A reasoning-distilled LLM achieves 0.926 AUC for one-year lung cancer risk on NLST, but the reasoning/no-reasoning comparison is confounded by dataset size and the reported train/test splits are internally inconsistent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Reasoning Language Model for Personalized Lung Cancer Screening
A reasoning-distilled LLM achieves 0.926 AUC for one-year lung cancer risk on NLST, but the reasoning/no-reasoning comparison is confounded by dataset size and the reported train/test splits are internally inconsistent.