Overlooked and underpowered: a meta-research addressing sample size in radiomics prediction models for binary outcomes
Question Sample size justification is critical to help minimize overfitting in developing a radiomics model, but is overlooked and underpowered in radiomics research. Findings Few of the radiomics models justified, calculated, or reported their sample size, and most of them did not meet the recent formal sample size criteria. Clinical relevance Radiomics models are often designed without sample size justification. Consequently, many models are too small to avoid overfitting. It should be encouraged to justify, perform, and report the considerations on sample size when developing radiomics models.
Authors
- Guangcheng Zhang (ORCID: https://orcid.org/0000-0002-7889-2710)
- Defang Ding (ORCID: https://orcid.org/0000-0001-9815-6318)
- Weiwu Yao (ORCID: https://orcid.org/0000-0002-6612-8520)
- Jingyu Zhong (ORCID: https://orcid.org/0000-0002-9817-2294)
- Run Jiang (ORCID: https://orcid.org/0009-0006-0200-5405)
- Haoda Chen (ORCID: https://orcid.org/0000-0002-5774-0742)
- Yang Song
- Qingqing Cen (ORCID: https://orcid.org/0000-0003-2590-0147)
- Xiang Ge (ORCID: https://orcid.org/0000-0001-9167-5334)
- Shiqi Mao (ORCID: https://orcid.org/0000-0001-8036-7336)
- Minda Lu
- Yue Xing (ORCID: https://orcid.org/0000-0001-6340-0640)
- Huan Zhang (ORCID: https://orcid.org/0000-0002-9838-0624)
- Xian‐Wei Liu (ORCID: https://orcid.org/0000-0002-0493-8210)
- Qian Yin (ORCID: https://orcid.org/0000-0002-0178-0817)
- Junjie Lu (ORCID: https://orcid.org/0000-0002-8370-7858)
- Yangfan Hu (ORCID: https://orcid.org/0000-0003-4313-1679)
- Jiarui Yang (ORCID: https://orcid.org/0000-0002-0613-5403)
- Jingshen Chu
Institutions
- Boston University (US)
- Tongji University (CN)
- Shanghai Jiao Tong University (CN)
- XinHua Hospital (CN)
- Ruijin Hospital (CN)
- Shanghai Ninth People's Hospital (CN)
- Tongren Hospital (CN)
- Shanghai Pulmonary Hospital (CN)
- Shanghai Sixth People's Hospital (CN)
- Siemens (China) (CN)
- Stanford University (US)
Publication Details
- Journal
- European Radiology
- Published
- 2025-01-09
- DOI
- https://doi.org/10.1007/s00330-024-11331-0
- Citations
- 18
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 24.48
Funders
- Shanghai Municipal Health Commission
- National Natural Science Foundation of China
- Science and Technology Commission of Shanghai Municipality
- Shanghai Jiao Tong University
- School of Medicine, Shanghai Jiao Tong University