Back

Agentic Chart Review from Longitudinal Clinical Notes: a Lung Cancer Guideline Concordance Use Case

Jiang, Y.; He, X.; Ai, X.; Jalal, S.; Maniar, R.; Majji, R. K.; Zhang, Y.; Liu, J.; Fedele, D.; Zhuang, Y.; Hollenbach, J.; Bian, J.

2026-06-03 oncology
10.64898/2026.06.02.26354727 medRxiv
Show abstract

Clinical chart abstraction extracts structured patient variables from longitudinal clinical notes but is labor-intensive and difficult to scale. We evaluated LLM agents for question-guided chart review using lung cancer molecular testing guideline concordance as a use case. Two configurations were compared: (1) sequential note review using metadata and chronology, and (2) the same framework augmented with keyword-based note search. Gold-standard labels were established by human annotators. The search-enabled agent achieved higher accuracy (92.4% vs. 83.5%) and reduced errors by more than half (41 vs. 89) by retrieving evidence from long, heterogeneous note histories. In guideline concordance evaluation, most determinate patient-rule assessments were concordant (80.7%), while most apparent non-concordance reflected missing molecular testing documentation rather than documented care deviations. These results suggest tool-augmented LLM agents can approximate key aspects of human chart review and support scalable information extraction from longitudinal clinical documentation.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.