Multimodal convolutional neural networks to detect fetal compromise during labor and delivery
- Submitting institution
-
University of Portsmouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 26096774
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2019.2933368
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 112026
- Volume
- 7
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2019
- 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
-
4
- Research group(s)
-
B - Computational Intelligence
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- A novel Deep Learning approach for automated analysis and prediction of the risk of baby oxygen starvation during childbirth based on cardiotocography (CTG) data and linked clinical data (comprising more than 35,000 births). The developed Multimodal Convolutional Neural Network models outperform the best feature extraction-based prediction methods in the area. These pioneering models and the obtained results provided a foundation for a recent successful EPSRC project bid EP-V002511-1 (£762,000) in partnership with Oxford University Hospitals NHS Trust.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -