Modelling Segmented Cardiotocography Time-Series Signals Using
One-Dimensional Convolutional Neural Networks for the Early Detection of
Abnormal Birth Outcomes
- Submitting institution
-
Liverpool John Moores University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2000
- Type
- D - Journal article
- DOI
-
10.1109/TETCI.2020.30200610
- Title of journal
- IEEE Transactions on Emerging Topics in Computational Intelligence
- Article number
- -
- First page
- 1
- Volume
- 0
- Issue
- -
- ISSN
- 2471-285X
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This research uses a windowing strategy in conjunction with a one dimensional Convolution Neural network to minimise variability in the interpretation of Cardiotocographic (CTG) traces. The research is a collaborative effort involving Computer Scientists at LJMU and Clinicians at University of Maryland. The research presents the benefits of an automated CTG trace windowing system to help reduce morbidity and mortality outcomes associated with abnormal deliveries. The research uses the CTU-UHB Intrapartum Cardiotocography Database from the Czech Technical University. The research serves as the basis for further collaboration between the authors involved.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
