Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomes

Fergus, P, Chalmers, C, Montañez, CC, Reilly, D, Lisboa, P and Pineles, B (2020) Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomes. IEEE Transactions on Emerging Topics in Computational Intelligence. ISSN 2471-285X

09201026.pdf - Accepted Version

Download (3MB) | Preview


Gynaecologists and obstetricians visually interpret cardiotocography (CTG) traces using the International Federation of Gynaecology and Obstetrics (FIGO) guidelines to assess the wellbeing of the foetus during antenatal care. This approach has raised concerns among professionals with regards to inter- and intra-variability where clinical diagnosis only has a 30\% positive predictive value when classifying pathological outcomes. Machine learning models, trained with FIGO and other user derived features extracted from CTG traces, have been shown to increase positive predictive capacity and minimise variability. This is only possible however when class distributions are equal which is rarely the case in clinical trials where case-control observations are heavily skewed in favour of normal outcomes. Classes can be balanced using either synthetic data derived from resampled case training data or by decreasing the number of control instances. However, this either introduces bias or removes valuable information. Concerns have also been raised regarding machine learning studies and their reliance on manually handcrafted features. While this has led to some interesting results, deriving an optimal set of features is considered to be an art as well as a science and is often an empirical and time consuming process. In this paper, we address both of these issues and propose a novel CTG analysis methodology that a) splits CTG time-series signals into n-size windows with equal class distributions, and b) automatically extracts features from time-series windows using a one dimensional convolutional neural network (1DCNN) and multilayer perceptron (MLP) ensemble. Collectively, the proposed approach normally distributes classes and removes the need to handcrafted features from CTG traces.

Item Type: Article
Additional Information: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords: cs.LG; cs.LG; stat.ML
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RG Gynecology and obstetrics
Divisions: Computer Science & Mathematics
Publisher: IEEE
Related URLs:
Date Deposited: 22 Oct 2020 09:03
Last Modified: 04 Sep 2021 06:29
DOI or ID number: 10.1109/TETCI.2020.3020061
URI: https://researchonline.ljmu.ac.uk/id/eprint/13888
View Item View Item