Classification of Cardiotocography Based on the Apriori Algorithm and Multi-Model Ensemble Classifier

Abstract

Cardiotocography (CTG) recorded fetal heart rate and its temporal relationship with uterine contractions. CTG intelligent classification plays an important role in evaluating fetal health and protecting fetal normal growth and development throughout pregnancy. At the feature selection level, this study uses the Apriori algorithm to search frequent item sets for feature extraction. At the level of the classification model, the combination model of AdaBoost and random forest with the highest classification accuracy is finally selected by comparing various models. The suspicious class data in the CTG data set affect the overall classification accuracy. The number of suspicious class data is predicted by the multi-model ensemble method. Finally, the data set is fused from three classifications to two classifications. The classification accuracy is 0.976, and the AUC is 0.98, which significantly improves the classification effect. In conclusion, the method used in this study has high accuracy in model classification, which is helpful to improve the accuracy of fetal abnormality detection.

Machine learning and disease prediction in obstetrics

“…Cardiotocography is the most prevalent diagnostic tool used for continuous fetal monitoring and assessments of fetal distress ( Cömert et al, 2019 ). They display biophysical signals for the fetal heart rate and uterine contractions ( Hoodbhoy et al, 2019 ; Chen and Yin, 2022 ). Using current standards for interpretation there is a high degree of inter and intra-observer variation.…”

Toward Enhanced Customer Transaction Insights: An Apriori Algorithm-based Analysis of Sales Patterns at University Industrial Corporation

“…Notably, it facilitated the development of an automatic diagnostic system for breast cancer detection [18], and the identification of distinguishing factors between dementia patients, and caregivers linked to long-term care services [19]. Furthermore, it revealed a set of frequent items aiding in fetal anomaly detection [20], and uncovered the primary combination of Chinese herbs for Alzheimer's disease treatment within acupuncture practices [21]. Research efforts extended into investigating acupuncture point combinations for the treatment of hemiparesis [22], exploring protein-gene interactions from omics data [23], and identifying links between Polycystic Ovary Syndrome (PCOS), and hormonal imbalances utilizing the DEODORANT model [24].…”

Prediction of miRNA–Disease Associations by Cascade Forest Model Based on Stacked Autoencoder

“…In the encoding phase, the original feature representation is fed to the encoder to achieve feature compression and dimensionality reduction. The corresponding formula is given by z = f e (wx + b), (23) where x is the original high-dimensional feature input, w and b denote the weights and bias, f e (•) represents the non-linear activation function of the encoder phase, and z is the output of the encoder. The purpose of the decoder is to use the latent representation z to reconstruct the input x.…”

“…The second category of methods is machine learning-based methods, which have been indicated to be powerful in many classification tasks, especially in bioinformatics [ 22 , 23 ]. For instance, Zheng et al [ 24 ] developed the MLMDA method to predict microRNA–disease associations.…”