Does combining numerous data types in multi-omics data improve or hinder performance in survival prediction? Insights from a large-scale benchmark study
Our findings challenge the prevailing notion that combining multiple omics data types in multi-omics survival prediction improves predictive performance. Thus, the widespread approach in multi-omics prediction of incorporating as many data types as possible should be reconsidered to avoid suboptimal prediction results and unnecessary expenditure.
Authors
- Yingxia Li (ORCID: https://orcid.org/0000-0002-4501-5834)
- Roman Hornung (ORCID: https://orcid.org/0000-0002-6036-1495)
- Ulrich Mansmann (ORCID: https://orcid.org/0000-0002-9955-8906)
- Tobias Herold (ORCID: https://orcid.org/0000-0002-9615-9432)
Institutions
- Zimmer Biomet (Netherlands) (NL)
- Zimmer Biomet (Germany) (DE)
- Munich Center for Machine Learning
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2024-09-02
- DOI
- https://doi.org/10.1186/s12911-024-02642-9
- Citations
- 10
- Primary Topic
- Epigenetics and DNA Methylation
- Type
- article
- Field-Weighted Citation Impact
- 2.34
Funders
- Deutsche Forschungsgemeinschaft
- China Scholarship Council
- Ludwig-Maximilians-Universität München