Prognostic role of Ki-67 in colorectal carcinoma: Development and evaluation of machine learning prediction models
In algorithmic model predictions, the SVM, RF, and XGBoost models achieved training AUC values of 0.851, 0.948, and 0.872, respectively, with corresponding test set AUC values of 0.795, 0.755, and 0.750, respectively. During external validation, their AUC values for predicting Ki-67 status reached 0.757, 0.749, and 0.783, respectively.
Authors
- Jie Jiang (ORCID: https://orcid.org/0000-0002-2739-6995)
- Da-Tong Zeng (ORCID: https://orcid.org/0000-0002-3338-4122)
- Weijian Huang (ORCID: https://orcid.org/0000-0001-8417-7804)
- Rui Lin (ORCID: https://orcid.org/0000-0002-3846-9301)
- Qi Li (ORCID: https://orcid.org/0000-0003-2120-2261)
- Bin Li (ORCID: https://orcid.org/0000-0002-8442-0154)
- Gang Chen (ORCID: https://orcid.org/0000-0002-8320-6594)
- Min Li (ORCID: https://orcid.org/0000-0002-7113-2700)
- Wan‐Ying Huang (ORCID: https://orcid.org/0000-0003-0461-7182)
- Shi-De Li
Institutions
- Guangxi Medical University (CN)
- First Affiliated Hospital of GuangXi Medical University (CN)
Publication Details
- Journal
- World Journal of Clinical Oncology
- Published
- 2025-08-20
- DOI
- https://doi.org/10.5306/wjco.v16.i8.107306
- Citations
- 1
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.36