Admission blood tests predicting survival of SARS-CoV-2 infected patients: a practical implementation of graph convolution network in imbalance dataset
The GCN model considerably outperformed all other machine learning methods and baseline CPH models. Thus, when applied to this imbalanced COVID survival dataset, adopting a population graph representation may be an approach to achieving good prediction.
Authors
- Varut Vardhanabhuti (ORCID: https://orcid.org/0000-0001-6677-3194)
- Douglas K. S. Ng (ORCID: https://orcid.org/0000-0002-5512-011X)
- Simon Ching Lam (ORCID: https://orcid.org/0000-0002-2982-9192)
- Kitty Yu-Yeung Lau (ORCID: https://orcid.org/0000-0002-1627-7472)
- Fan Huang (ORCID: https://orcid.org/0000-0002-9767-089X)
- Jie Lian (ORCID: https://orcid.org/0000-0002-2005-2022)
- Mohamad Koohli-Moghadam
- Xinhai Huang
- Carlin Chun Fai Chu
Institutions
- Tung Wah College (HK)
- HKU-Pasteur Research Pole (HK)
- Hang Seng University of Hong Kong (HK)
- University of Hong Kong (HK)
Publication Details
- Journal
- BMC Infectious Diseases
- Published
- 2024-08-09
- DOI
- https://doi.org/10.1186/s12879-024-09699-x
- Primary Topic
- Imbalanced Data Classification Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00