Prenatal fetal heart monitoring signal intelligent interpretation method

An intelligent interpretation and signal technology, applied in the field of deep learning, can solve problems such as the lack of in-depth research on the impact of uterine contraction pressure signals, fetal movement signals, fetal health conditions, fetal monitoring machines that have not reached the level of intelligence, and signal preprocessing processes that are simple, etc., to achieve The effect of reducing fetal mortality and caesarean section rate, improving classification and discrimination performance, and avoiding medical intervention

Pending Publication Date: 2021-10-01
GUANGZHOU SUNRAY MEDICAL APP
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the model using signal modeling only considers the fetal heart rate signal, ignoring the relationship between the fetal heart rate signal and the uterine contraction pressure signal, and has not studied the influence of the uterine contraction pressure signal and the fetal movement signal on the health status of the fetus, and the process of signal preprocessing too simple
[0006] In general, the prenatal fetal monitoring machines currently used at home and abroad are still not able to reach the level of intelligence, and the accuracy rate of identifying suspicious categories is only 45-82%, and the accuracy rate of abnormal categories is only 66-94%. clinical application

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Prenatal fetal heart monitoring signal intelligent interpretation method
  • Prenatal fetal heart monitoring signal intelligent interpretation method
  • Prenatal fetal heart monitoring signal intelligent interpretation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] A pre-prenatal fetal heart monitoring signal provided by the present invention includes the following steps:

[0034] S1: Get raw CTG signal data containing the fetal heart rate signal, the uterine pressure signal, and the fetal movement signal;

[0035] S2: Pretreatment of the fetal heart rate signal, the uterine pressure signal, and the fetal movement, forming a fusion multi-signal data set;

[0036] The pretreatment includes interpolation or deleting a fetal heart rate signal, a uterine pressure signal, a fetal signal, respectively;

[0037] The pretreatment also includes standardization of the fetal heart rate signal of the interpolated or deleted process;

[0038] The pretreatment also includes a sliding window segmentation of the interpolation or deleted process-induced fetal heart signal, which is not less than p on the normalization process of the interpolated or deleted fetal heart rate signal. Fetal heart rate signal fragment; where P is 750;

[0039] The standard...

Embodiment 2

[0073] In order to verify the data set to be classified differences affect the ability of discriminating the smart interpretation method of the present invention. Example 2 is provided to verify the control group four, group A: Waiting classification data set containing only criteria fetal heart rate signal (the FHR); control group B: a data set containing only be classified contractions signal (the UC); group C : data set containing only be classified FM signal (the FM); group D: a data set containing only be classified standard contractions and fetal heart rate of the combined signal (FU). The remaining group of four process steps consistent with Example 1. Embodiment 2 Comparative Example verification and accuracy analysis of four cases in the control group 1 embodiment, precision, recall, specificity, Fl value, Kappa coefficient, the coefficient and the MCC AUC values, comparative analysis of the results shown in Table 2.

[0074] Comparative Example 1 Performance analysis res...

Embodiment 3

[0078] In order to verify the fusion multi-signal data set synchronous with the sliding window segmentation process to discriminate the intelligent interpretation method of the present invention. The fusion multi-signal data set of the control group E did not perform the sliding window segmentation, and the remaining method steps were consistent with the first embodiment. Verification Example 3 Comparative Analysis Example 1 The accuracy, accuracy, recall rate, specificity, F1 value, Kappa coefficient, MCC coefficient, and AUC values ​​were shown in Table 3.

[0079] Table 3 Comparative Analysis Results of Control Group B and Example 1

[0080]

[0081] The results of Table 3 show that the fusion multi-signal data set is synchronized with the control group E, the accuracy, the recall rate, the F1 value, the KAPPA coefficient, the MCC coefficient, and the AUC value are reached. A higher degree, indicating that the classification discriminant performance of the intelligent judgmen...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a prenatal fetal heart monitoring signal intelligent interpretation method which comprises the following steps: preprocessing a fetal heart rate signal, a uterine contraction pressure signal and a fetal movement signal to obtain a fused multi-signal data set; then performing segmentation processing, and constructing a data set to be classified; and inputting an embedded layer, a splicing layer, a bidirectional gating circulation unit layer and a full connection layer of the prenatal fetal monitoring intelligent interpretation model in sequence, and performing sigmoid function compression on an output result to obtain a classification judgment result. According to the intelligent interpretation method, the uterine contraction pressure signal and the fetal movement signal are integrated into the antenatal fetal monitoring intelligent interpretation model based on the bidirectional gating circulation unit, and compared with other deep learning models, the intelligent interpretation method is short in consumed time and has better classification and discrimination capacity.

Description

Technical field [0001] The present invention relates to a depth learning method, in particular, to a pre-prenatal fetal heart monitoring signal intelligent interpretation method for intelligent classification discrimination of prenatal fetal condition assessment. Background technique [0002] Pre-prenatal fetal monitoring is widely used to assess the healthy development of the fetus and treat it before the fetus has adverse reactions. Fetal Heart Monitor Monitoring (CTG) is an important tool for fetal prenatal health monitoring, recording changes in fetal heart rate during pregnancy, and its time relationship with contractions. The role is, but is not limited to, determining whether the fetus is hypoxia, determining whether pregnant women are required to give birth through caesarean section, and to guide fetal health status. [0003] At this stage, the judgment of fetal heart harvest monitoring map (CTG) is responsible for the obstetrician. The judgment is based primarily in the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/11A61B5/024A61B5/00
CPCA61B5/1118A61B5/02411A61B5/4356A61B5/4362A61B5/7235A61B5/7267A61B5/7203A61B5/725A61B2503/02
Inventor 魏航陈帆费悦陈沁群洪佳明洪乐雄李丽陈剑梅林伙旺
Owner GUANGZHOU SUNRAY MEDICAL APP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap