Deep neural architectures for prediction in healthcare
- Submitting institution
-
University of Lincoln
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 30087
- Type
- D - Journal article
- DOI
-
10.1007/S40747-017-0064-6
- Title of journal
- Complex & Intelligent Systems
- Article number
- -
- First page
- 119
- Volume
- 4
- Issue
- 2
- ISSN
- 2199-4536
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2017
- URL
-
https://doi.org/10.1007/S40747-017-0064-6
- 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
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 15
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The approach developed in this paper, based on unsupervised analysis of latent information extracted from trained CNN-RNNs for Parkinson’s prediction, further provided a unified prediction framework, producing excellent results over different data cohorts, such as the standard PPMI dataset (IJCNN 2019, https://doi.org/10.1109/IJCNN.2019.8851995, IET Image Processing https://doi.org/10.1049/iet-ipr.2019.1526). The approach was recently applied for
Covid-19 diagnosis from Chest CT scans and x-rays (ECAI 2020: 1 st TAILOR Workshop on Foundations of Trustworthy AI: Integrating Learning, Optimization, Reasoning,
https://www.ida.liu.se/~frehe08/tailor2020/TAILOR_2020_paper_47.pdf) and was adopted by the Greek Infrastructures for Research and Technology for Covid-19 diagnosis from data obtained from all public Greek Hospitals (
https://grnet.gr/en/2021/01/15/announcement_grnet_covid19_15_1_21_en/).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -