RDDL: A systematic ensemble pipeline tool that streamlines balancing training schemes to reduce the effects of data imbalance in rare-disease-related deep-learning applications

• Published in: Computational biology and chemistry 2023-10, Vol.106, p.107929-107929, Article 107929
• Main Authors: Yang, Tzu-Hsien, Liao, Zhan-Yi, Yu, Yu-Huai, Hsia, Min
• Format: Article
• Language: English
• Subjects: Identification of lowly prevalent diseases; Imbalanced data classification; Model ensemble; Rare disease
• ISSN: 1476-9271; 1476-928X
• DOI: 10.1016/j.compbiolchem.2023.107929

Identifying lowly prevalent diseases, or rare diseases, in their early stages is key to disease treatment in the medical field. Deep learning techniques now provide promising tools for this purpose. Nevertheless, the low prevalence of rare diseases entangles the proper application of deep networks for disease identification due to the severe class-imbalance issue. In the past decades, some balancing methods have been studied to handle the data-imbalance issue. The bad news is that it is verified that none of these methods guarantees superior performance to others. This performance variation causes the need to formulate a systematic pipeline with a comprehensive software tool for enhancing deep-learning applications in rare disease identification. We reviewed the existing balancing schemes and summarized a systematic deep ensemble pipeline with a constructed tool called RDDL for handling the data imbalance issue. Through two real case studies, we showed that rare disease identification could be boosted with this systematic RDDL pipeline tool by lessening the data imbalance problem during model training. The RDDL pipeline tool is available at https://github.com/cobisLab/RDDL/. [Display omitted] •The low prevalence of rare diseases complicates related deep network applications.•Solving data imbalance in rare diseases requires considering all balancing schemes.•A tool called RDDL was implemented to help users handle the issue systematically.•RDDL applies to diverse rare disease data that bear different modalities.