Development and validation of a circulating tumor DNA-based machine learning model for predicting immunotherapy response in non-small cell lung cancer
Ji Xia, Tianchu He, Yong Hu, Daobin Zhou, Dan Zou, Ya Li, Min Zhang, Benlan Li, Minfang Wang, Xian Liu, Zhongjun Huang, Shengfa Su, Jie Peng · 2025
Read Development and validation of a circulating tumor DNA-based machine learning model for predicting immunotherapy response in non-small cell lung cancer by Ji Xia, Tianchu He, Yong Hu, Daobin Zhou, Dan Zou, Ya Li, Min Zhang, Benlan Li, Minfang Wang, Xian Liu, Zhongjun Huang, Shengfa Su, Jie Peng (2025) 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/pmc-12776157.txt.
Description
Ji Xia and co-authors built in 2025 a blood-based model to predict who gains from immune therapy for lung cancer. Marks in use today sort patients poorly. Their model reads tumor DNA floating in blood, taken before care, from a large trial group. A shrink method picked forty-one mutations, and a support vector machine learned to call lasting benefit, meaning response or calm disease for six months or more.
The model held up in two more groups, one trial and one hospital set, with strong accuracy. Patients it scored low-risk lived far longer without growth and overall. The gene set pointed at vessel and signal paths tied to resistance. The team pitches the blood test as a way to spare repeat tissue biopsies.
Catalog record
| CREATOR | Ji Xia, Tianchu He, Yong Hu, Daobin Zhou, Dan Zou, Ya Li, Min Zhang, Benlan Li, Minfang Wang, Xian Liu, Zhongjun Huang, Shengfa Su, Jie Peng |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |