Method and device for analyzing electronic fetal heart monitoring data based on artificial intelligence

Abstract

The invention discloses a method and device for analyzing electronic fetal heart monitoring data based on artificial intelligence. The method comprises the steps of carrying out preprocessing according to initial EFM data so as to obtain EFM data, carrying out characteristic extraction on the EFM data, carrying out characteristic screening on initial EFM data characteristics according to a preset characteristic screening method so as to obtain EFM data characteristics, establishing an algorithmic model according to the EFM data characteristics, encapsulating the algorithmic model so as to obtain an encapsulated model, inputting continuous-acquired EFM data into the encapsulated model for training, outputting a probability value of EFM data prediction results, inputting the probability value into a preset regressive analysis equation for analysis, and outputting a probability value of acidosis and fetal distress of a fetus after combining sufferer's clinical features. Through extracting a plurality of characteristics from the EFM data, wrong clinical decisions caused by individual differences of manual reading of fetal heart monitoring data are reduced; and meanwhile, a direct relation between the fetal heart monitoring data and a fetus delivery outcome is mined through artificial intelligence algorithms, so that the efficiency of clinical decision making is increased.

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 widely used clinically to evaluate the intrauterine status of the fetus. Using the ultrasound Doppler principle, the fetal heart rate (fetal heart rate, FHR) and maternal uterine contraction pressure (uterine contraction, UC) were collected respectively through the fetal heart signal acquisition probe and the uterine contraction signal acquisition probe fixed in the pregnant woman's abdomen. After continuous acquisition and signal conversion, the fetal heart rate curve and uterine contraction pressure value curve are displayed on the display screen. According to the manifestations of different EFM waveforms, clinicians can roughly judge whether the fetus h...

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