AI & dataIn silicoPreprint

Extracting smoking history from clinical notes for lung cancer screening decision support: comparing a structured-judgment model with general-purpose large language models

Figure 1. Study design. Reference labels were fixed before each note was generated.
Open the figure at full size
Figure 1. Study design. Reference labels were fixed before each note was generated.Study design. Reference labels were fixed before each note was generated.Wright et al.

medRxiv

The paper

Vanderbilt University Medical Center

medRxiv · 26 Sep 2026 · Preprint, not peer-reviewed

doi.org/10.64898/2026.09.24.26363906

More on Resources: datasets, atlases and tools