Body composition radiomics integrated with machine learning to predict prognosis in advanced NSCLC treated with first-line immunochemotherapy and concurrent radiotherapy
Wen Xu, Yongze Yu, GongHua Dai, Jian He, Xin Li, Li Zhang, Xuejiao Zeng, Lungui Hu, Jinyuan Zhang, Qiyu Fang, Lijun Liao · 2026
Read Body composition radiomics integrated with machine learning to predict prognosis in advanced NSCLC treated with first-line immunochemotherapy and concurrent radiotherapy by Wen Xu, Yongze Yu, GongHua Dai, Jian He, Xin Li, Li Zhang, Xuejiao Zeng, Lungui Hu, Jinyuan Zhang, Qiyu Fang, Lijun Liao (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/PMC13527977.txt.
Description
Wen Xu and ten colleagues report a 2026 study using body composition scans to predict outcomes in advanced lung cancer. The patients had non-small cell lung cancer treated with combined immuno-chemotherapy and radiotherapy. The team studied 87 patients. From scans at the third lumbar vertebra they extracted texture features, called radiomics, from muscle and fat tissue.
Six machine learning models were built from the best features. A combined model adding a total fat index performed best. Its area under the curve reached about 0.86 in training data and 0.83 in test data. Patients labeled high risk had clearly shorter progression-free survival. The authors propose the model could flag who benefits most from adding radiotherapy. Larger confirming studies would still be needed.
Catalog record
| CREATOR | Wen Xu, Yongze Yu, GongHua Dai, Jian He, Xin Li, Li Zhang, Xuejiao Zeng, Lungui Hu, Jinyuan Zhang, Qiyu Fang, Lijun Liao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42555 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |