A clinical-radiomic model based on best subset regression for prognostic prediction in natural killer/T-cell lymphoma
Fangfang Tian, Longlan Chen, Xiaoliang Chen, Hua Pang · 2026
Read A clinical-radiomic model based on best subset regression for prognostic prediction in natural killer/T-cell lymphoma by Fangfang Tian, Longlan Chen, Xiaoliang Chen, Hua Pang (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/PMC13560112.txt.
Description
Fangfang Tian and three colleagues build prognostic models for natural killer/T-cell lymphoma from clinical data and PET/CT imaging. Their 2026 retrospective study analyzed 114 patients scanned before treatment. Variables ranged from age and albumin to Epstein-Barr virus status and a radiomics score distilled from scan texture. Three selection methods competed to choose the predictors.
Best subset regression beat the other two approaches. Its survival model combined albumin, viral status, the scan's maximum uptake value, a lumbar-to-liver uptake ratio, and the radiomics score, reaching a three-year area under the curve of 0.883 in the reported results. A separate progression model used age, viral status, and the Ki67 growth marker. Bootstrap checks supported the models internally. The authors offer the combined clinical-radiomic tool for sorting patients by risk and tailoring treatment plans.
Catalog record
| CREATOR | Fangfang Tian, Longlan Chen, Xiaoliang Chen, Hua Pang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36292 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |