; improving the initial fetal heart rate analysis model into a deep residual model to obtain a first fetal heart rate analysis model; introducing a bidirectional gated recurrent unit into the first fetal heart rate analysis model to obtain a second fetal heart rate analysis model; introducing a multi-scale feature extraction module and a feature fusion module into the second fetal heart rate analysis model to obtain a third fetal heart rate analysis model; introducing a position encoding module into the third fetal heart rate analysis model to obtain a fourth fetal heart rate analysis model; introducing a channel attention mechanism into the fourth fetal heart rate analysis model to obtain a fetal heart rate analysis model to be trained; and inputting the model training dataset into the fetal heart rate analysis model to be trained for model training to obtain a preset fetal heart rate analysis model. Compared with the prior art, this embodiment effectively improves the performance of model analysis and further improves the accuracy of fetal heart rate analysis.

[0097] refer to Figure 7 , Figure 7 This is a flowchart illustrating the third embodiment of the fetal heart rate analysis method of the present invention.

[0098] Based on the above embodiments, in this embodiment, step S01 includes steps S011 to S014:

[0099] Step S011: Obtain the original fetal heart rate dataset and classify the original fetal heart rate dataset to obtain the classification result.

[0100] Step S012: Label the original fetal heart rate dataset based on the classification results to obtain the labeled fetal heart rate dataset.

[0101] Step S013: Clean the labeled fetal heart data dataset according to the fetal heart data screening criteria to obtain a cleaned fetal heart data dataset.

[0102] Step S014: Perform moving average smoothing on the cleaned fetal heart rate dataset to obtain the model training dataset.

[0103] It should be understood that classifying the original fetal heart rate dataset means identifying the positive (positive) and negative (negative) samples in the original fetal heart rate dataset.

[0104] It should be explained that the above fetal heart rate data screening criteria include: deleting all records with a disconnection time of more than 2 minutes; excluding records with a total monitoring time of less than 20 minutes, except for disconnections and obvious data abnormalities (fetal heart rate below 50 bpm or above 220 bpm, usually caused by poor contact); and excluding data for which the doctor cannot make an accurate judgment.

[0105] It should be noted that, in order to further improve data quality, step S014 also includes: performing moving average smoothing on the cleaned fetal heart rate dataset according to a preset time window to obtain a processed fetal heart rate dataset; performing data augmentation on the processed fetal heart rate dataset to obtain an augmented fetal heart rate dataset; and adjusting the augmented fetal heart rate dataset according to the number of each fetal heart rate data category in the augmented fetal heart rate dataset to obtain a model training dataset.

[0106] It is understood that the aforementioned preset time window can be customized by the system administrator, and this embodiment does not impose any restrictions on it.

[0107] It should be noted that the above adjustment of the enhanced fetal heart rate dataset based on the number of each fetal heart rate data category in the enhanced fetal heart rate dataset is to ensure that the number of each fetal heart rate data category in the enhanced fetal heart rate dataset is equal.

[0108] In the specific implementation, it is assumed that the original dataset contains a total of 20484 records. After labeling, the number of positive (positive) samples is 2790, and the number of negative (negative) samples is 17694. After data cleaning of the labeled fetal heart rate dataset, the number of remaining positive and negative samples in the cleaned fetal heart rate dataset is reduced to 2342 and 13556, respectively. To further improve data quality, the cleaned fetal heart rate dataset is subjected to moving average smoothing with a window size of 10 (2.5 seconds). Then, each record is cropped into a segment of 4800 (20 minutes) in length, with an overlap of 1200, for data augmentation. The cropped data retains the same label as the original data. After this step, the number of positive and negative samples is adjusted to 5400 and 19654, respectively. To maintain the balance between samples, 5400 data points are randomly selected from the negative samples. Ultimately, a dataset consisting of a total of 10,800 data points (i.e., the model training dataset), containing an equal number of positive and negative samples, was used for subsequent analysis.

[0109] This embodiment discloses the following steps: acquiring a raw fetal heart rate dataset; classifying the raw fetal heart rate dataset to obtain classification results; labeling the raw fetal heart rate dataset based on the classification results to obtain a labeled fetal heart rate dataset; cleaning the labeled fetal heart rate dataset according to fetal heart rate data selection criteria to obtain a cleaned fetal heart rate dataset; applying a moving average smoothing process to the cleaned fetal heart rate dataset according to a preset time window to obtain a processed fetal heart rate dataset; performing data augmentation on the processed fetal heart rate dataset to obtain an augmented fetal heart rate dataset; and adjusting the augmented fetal heart rate dataset according to the number of fetal heart rate data categories in the augmented fetal heart rate dataset to obtain a model training dataset. Compared to existing technologies, this embodiment improves data quality and ensures the effectiveness of fetal heart rate analysis results generated by the preset fetal heart rate analysis model.

[0110] Furthermore, this embodiment of the invention also proposes a storage medium storing a fetal heart rate analysis program, which, when executed by a processor, implements the steps of the fetal heart rate analysis method described above.

[0111] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the fetal heart rate analysis device of the present invention.

[0112] like Figure 8 As shown, the fetal heart rate analysis device proposed in this embodiment of the invention includes: a data acquisition module 801, a data analysis module 802, and a data distribution module 803.

[0113] The data acquisition module 801 is used to acquire fetal heart rate data and basic user information uploaded by the user.

[0114] The data analysis module 802 is used to input the fetal heart data and the user's basic information into a preset fetal heart analysis model to obtain fetal heart analysis results. The preset fetal heart analysis model includes a position encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module.

[0115] The data distribution module 803 is used to distribute the fetal heart data, the user's basic information, and the fetal heart analysis results to doctors of different levels based on the fetal heart analysis results.

[0116] The data distribution module 803 is further configured to, if the fetal heart rate analysis result is normal, send the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result to a doctor for fetal heart rate analysis review; if the fetal heart rate analysis result is abnormal, distribute the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result to two doctors at the level of associate chief physician or above for fetal heart rate analysis review.

[0117] This device embodiment discloses the acquisition of fetal heart rate data and basic user information uploaded by the user; inputting the fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results. The preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module; and distributing the fetal heart rate data, the basic user information, and the fetal heart rate analysis results to doctors at different levels based on the fetal heart rate analysis results. Because this device embodiment inputs fetal heart rate data and basic user information into a preset fetal heart rate analysis model to obtain fetal heart rate analysis results, and the preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module, compared to existing technologies, this device embodiment improves the accuracy of fetal heart rate analysis, thereby solving the technical problems of scarce hospital resources and low medical efficiency in existing fetal heart rate monitoring processes.

[0118] Based on the first embodiment of the fetal heart rate analysis device of the present invention described above, a second embodiment of the fetal heart rate analysis device of the present invention is proposed.

[0119] In this embodiment, the data acquisition module 801 is further configured to acquire the original fetal heart rate dataset, perform data preprocessing on the original fetal heart rate dataset to obtain a model training dataset; construct a one-dimensional convolutional neural network model and use the one-dimensional convolutional neural network model as the initial fetal heart rate analysis model; improve the initial fetal heart rate analysis model to obtain a fetal heart rate analysis model to be trained; and input the model training dataset into the fetal heart rate analysis model to be trained for model training to obtain a preset fetal heart rate analysis model.

[0120] The data acquisition module 801 is further configured to improve the initial fetal heart rate analysis model into a deep residual model to obtain a first fetal heart rate analysis model; introduce a bidirectional gated recurrent unit into the first fetal heart rate analysis model to obtain a second fetal heart rate analysis model; introduce a multi-scale feature extraction module and a feature fusion module into the second fetal heart rate analysis model to obtain a third fetal heart rate analysis model; introduce a position encoding module into the third fetal heart rate analysis model to obtain a fourth fetal heart rate analysis model; and introduce a channel attention mechanism into the fourth fetal heart rate analysis model to obtain a fetal heart rate analysis model to be trained.

[0121] The data acquisition module 801 is also used to evaluate the preset fetal heart rate analysis model using model evaluation indicators, including accuracy, precision, recall and F1 score.

[0122] Other embodiments or specific implementations of the fetal heart rate analysis device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0123] This application provides a fetal heart rate analysis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the fetal heart rate analysis method in the above embodiment 1.

[0124] The following is for reference. Figure 9 The diagram illustrates a structural schematic of a fetal heart rate analysis device suitable for implementing embodiments of this application. The fetal heart rate analysis device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 9 The fetal heart rate analysis device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0125] like Figure 9 As shown, the fetal heart rate analysis device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the fetal heart rate analysis device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the fetal heart rate analyzer to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a fetal heart rate analyzer with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0126] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0127] The fetal heart rate analysis device provided in this application, employing the fetal heart rate analysis method described in the above embodiments, can solve the technical problem of how to improve the accuracy of fetal heart rate analysis. Compared with the prior art, the beneficial effects of the fetal heart rate analysis device provided in this application are the same as those of the fetal heart rate analysis method provided in the above embodiments, and other technical features of this fetal heart rate analysis device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0128] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0129] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0130] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0131] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0133] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for fetal heart rate analysis, characterized in that, The method includes: Obtain fetal heart rate data and basic user information uploaded by the user; The fetal heart rate data and the user's basic information are input into a preset fetal heart rate analysis model to obtain the fetal heart rate analysis results. The preset fetal heart rate analysis model includes a location encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module. Based on the fetal heart rate analysis results, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis results are distributed to doctors at different levels; Before the steps of obtaining the fetal heart rate data and basic user information uploaded by the user, the method further includes: Obtain the original fetal heart rate dataset and perform data preprocessing on the original fetal heart rate dataset to obtain the model training dataset; A one-dimensional convolutional neural network model is constructed, and the one-dimensional convolutional neural network model is used as the initial fetal heart rate analysis model; The initial fetal heart rate analysis model is improved to obtain a fetal heart rate analysis model to be trained; The model training dataset is input into the fetal heart rate analysis model to be trained to obtain the preset fetal heart rate analysis model. The step of improving the initial fetal heart rate analysis model to obtain the fetal heart rate analysis model to be trained includes: The initial fetal heart rate analysis model was improved into a deep residual model to obtain the first fetal heart rate analysis model. A bidirectional gated cyclic unit is introduced into the first fetal heart rate analysis model to obtain a second fetal heart rate analysis model. A multi-scale feature extraction module and a feature fusion module are introduced into the second fetal heart rate analysis model to obtain a third fetal heart rate analysis model. A position encoding module is introduced into the third fetal heart rate analysis model to obtain a fourth fetal heart rate analysis model; A channel attention mechanism is introduced into the fourth fetal heart rate analysis model to obtain the fetal heart rate analysis model to be trained.

2. The fetal heart rate analysis method as described in claim 1, characterized in that, The steps of obtaining the original fetal heart rate dataset and performing data preprocessing on the original fetal heart rate dataset to obtain the model training dataset include: Obtain the original fetal heart rate dataset and classify the original fetal heart rate dataset to obtain the classification results; The original fetal heart rate dataset is labeled based on the classification results to obtain the labeled fetal heart rate dataset. The labeled fetal heart data dataset was cleaned according to the fetal heart data screening criteria to obtain a cleaned fetal heart data dataset. The cleaned fetal heart rate dataset is smoothed by moving average to obtain the model training dataset.

3. The fetal heart rate analysis method as described in claim 2, characterized in that, The step of performing moving average smoothing on the cleaned fetal heart rate dataset to obtain the model training dataset includes: The cleaned fetal heart rate dataset is smoothed by a moving average according to a preset time window to obtain the processed fetal heart rate dataset. The processed fetal heart rate dataset is subjected to data augmentation to obtain an augmented fetal heart rate dataset; The enhanced fetal heart rate dataset is adjusted based on the number of each fetal heart rate data category in the enhanced fetal heart rate dataset to obtain the model training dataset.

4. The fetal heart rate analysis method as described in claim 1, characterized in that, The step of distributing the fetal heart rate data, the user's basic information, and the fetal heart rate analysis results to doctors at different levels based on the fetal heart rate analysis results includes: If the fetal heart rate analysis result is normal, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result will be sent to a doctor for fetal heart rate analysis review. If the fetal heart rate analysis result is abnormal, the fetal heart rate data, the user's basic information, and the fetal heart rate analysis result will be distributed to two doctors at the level of associate chief physician or above for fetal heart rate analysis review.

5. The fetal heart rate analysis method as described in claim 1, characterized in that, After the step of inputting the model training dataset into the fetal heart rate analysis model to be trained for model training and obtaining the preset fetal heart rate analysis model, the method further includes: The preset fetal heart rate analysis model is evaluated using model evaluation metrics, which include: accuracy, precision, recall, and F1 score.

6. A fetal heart rate analyzer, characterized in that, The device includes: The data acquisition module is used to acquire fetal heart rate data and basic user information uploaded by the user. The data analysis module is used to input the fetal heart data and the user's basic information into a preset fetal heart analysis model to obtain fetal heart analysis results. The preset fetal heart analysis model includes a position encoding module, a bidirectional gated loop unit, a channel attention mechanism, a multi-scale feature extraction module, and a feature fusion module. The data distribution module is used to distribute the fetal heart data, the user's basic information, and the fetal heart analysis results to doctors of different levels based on the fetal heart analysis results. The data acquisition module is further configured to acquire the original fetal heart rate dataset, perform data preprocessing on the original fetal heart rate dataset to obtain a model training dataset; construct a one-dimensional convolutional neural network model and use the one-dimensional convolutional neural network model as the initial fetal heart rate analysis model; improve the initial fetal heart rate analysis model to obtain a fetal heart rate analysis model to be trained; input the model training dataset into the fetal heart rate analysis model to be trained for model training to obtain a preset fetal heart rate analysis model. The data acquisition module is further configured to improve the initial fetal heart rate analysis model into a deep residual model to obtain a first fetal heart rate analysis model; introduce a bidirectional gated recurrent unit into the first fetal heart rate analysis model to obtain a second fetal heart rate analysis model; introduce a multi-scale feature extraction module and a feature fusion module into the second fetal heart rate analysis model to obtain a third fetal heart rate analysis model; introduce a position encoding module into the third fetal heart rate analysis model to obtain a fourth fetal heart rate analysis model; and introduce a channel attention mechanism into the fourth fetal heart rate analysis model to obtain a fetal heart rate analysis model to be trained.

7. A fetal heart rate analysis device, characterized in that, The device includes: a memory, a processor, and a fetal heart rate analysis program stored in the memory and executable on the processor, the fetal heart rate analysis program being configured to implement the steps of the fetal heart rate analysis method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores a fetal heart rate analysis program, which, when executed by a processor, implements the steps of the fetal heart rate analysis method as described in any one of claims 1 to 5.

Images