A novel generative adversarial networks modelling for the class imbalance problem in high dimensional omics data
Cusworth, Samuel Gkoutos, Georgios V Acharjee, Animesh
Cusworth, Samuel
Gkoutos, Georgios V
Acharjee, Animesh
Abstract
Class imbalance remains a large problem in high-throughput omics analyses, causing bias towards the over-represented class when training machine learning-based classifiers. Oversampling is a common method used to balance classes, allowing for better generalization of the training data. More naive approaches can introduce other biases into the data, being especially sensitive to inaccuracies in the training data, a problem considering the characteristically noisy data obtained in healthcare. This is especially a problem with high-dimensional data. A generative adversarial network-based method is proposed for creating synthetic samples from small, high-dimensional data, to improve upon other more naive generative approaches. The method was compared with 'synthetic minority over-sampling technique' (SMOTE) and 'random oversampling' (RO). Generative methods were validated by training classifiers on the balanced data.
Keywords: Class imbalance; GAN; Multiomics; Synthetic data.
MIDER Authors
Citations
Altmetric:
Date
2024-03-28
Type
Article
Subject
Health services. Management, Public health. Health statistics. Occupational health. Health education
Collections
Citation
Cusworth S, Gkoutos GV, Acharjee A. A novel generative adversarial networks modelling for the class imbalance problem in high dimensional omics data. BMC Med Inform Decis Mak. 2024 Mar 28;24(1):90. doi: 10.1186/s12911-024-02487-2. PMID: 38549123; PMCID: PMC10979623.
Journal / Source Title
BMC Medical Informatics and Decision Making
DOI
10.1186/s12911-024-02487-2
PMID
38549123
Publisher
BioMed Central