A method and device for analyzing electronic fetal heart rate monitoring data based on artificial intelligence

Abstract

The invention discloses a method and a device for analyzing electronic fetal heart rate monitoring data based on artificial intelligence. The method includes: preprocessing according to initial EFM data to obtain EFM data; Perform feature screening on the initial EFM data features, obtain the EFM data features, build an algorithm model according to the EFM data features, encapsulate the algorithm model, obtain the encapsulation model, input the continuously collected EFM data into the encapsulation model for training, and output the probability of EFM data prediction results The probability value is input into the preset regression analysis equation for analysis, and the probability value of fetal acidosis and fetal distress combined with the clinical characteristics of the patient is output. By extracting various features of EFM data, erroneous clinical decisions caused by manual interpretation of individual differences in fetal heart rate monitoring data are reduced. At the same time, artificial intelligence algorithms are used to mine the direct connection between fetal heart rate monitoring data and fetal delivery outcomes, which improves clinical decision-making. s efficiency.

Description

technical field [0001] The invention relates to the technical field of electronic fetal heart rate monitoring, in particular to a method and device for analyzing electronic fetal heart rate monitoring data based on artificial intelligence. Background technique [0002] Electronic fetal monitoring (EFM) is a medical device that is widely used in clinic to evaluate the intrauterine state of the fetus. Using the principle of ultrasound Doppler, the fetal heart rate (fetal heart rate, FHR) and the uterine contraction (UC) of the pregnant woman were collected respectively through the fetal heart signal acquisition probe and the uterine contraction signal acquisition probe fixed on the abdomen of the pregnant woman. After continuous acquisition and signal conversion, it is displayed on the display as the curve of fetal heart rate and uterine contraction pressure value. According to the manifestations of different EFM waveforms, clinicians can roughly judge whether the fetus has i...

AI Technical Summary

Problems solved by technology

[0004] However, the fetal monitoring classification results obtained by the scoring system cannot fully reflect the intrauterine status of the fetus. With the development of artificial intelligence, in order to improve the value and accuracy of electronic fetal heart rate monitoring data in evaluating fetal Combination of fetal monitoring analysis

However, the included fetal monitoring information is less, which is likely to cause errors and deviations, and the analysis results are not good, and there is no further research on the relationship between this classification and the intrauterine status of the fetus, which cannot meet the needs of clinical practice.

Images