Bio-process inspired characterization of pregnancy evolution using entropy and its application in preterm birth detection. (May 2022)

• Record Type: Journal Article
• Authors: Lou, Hangxiao; Liu, Haifeng; Chen, Zhenqin; Zhen, Zi'ang; Dong, Bo; Xu, Jinshan
• Is Part Of: Biomedical signal processing and control. Volume 75(2022)
• Publication Date: 2022-05
• Subjects: Electrohysterogram -- entropy features -- machine learning -- preterm birth prediction; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103587
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: We corrected the improper description on the dataset and gave more accurate citations to the existing works according to referee's suggestions. We updated Fig. 4 to illustrate the dynamical changes the uterus experiences throughout the pregnancy, and corrected the misleading interpolation. We discussed the effect of the very small number of preterm samples in testing set. We rearranged the panels in Fig. 3 in a descending order of the time-to-delivery. Abstract: The lack of effective method for an early diagnosis of preterm births makes it a public health problem world-widely. The relationship between the uterine contraction and the underlying electrical muscle cells makes the machine-learning-based Eelctrohysterogram (EHG) signal processing an ideal direction for the development of methods for preterm births. Inspired by the observation of dynamical changes of the uterus experiences throughout the whole pregnancy, we used entropy features extracted from the time–frequency expansion of the original EHG signal to characterize the uterine activities. These entropy features were then rescaled by the gestational age at recording (recording time) to characterize the evolution speed of the uterus toward delivery. By selecting out the most relevant frequency components using the principle components analysis (PCA), the Gaussian Naive Bayes (GNB) classifier trained and evaluated with samples prepared under the Partition-Synthesis oversampling scheme gives average preterm births prediction accuracy, sensitivity, specificity and AUC values as high as 0.75, 0.84, 0.66, and 0.84, respectively.