The optimal SVM model from multi-model comparison outperforms conventional criteria in preoperative prediction of ovarian cancer residual disease
Dongdong Ye, Shaodan Lin, Zhuyan Shao, Yunyun Liu, Bin Wu, Chuying Huo, Dongdong Xu, Suen Wai Pang, Chunxian Huang, Jingyan Li, Jiachen Liu, Lijuan Wang, Tao Zhu, Huaiwu Lu · 2026
Read The optimal SVM model from multi-model comparison outperforms conventional criteria in preoperative prediction of ovarian cancer residual disease by Dongdong Ye, Shaodan Lin, Zhuyan Shao, Yunyun Liu, Bin Wu, Chuying Huo, Dongdong Xu, Suen Wai Pang, Chunxian Huang, Jingyan Li, Jiachen Liu, Lijuan Wang, Tao Zhu, Huaiwu Lu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13563794.txt.
Description
Dongdong Ye and thirteen colleagues train a machine learning model to predict, before surgery, whether ovarian cancer operations will leave tumour behind. Leftover disease worsens survival, and failed attempts cost patients dearly, yet the standard scoring rules judge operability imperfectly. Their 2026 multicentre study gathered 203 patients treated between 2017 and 2024, with 153 for training and 50 for validation. Inputs joined texture features from PET/CT scans, metabolic readings from the same images, and blood biomarkers pulled from records. Seven model types were trained and compared under nested cross-checks.
A support vector machine won, scoring 0.896 in training and 0.872 in validation on the accuracy curve, far ahead of the conventional Suidan criteria at 0.696. Tumour shape measures, peak metabolic activity, CA-125, and albumin carried the predictions. Patients the model flagged as high risk did die sooner. The authors say automated scan reading and wider validation stand between the tool and the clinic.
Catalog record
| CREATOR | Dongdong Ye, Shaodan Lin, Zhuyan Shao, Yunyun Liu, Bin Wu, Chuying Huo, Dongdong Xu, Suen Wai Pang, Chunxian Huang, Jingyan Li, Jiachen Liu, Lijuan Wang, Tao Zhu, Huaiwu Lu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44354 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |